Refresh planner queue for 4710

Co-authored-by: Codex <codex@openai.com>

.github/loop/PRIORITIES.md

@@ -21,7 +21,10 @@ changes, architectural rewrites. Those go to the human.
 
 ## Work queue (ranked)
 
-1. **Add a one-command 0→hero demo entrypoint** ([#4097](https://github.com/micro/go-micro/issues/4097)) — the first-agent, install, debugging, and architecture wayfinding have landed, but the adoption path still asks newcomers to translate docs into several commands before they see the whole services → agents → workflows lifecycle. Add a discoverable `micro` entrypoint that either runs the maintained provider-free 0→hero flow or prints exact commands for it, link it from the first-agent docs, and guard the CLI/docs boundary with focused tests.
+1. **Verify 0-to-hero lifecycle transcript in CI** ([#4711](https://github.com/micro/go-micro/issues/4711)) — #4707 closed the first-agent wayfinding contract, so the highest-value Now-roadmap adoption gap moves to the full 0→hero services → agents → workflows lifecycle. The README, website, and v6.6.0 story now promise scaffold → run → chat → inspect → flow history → deploy dry-run as one walkable path; make that transcript a no-secret CI contract so the on-ramp cannot drift while internals keep hardening.
+2. **Add first-agent debugging golden transcript coverage** ([#4712](https://github.com/micro/go-micro/issues/4712)) — Developer adoption still depends on recovery, not just happy-path setup. The CLI now points users through `micro agent demo`, quickcheck/debug, examples, chat, and inspect; verify those outputs against the maintained first-agent example so a new user who stalls can recover without learning package internals. Keep this scoped to docs/CLI contract coverage, not command redesign.
+3. **Gate mock provider plan-delegate resume scenarios** ([#4713](https://github.com/micro/go-micro/issues/4713)) — #4709 closed the live AtlasCloud nested tool-call rejection gap, but the underlying agent-loop risk remains valuable enough to keep near the top: completed plan steps, notifications, unsafe fallback parsing, and resume semantics must stay deterministic without provider keys. Capture the recent provider failures in mock-based regression coverage before broadening into live-provider conformance.
+4. **Migrate store/postgres from pgx/v4 to pgx/v5** ([#4556](https://github.com/micro/go-micro/issues/4556)) — Security upkeep matters to the service-framework half of the harness, and #4556 is the remaining open enhancement/security item. Keep it below the adoption and agent-loop contracts because it is narrower than the current developer-adoption goal, but do not let reachable dependency risk drift indefinitely.
 
 _Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
 architecture-review pass._

.github/workflows/govulncheck.yml

@@ -0,0 +1,65 @@
+name: govulncheck
+
+# Deterministic vulnerability gate: runs govulncheck (reachability-aware CVE
+# scanner) on every push/PR. Fails on any reachable vulnerability EXCEPT the
+# explicit ALLOWLIST of known-unfixable ones, so a new vuln breaks the build
+# while tracked, no-upstream-fix ones don't. This is the gate the loop's
+# `security` role sits on top of — the role audits; this blocks known CVEs.
+#
+# Make this a required status check on the default branch to enforce it.
+
+on:
+  push:
+    branches: ["**"]
+  pull_request:
+    branches: ["**"]
+
+permissions:
+  contents: read
+
+jobs:
+  govulncheck:
+    name: govulncheck
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: "1.25"
+          check-latest: true
+      - name: Install govulncheck
+        run: go install golang.org/x/vuln/cmd/govulncheck@latest
+      - name: Scan
+        env:
+          # Reachable vulnerabilities with NO upstream fix, accepted for now and
+          # tracked for remediation. Remove an ID the moment its fix lands.
+          #   GO-2026-5004  github.com/jackc/pgx/v4        -> pgx v5 migration (#4556)
+          #   GO-2026-4518  github.com/jackc/pgproto3/v2   -> pgx v5 migration (#4556)
+          ALLOWLIST: "GO-2026-5004 GO-2026-4518"
+        run: |
+          out=$(mktemp)
+          govulncheck ./... >"$out" 2>&1 && code=0 || code=$?
+          cat "$out"
+          if [ "$code" -eq 0 ]; then
+            echo "govulncheck: no reachable vulnerabilities."
+            exit 0
+          fi
+          if [ "$code" -ne 3 ]; then
+            echo "::error::govulncheck failed to run (exit $code)."
+            exit 1
+          fi
+          found=$(grep -oE 'Vulnerability #[0-9]+: GO-[0-9]{4}-[0-9]+' "$out" | grep -oE 'GO-[0-9]{4}-[0-9]+' | sort -u)
+          unexpected=""
+          for id in $found; do
+            case " $ALLOWLIST " in
+              *" $id "*) ;;
+              *) unexpected="$unexpected $id" ;;
+            esac
+          done
+          if [ -n "$unexpected" ]; then
+            echo "::error::Unexpected reachable vulnerabilities:$unexpected"
+            echo "If a fix exists, bump the dependency/toolchain. If genuinely unfixable, add the ID to ALLOWLIST with a tracking issue."
+            exit 1
+          fi
+          echo "govulncheck: only allow-listed (known-unfixable) vulnerabilities present:$found"
+          echo "OK."

.github/workflows/harness.yml

@@ -47,7 +47,7 @@ jobs:
   harness-live:
     name: Provider harnesses (live LLM conformance)
     runs-on: ubuntu-latest
-    # Only on the daily schedule or a manual run — never automatically on
+    # Only on the hourly schedule or a manual run — never automatically on
     # every push/PR, so changes don't quietly burn API credits. Trigger it
     # by hand (Actions → Harness → Run workflow) when changing the agent,
     # flow, or AI internals and you want a real-model check.

.github/workflows/lint.yaml

@@ -21,7 +21,7 @@ jobs:
       - name: Set up Go
         uses: actions/setup-go@v5
         with:
-          go-version: 1.24
+          go-version: "1.25"
           check-latest: true
           cache: true
       - name: golangci-lint

.github/workflows/loop-release.yml

@@ -1,9 +1,11 @@
 name: "Loop: Release"
 
-# Generated by `micro loop init`. Cuts the next PATCH tag
-# (vMAJOR.MINOR.PATCH+1) when the default branch has new commits
-# since the latest such tag, and pushes it with a PAT (CODEX_TRIGGER_TOKEN) so any
-# tag-triggered release workflow fires. Minor/major bumps stay with a human.
+# Generated by `micro loop init`. Cuts the next tag when the default branch has
+# new commits since the latest one, and pushes it with a PAT (CODEX_TRIGGER_TOKEN)
+# so any tag-triggered release workflow fires. The bump reflects what shipped,
+# read from the CHANGELOG [Unreleased] section: new features (Added/Changed) cut
+# a MINOR; fixes/docs only cut a PATCH; breaking changes are skipped so a MAJOR
+# stays a human decision.
 #
 # The tag MUST be pushed with a PAT, not the default GITHUB_TOKEN: a tag pushed
 # by GITHUB_TOKEN does not trigger other workflows (Actions blocks that recursion).
@@ -66,11 +68,30 @@ jobs:
             [0-9]*.[0-9]*.[0-9]*) ;;
             *) echo "unexpected tag shape: $LATEST" ; exit 1 ;;
           esac
-          NEXT="v${major}.${minor}.$((patch + 1))"
-          echo "cutting: $NEXT ($COUNT commits since $LATEST)"
+
+          # Choose the bump from what actually shipped, read from the CHANGELOG
+          # [Unreleased] section (kept current by the coherence role):
+          #   new features (### Added / ### Changed) -> MINOR
+          #   fixes/docs only                        -> PATCH
+          #   breaking (### Removed / "(breaking)")  -> skip; a major is a human call
+          UNRELEASED=""
+          if [ -f CHANGELOG.md ]; then
+            UNRELEASED=$(awk '/^## \[Unreleased\]/{f=1; next} /^## \[/{f=0} f' CHANGELOG.md)
+          fi
+          if printf '%s\n' "$UNRELEASED" | grep -qiE '^### Removed|^### Changed \(breaking\)|BREAKING'; then
+            echo "CHANGELOG [Unreleased] contains breaking changes — a major release is a human decision. Skipping."
+            exit 0
+          elif printf '%s\n' "$UNRELEASED" | grep -qE '^### (Added|Changed)'; then
+            NEXT="v${major}.$((minor + 1)).0"
+            KIND="minor (new features)"
+          else
+            NEXT="v${major}.${minor}.$((patch + 1))"
+            KIND="patch (fixes/docs only)"
+          fi
+          echo "cutting: $NEXT — $KIND ($COUNT commits since $LATEST)"
 
           git config user.name "loop release bot"
           git config user.email "noreply@users.noreply.github.com"
-          git tag -a "$NEXT" -m "Release $NEXT — automated patch ($COUNT commits since $LATEST)"
+          git tag -a "$NEXT" -m "Release $NEXT — automated $KIND ($COUNT commits since $LATEST)"
           git push "https://x-access-token:${RELEASE_TOKEN}@github.com/${REPO}.git" "$NEXT"
           echo "Pushed $NEXT."

.github/workflows/loop-triage.yml

@@ -8,7 +8,7 @@ name: "Loop: Triage"
 
 on:
   workflow_run:
-    workflows: ["Harness (E2E)", "Lint", "Run Tests"]
+    workflows: ["Harness (E2E)", "Lint", "Run Tests", "govulncheck"]
     types: [completed]
 
 permissions:

.github/workflows/tests.yaml

@@ -19,7 +19,7 @@ jobs:
       - name: Set up Go
         uses: actions/setup-go@v3
         with:
-          go-version: 1.24
+          go-version: "1.25"
           check-latest: true
           cache: true
       - name: Get dependencies
@@ -56,7 +56,7 @@ jobs:
       - name: Set up Go
         uses: actions/setup-go@v3
         with:
-          go-version: 1.24
+          go-version: "1.25"
           check-latest: true
           cache: true
       - name: Get dependencies

CHANGELOG.md

@@ -5,9 +5,10 @@ All notable changes to Go Micro are documented here.
 Format follows [Keep a Changelog](https://keepachangelog.com/) and versions
 follow [Semantic Versioning](https://semver.org/), matching the git tags and
 [GitHub releases](https://github.com/micro/go-micro/releases) (`v6.MINOR.PATCH`).
-Patch releases are cut automatically as the loop merges improvements; the
-`[Unreleased]` section below is kept current between tags and rolled into the
-next version when it ships.
+Releases are cut automatically as the loop merges improvements — a **minor**
+bump when new features land (`### Added`/`### Changed`), a **patch** when it's
+fixes/docs only; major bumps stay a human decision. The `[Unreleased]` section
+below is kept current between tags and rolled into the next version when it ships.
 
 > Earlier `2026.0x` headings are historical calendar-style markers from before
 > v6 tagging; they are kept for continuity and not reused.
@@ -16,6 +17,177 @@ next version when it ships.
 
 ## [Unreleased]
 
+### Added
+- **First-agent chat/inspect fixture** — the maintained first-agent CLI fixture now covers chat and inspect boundaries together. (`internal/harness/`, `cmd/micro/`)
+- **Zero-to-hero inspect transcript check** — the 0→hero harness now verifies the inspect transcript path stays visible in the lifecycle walkthrough. (`internal/harness/zero-to-hero-ci/`, `internal/website/docs/`)
+
+### Changed
+- **Plan-delegate plan persistence** — plan/delegate runs now persist plan state more defensively across harness scenarios. (`agent/`, `internal/harness/`)
+
+### Fixed
+- **Zero-to-hero fixture output race** — 0→hero fixture output is less race-prone during harness runs. (`internal/harness/zero-to-hero-ci/`)
+
+---
+
+## [6.6.0] - July 2026
+
+### Added
+- **First-agent guide chain contract** — the harness now verifies the install → demo → examples → 0→hero guide chain stays connected for new agent builders. (`internal/harness/`, `internal/website/docs/`)
+- **First-agent docs wayfinding guard** — the local harness now includes a focused no-network check for first-agent and 0→hero docs links. (`Makefile`, `internal/harness/`)
+- **First-agent quickcheck breadcrumbs** — first-agent docs now surface quickcheck wayfinding for install, scaffold, chat, inspect, and recovery paths. (`internal/website/docs/`, `README.md`)
+- **First-agent chat wayfinding verification** — the harness now verifies first-agent chat wayfinding remains discoverable from the public docs route. (`internal/harness/`, `internal/website/docs/`)
+
+### Changed
+- **Universe A2A reachability probe** — the universe harness now exercises A2A reachability more defensively. (`internal/harness/`)
+- **AtlasCloud workspace repair fallback** — AtlasCloud fallback handling now recovers workspace-repair tool calls more reliably. (`ai/atlascloud/`, `agent/`)
+- **AtlasCloud empty-argument tool repair** — AtlasCloud text tool-call repair now handles empty-argument calls more consistently. (`ai/atlascloud/`, `agent/`)
+
+### Removed
+- **`go-micro.dev/v6/ai/flow`** — the alias-only backward-compatibility shim is removed; import the canonical [`go-micro.dev/v6/flow`](flow) instead (same types and functions). It had no internal callers. (`ai/flow/`)
+
+### Fixed
+- **A2A fallback artifact text** — A2A fallback responses now avoid leaking provider artifact text into agent-visible output. (`gateway/a2a/`, `agent/`)
+- **Launch readiness notification replays** — launch-readiness notification replay paths now deduplicate repeated side effects. (`agent/`, `internal/harness/`)
+- **Plan-delegate harness cleanup** — plan/delegate harness cleanup is more reliable after conformance runs. (`internal/harness/`)
+- **AtlasCloud spoken notify replays** — AtlasCloud fallback handling now collapses spoken notification replays more consistently. (`ai/atlascloud/`, `agent/`)
+- **Agent-flow onboarding side effects** — onboarding side-effect checks are more stable across the agent-flow harness. (`agent/`, `internal/harness/`)
+- **Plan-delegate plan-only side effects** — plan/delegate recovery now preserves plan-only side effects more reliably. (`agent/`, `internal/harness/`)
+- **Checkpointed tool result recording** — checkpoint resume paths now guard tool-result recording against duplicate or stale writes. (`agent/`)
+- **Agent timeout notification completion** — universe runs now finalize observed notifications more reliably after agent timeouts. (`agent/`, `internal/harness/`)
+- **Completed plan-delegate side effects** — completed plan/delegate side effects are accepted more consistently in recovery paths. (`agent/`, `internal/harness/`)
+- **Agent-flow onboarding notifications** — agent-flow onboarding notification recovery is more reliable across replay scenarios. (`agent/`, `internal/harness/`)
+
+### Documentation
+- **Agent-agnostic mention model** — loop docs now describe the mention-driven agent model without binding it to one coding agent. (`internal/docs/`, `.github/loop/`)
+- **First-agent quickcheck docs** — public docs now surface the first-agent quickcheck path for faster troubleshooting. (`internal/website/docs/`)
+- **Agent resume breadcrumbs** — docs now add clearer resume breadcrumbs for checkpointed agent runs. (`internal/website/docs/`)
+
+### Security
+- **Govulncheck vulnerability gate** — CI now includes a govulncheck gate and wires vulnerability failures into loop triage. (`.github/workflows/`, `cmd/micro/loop/`)
+- **Dependency vulnerability patches** — toolchain and dependency updates patch reachable CVEs across the project. (`go.mod`, `go.sum`)
+
+---
+
+## [6.5.0] - July 2026
+
+### Added
+- **Agent stream provider conformance** — provider conformance now covers agent streaming behavior so streaming-capable providers stay aligned with the harness contract. (`agent/`, `internal/harness/`)
+- **First-agent docs CLI parity check** — the harness now verifies first-agent docs commands match the CLI wayfinding surface. (`internal/harness/`, `internal/website/docs/`)
+- **Focused CLI inner-loop contract** — the local harness now covers scaffold, run/chat/inspect, and deploy dry-run boundaries in one first-run contract. (`internal/harness/`)
+- **First-agent wayfinding breadcrumbs** — first-agent docs and examples now have locked breadcrumb coverage from the README through the runnable examples. (`README.md`, `internal/website/docs/`, `examples/`)
+- **Offline `micro new` contract** — project scaffolding now has an offline contract so the first service path stays runnable without network access. (`cmd/micro/`, `internal/harness/`)
+
+### Changed
+- **Provider model call timeouts** — model call timeout enforcement now wraps provider calls more defensively, reducing hangs in agent and harness paths. (`agent/`, `ai/`)
+- **First-agent harness diagnostics** — getting-started harness logs now make first-run and 0→hero failures easier to locate. (`internal/harness/`)
+- **MiniMax streaming conformance** — MiniMax streaming coverage now exercises broader provider conformance behavior. (`ai/minimax/`, `internal/harness/`)
+- **AtlasCloud streaming tool capability** — AtlasCloud tool-streaming capability detection is now aligned with provider fallback behavior. (`ai/atlascloud/`, `agent/`)
+
+### Fixed
+- **Partial text tool calls** — text tool-call recovery now repairs partial function-style calls more reliably before fallback parsing continues. (`agent/`)
+- **Retry timeout test stability** — retry timeout coverage is less race-prone. (`agent/`)
+- **Checkpointed tool-call resume** — resumed agent runs now preserve checkpointed tool calls across startup resume paths. (`agent/`)
+- **Model retry backoff contracts** — retry backoff behavior now has focused contract coverage for model-call failures. (`agent/`, `ai/`)
+- **AtlasCloud conformance markers** — AtlasCloud fallback paths now preserve conformance markers through tool-call recovery. (`ai/atlascloud/`, `agent/`)
+- **AtlasCloud delegate text fallback** — delegate text fallback recovery is more reliable for AtlasCloud responses. (`ai/atlascloud/`, `agent/`)
+- **AtlasCloud incomplete plan repairs** — incomplete plan repair paths now recover more consistently in AtlasCloud fallback handling. (`ai/atlascloud/`, `agent/`)
+- **AtlasCloud partial text tool calls** — AtlasCloud fallback handling now repairs partial text-rendered tool calls more reliably. (`ai/atlascloud/`, `agent/`)
+
+### Documentation
+- **Roadmap agent status** — public roadmap docs now reflect the current agent lifecycle status more consistently. (`internal/website/docs/`)
+- **Agent resume limits** — docs now describe checkpoint resume boundaries for agent runs. (`internal/website/docs/`)
+- **Zero-to-hero harness boundaries** — docs now clarify which 0→hero lifecycle checks are maintained by the local harness. (`internal/website/docs/`, `internal/harness/`)
+- **First-agent wayfinding guard** — first-agent docs wayfinding now has tighter guard coverage around the README, docs, and examples chain. (`README.md`, `internal/website/docs/`)
+
+---
+
+## [6.4.0] - July 2026
+
+### Added
+- **Provider HTTP retry signals** — provider failures now preserve HTTP status and `Retry-After` details so retry classification and backoff can respond to rate limits and unavailable providers. (`ai/`)
+- **Zero-to-hero deploy dry-run verification** — the maintained 0→hero harness now covers deploy dry-run boundaries for the services → agents → workflows lifecycle. (`internal/harness/`)
+- **First-agent CLI wayfinding verification** — the harness now checks that first-agent CLI wayfinding stays discoverable. (`internal/harness/`)
+- **Agent startup resume verification** — agent startup resume now has focused checkpoint coverage. (`agent/`, `internal/harness/`)
+- **Direct first-agent chat prompts** — first-agent flows can accept direct chat prompts, reducing friction in the first useful conversation. (`cmd/micro/`, `agent/`)
+- **Workflow run info on tool spans** — agent tool spans now include workflow run details for easier trace correlation. (`agent/`, `flow/`)
+
+### Fixed
+- **Stream fallback memory** — unsupported streaming attempts no longer leave stale duplicate user turns before fallback paths continue with non-streaming agent calls. (`agent/`)
+- **Function-style text tool calls** — agent fallback parsing now recognizes provider replies that render tools as function-style calls, including nested JSON arguments. (`agent/`)
+- **Plan/delegate notify recovery** — plan-delegate recovery now waits for recovered notify side effects and routes retries through the communications agent that owns the notification. (`internal/harness/`)
+- **Onboarding side-effect enforcement** — the agent-flow harness now fails when required onboarding side effects are missing, making lifecycle regressions visible. (`internal/harness/`)
+- **Plan/delegate notify stability** — notify recovery is more deterministic across retry and replay paths. (`agent/`, `internal/harness/`)
+- **AtlasCloud MiniMax tool fallback** — AtlasCloud MiniMax service-tool fallback now handles 400 responses and follow-up retries more reliably. (`ai/atlascloud/`, `agent/`)
+
+### Documentation
+- **First-agent docs wayfinding guard** — the local harness now includes a focused no-network check for first-agent and 0→hero docs links. (`Makefile`, `internal/harness/`)
+
+---
+
+## [6.3.18] - July 2026
+
+### Added
+- **StreamAsk close cancellation** — agent streaming calls now cancel promptly when their runner closes, avoiding orphaned stream work. (`agent/`)
+- **Agent resume pending helper** — agent durability now has a focused helper for resuming pending checkpointed runs. (`agent/`)
+- **Agent tool retry tracing** — agent traces now include tool retry attempts for easier debugging of retry/fallback behavior. (`agent/`)
+- **Shared-broker universe harness** — the universe harness now runs against the shared broker path, improving coverage of the same runtime wiring used by services, agents, and workflows. (`internal/harness/`)
+
+### Fixed
+- **Plan/delegate retry idempotency** — agent retries now preserve side-effect and notification dedupe across conformance retry paths, including completion and owner-notification edge cases. (`agent/`, `internal/harness/`)
+- **AtlasCloud text tool calls** — AtlasCloud fallback handling now recovers more text-rendered tool calls from OpenAI-compatible responses. (`ai/atlascloud/`, `agent/`)
+- **OpenAI-compatible text tool calls** — OpenAI-compatible providers now recover text-rendered tool calls more reliably. (`agent/`)
+- **AtlasCloud multi-step follow-ups** — AtlasCloud tool fallback handling now continues multi-step tool follow-up paths more reliably. (`ai/atlascloud/`, `agent/`)
+
+### Documentation
+- **Agent debugging quickcheck** — docs now include a focused quickcheck path for first-agent debugging. (`internal/website/docs/`)
+- **Website first-agent examples map** — website docs now link the maintained examples wayfinding map for the first-agent route. (`internal/website/docs/`)
+- **Examples wayfinding index** — examples docs now provide a central map for first-agent, support, and interop examples. (`examples/`, `internal/website/docs/`)
+
+---
+
+## [6.3.17] - July 2026
+
+### Added
+- **First-agent examples CLI wayfinding** — `micro examples` now prints the maintained provider-free first-agent examples in copy/paste order. (`cmd/micro/`)
+- **0→hero CLI entrypoint** — `micro zero-to-hero` now points developers at the maintained no-secret services → agents → workflows harness and runnable examples. (`cmd/micro/`)
+- **First-agent tutorial smoke harness** — the first-agent tutorial path now has smoke coverage to keep the no-secret on-ramp runnable. (`internal/harness/`)
+- **No-secret agent debugging smoke** — the no-secret agent debugging path now has smoke coverage for the first-agent troubleshooting flow. (`internal/harness/`)
+- **Durable checkpoint resume smoke coverage** — durable agent resume after checkpointing now has focused smoke coverage. (`agent/`, `internal/harness/`)
+
+### Fixed
+- **Plan/delegate notify replays** — duplicate and replayed plan-delegate notifications are now idempotent, so resumed runs do not duplicate completed notifications. (`agent/`, `internal/harness/`)
+- **Provider conformance scheduling** — provider conformance workflow dispatches now guard their scheduling path more reliably. (`.github/workflows/`)
+- **Plan/delegate notification completion** — delegated notifications now preserve plan completion state more reliably, including duplicate, paraphrased, and delegated-owner notification paths. (`agent/`, `internal/harness/`)
+- **AtlasCloud tool fallback** — AtlasCloud built-in tool schemas and follow-up tool fallback handling now recover conformance delegate retries more reliably. (`ai/atlascloud/`, `agent/`)
+- **Agent conformance retry completion** — conformance retry prompts and completion handling are more deterministic for delegated agent runs. (`agent/`, `internal/harness/`)
+
+### Documentation
+- **First-agent quickstart numbering** — the first-agent on-ramp numbering is consistent across the README and website docs. (`README.md`, `internal/website/docs/`)
+- **First-agent inspect command** — docs now use the maintained `micro inspect agent <name>` form. (`README.md`, `internal/website/docs/`)
+- **`micro loop` quickstart wayfinding** — docs now surface the loop quickstart from the public docs index and README wayfinding. (`README.md`, `internal/website/docs/`)
+
+---
+
+## [6.3.16] - July 2026
+
+### Added
+- **No-secret agent demo CLI** — the CLI now surfaces `micro agent demo`, making the provider-free first-agent path discoverable from the installed binary. (`cmd/micro/`)
+- **First-agent recovery doctor** — first-agent recovery checks now help diagnose install, scaffold, and provider setup issues before the live agent run. (`cmd/micro/`, `internal/website/docs/guides/`)
+
+### Changed
+- **Architecture lifecycle docs** — the architecture guide now leads with the services → agents → workflows lifecycle and the first-agent on-ramp. (`internal/website/docs/architecture.md`)
+- **First-agent on-ramp** — README and website docs now lead new users through install troubleshooting, no-secret demos, the smallest first-agent example, debugging, and the 0→hero reference path in the same order. (`README.md`, `internal/website/docs/`)
+
+### Fixed
+- **Config close idempotency** — config close paths now tolerate repeated closes safely. (`config/`)
+- **OpenTelemetry child span events** — agent traces now preserve child span events more reliably. (`agent/`)
+
+### Documentation
+- **Security reporting** — security docs now route vulnerability reports through GitHub Security Advisories. (`SECURITY.md`, `internal/website/docs/`)
+- **Install troubleshooting** — the first-agent on-ramp now includes clearer install and PATH recovery guidance. (`internal/website/docs/guides/install-troubleshooting.md`)
+
+---
+
 ## [6.3.15] - July 2026
 
 ### Added

Makefile

@@ -8,7 +8,7 @@ LDFLAGS = -X $(GIT_IMPORT).BuildDate=$(BUILD_DATE) -X $(GIT_IMPORT).GitCommit=$(
 # GORELEASER_DOCKER_IMAGE = ghcr.io/goreleaser/goreleaser-cross:v1.25.7
 GORELEASER_DOCKER_IMAGE = ghcr.io/goreleaser/goreleaser:latest
 
-.PHONY: test test-race test-coverage harness install-smoke provider-conformance-mock provider-conformance lint fmt install-tools proto clean help gorelease-dry-run gorelease-dry-run-docker
+.PHONY: test test-race test-coverage harness inner-loop cli-wayfinding docs-wayfinding install-smoke provider-conformance-mock provider-conformance lint fmt install-tools proto clean help gorelease-dry-run gorelease-dry-run-docker
 
 # Default target
 help:
@@ -19,6 +19,9 @@ help:
 	@echo "  make test-coverage - Run tests with coverage"
 	@echo "  make lint          - Run linter"
 	@echo "  make harness       - Run deterministic getting-started and end-to-end harnesses"
+	@echo "  make inner-loop    - Verify scaffold → run/chat/inspect → deploy dry-run contract"
+	@echo "  make cli-wayfinding - Verify installed first-agent CLI wayfinding commands"
+	@echo "  make docs-wayfinding - Verify first-agent docs/CLI wayfinding stays in sync"
 	@echo "  make install-smoke - Verify the local install.sh and first-run CLI smoke path"
 	@echo "  make provider-conformance-mock - Run cross-provider harness with deterministic mock provider"
 	@echo "  make provider-conformance - Run harnesses against configured live providers"
@@ -49,12 +52,37 @@ test-coverage:
 # This mirrors the default CI path so local dogfooding catches scaffold,
 # run/chat/inspect, and 0→hero regressions before a PR is opened.
 harness:
-	$(MAKE) install-smoke
-	go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
+	$(MAKE) cli-wayfinding
+	$(MAKE) inner-loop
 	./internal/harness/zero-to-hero-ci/run.sh
 	go run ./internal/harness/agent-flow
 	$(MAKE) provider-conformance-mock
 
+# Focused provider-free CLI inner-loop contract: scaffold a service, keep the
+# run/chat/inspect commands discoverable, and prove deploy dry-run reaches the
+# documented boundary without remote side effects. Use this when README/docs/CLI
+# drift is the concern and the full runtime harness is more than you need.
+inner-loop:
+	go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
+	go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestZeroToHeroCLIBoundaries|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1
+	go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
+	go test ./internal/harness/zero-to-hero-ci -run 'TestZeroToHeroDeployDryRunCommandSmoke|TestNoSecretFirstAgentDebuggingSmoke|TestYourFirstAgentTutorialSmoke' -count=1
+
+# Verify the installed CLI keeps the first-agent on-ramp commands discoverable.
+# This guards the no-secret commands README/docs recommend (`micro agent demo`,
+# `micro examples`, and `micro zero-to-hero`) as a CI contract.
+cli-wayfinding:
+	go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestExamplesWayfindingIndexStaysLinked|TestExamplesCommandPointsAtWayfindingIndex|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1
+	$(MAKE) docs-wayfinding
+	$(MAKE) install-smoke
+
+# Verify the README and website first-agent/0→hero wayfinding links resolve to
+# maintained local docs and examples. This is a focused no-network guard for the
+# developer-adoption on-ramp.
+docs-wayfinding:
+	go test ./internal/harness/zero-to-hero-ci -run 'TestFirstAgentWayfinding' -count=1
+	go test ./cmd/micro -run 'TestFirstAgentDocsMatchCLIOutput|TestFirstAgentWalkthroughCLIBoundaries' -count=1
+
 # Verify the documented install script and first-run CLI command boundaries without
 # provider keys or network access.
 install-smoke:
@@ -110,4 +138,3 @@ gorelease-dry-run:
 		-w /$(NAME) \
 		$(GORELEASER_DOCKER_IMAGE) \
 		--clean --verbose --skip=publish,validate --snapshot
-

README.md

@@ -1,4 +1,4 @@
-# Go Micro [![Go.Dev reference](https://img.shields.io/badge/go.dev-reference-007d9c?logo=go&logoColor=white&style=flat-square)](https://pkg.go.dev/go-micro.dev/v6?tab=doc) [![Go Report Card](https://goreportcard.com/badge/github.com/go-micro/go-micro)](https://goreportcard.com/report/github.com/go-micro/go-micro) [![Discord](https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white&style=flat-square)](https://discord.gg/G8Gk5j3uXr)
+# Go Micro [![Go.Dev reference](https://img.shields.io/badge/go.dev-reference-007d9c?logo=go&logoColor=white&style=flat-square)](https://pkg.go.dev/go-micro.dev/v6?tab=doc) [![Discord](https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white&style=flat-square)](https://discord.gg/G8Gk5j3uXr)
 
 Go Micro is an **agent harness** and service framework for Go.
 
@@ -31,6 +31,7 @@ Running Go Micro in production, or building on it and want help? Paid **support,
 - [Building Agents](#building-agents) — [Plan & Delegate](#plan--delegate), [Pluggable](#batteries-included-pluggable), [Paid tools (x402)](#paid-tools-x402), [A2A](#reachable-by-other-agents-a2a)
 - [Features](#features)
 - [CLI](#cli)
+- [Autonomous improvement loop](#autonomous-improvement-loop)
 - [Multi-Service Projects](#multi-service-projects)
 - [Data Model](#data-model)
 - [AI Providers](#ai-providers)
@@ -77,6 +78,12 @@ access or provider keys, use:
 make install-smoke
 ```
 
+To verify the focused CLI inner-loop contract — scaffold → run/chat/inspect → deploy dry-run — use:
+
+```bash
+make inner-loop
+```
+
 To run the broader local contract (including the [0→hero services → agents → workflows path](internal/website/docs/guides/zero-to-hero.md),
 chat/inspect CLI boundaries, and deploy dry-run), use:
 
@@ -90,19 +97,46 @@ After install and the first `micro new`/`micro run` smoke check, take the
 walkable agent path in this order:
 
 1. [Install troubleshooting](internal/website/docs/guides/install-troubleshooting.md) — verify the binary installer or `go install`, `PATH`, `micro --version`, and the no-secret smoke path before agent work.
+
+Run `make docs-wayfinding` to verify the focused no-secret docs/CLI contract that keeps these README and website commands aligned with the installed CLI.
+
 2. `micro agent demo` — print the provider-free first-agent demo command and next docs steps from the installed CLI.
-3. [Smallest first-agent example](examples/first-agent/) — run one service-backed agent with a mock model and no provider key.
-4. [No-secret first-agent transcript](internal/website/docs/guides/no-secret-first-agent.md) — run the
+3. `micro agent quickcheck` (or `micro agent debug`) — when scaffold → run → chat → inspect stalls, print the short recovery map before you dive into the full debugging guide.
+4. `micro examples` — print the maintained provider-free runnable examples in copy/paste order.
+5. `micro zero-to-hero` — print the maintained one-command no-secret lifecycle harness and runnable examples.
+6. [Examples wayfinding index](examples/INDEX.md) — choose the smallest no-secret first-agent, maintained [0→hero support reference](examples/support/), and next interop examples from one map.
+7. [Smallest first-agent example](examples/first-agent/) — run one service-backed agent with a mock model and no provider key.
+8. [No-secret first-agent transcript](internal/website/docs/guides/no-secret-first-agent.md) — run the
    maintained support agent with a mock model and see services → agents → workflows succeed without a key.
-5. [Your First Agent](internal/website/docs/guides/your-first-agent.md) — build a
+9. [Your First Agent](internal/website/docs/guides/your-first-agent.md) — build a
    service-backed agent and talk to it with `micro chat`.
-6. [Debugging your agent](internal/website/docs/guides/debugging-agents.md) — use
-   `micro agent inspect`, run history, memory, and provider checks when the first
-   conversation does something unexpected.
-7. [0→hero Reference](internal/website/docs/guides/zero-to-hero.md) — complete the
+10. [Debugging your agent](internal/website/docs/guides/debugging-agents.md) — use
+   `micro agent preflight` before `micro run`, `micro agent doctor` after `micro run`,
+   then `micro chat` and `micro inspect agent <name>` to recover run history, memory,
+   and provider checks when the first conversation does something unexpected.
+11. [0→hero Reference](internal/website/docs/guides/zero-to-hero.md) — complete the
    services → agents → workflows loop with scaffold, run, chat, inspect, flow
    history, and deploy dry-run commands that match the maintained harness.
 
+### Autonomous improvement loop
+
+Want the same services → agents → workflows lifecycle applied to your
+repository? `micro loop` scaffolds the autonomous improvement loop used by Go
+Micro itself: a North Star, ranked issue queue, role prompts, GitHub Actions
+workflows, and verification for CI-gated PRs.
+
+```bash
+micro loop init --roles all
+micro loop verify
+```
+
+Before turning on the schedule, configure a dispatch token such as
+`CODEX_TRIGGER_TOKEN`, protect the default branch with required CI checks
+(`go build ./...`, `go test ./...`, and `golangci-lint run ./...` for this
+repository), and seed `.github/loop/PRIORITIES.md` with one scoped issue per
+increment. See the [`micro loop` quickstart](internal/website/docs/guides/micro-loop.md)
+for the setup checklist and operating model.
+
 ### Generate from a prompt — with an LLM key
 
 Set a provider key, describe what you want, and the AI designs services, writes handlers, compiles, and starts them:

ROADMAP.md

@@ -14,8 +14,9 @@ The full, current roadmap lives at **[go-micro.dev/docs/roadmap](https://go-micr
 
 ## Where we are (v6)
 
-Services, agents (`plan`/`delegate`, guardrails, memory, tool middleware), durable
-flows, the MCP and A2A gateways (both directions, including A2A streaming,
+Services, agents (`plan`/`delegate`, guardrails, memory, tool middleware,
+checkpoint/resume, and OpenTelemetry run spans), durable flows, the MCP and A2A
+gateways (both directions, including A2A streaming,
 push notifications, and multi-turn continuation), x402 paid tools, secure by
 default.
 
@@ -39,11 +40,24 @@ default.
   propagation, retry/backoff.
 - **Getting-started contract** — define and CI-verify the 0→1 and 0→hero flows.
 
+## Shipped agent depth
+
+- **Durable agent loop** — opt-in `Checkpoint` support lets agent `Ask` and
+  streaming runs persist, list pending work, and resume without replaying completed
+  tool calls. Human-input pauses resume through explicit input helpers.
+- **Agent observability** — agent `RunInfo` now feeds OpenTelemetry spans/events
+  across runs, model turns, tool calls, retries, delegation lineage, and resume
+  checkpoints.
+
 ## Next — agentic depth
 
-- **Durable agent loop** — resume a long run via `Checkpoint` (flows already do).
 - **Streaming** — broaden provider-backed `ai.Stream` coverage and keep chat/A2A streaming end to end.
-- **Agent observability** — `RunInfo` → OpenTelemetry spans.
+- **Resume operations polish** — keep improving CLI/docs breadcrumbs for finding
+  pending agent runs and deciding whether to call resume, resume-input, or stream
+  resume in production.
+- **Observability hardening** — keep span attributes and run inspection coherent
+  across agents, flows, and gateways as more providers and workflow paths are
+  exercised.
 
 ## Later
 

agent/agent.go

@@ -33,6 +33,7 @@ import (
 	_ "go-micro.dev/v6/ai/atlascloud"
 	_ "go-micro.dev/v6/ai/gemini"
 	_ "go-micro.dev/v6/ai/groq"
+	_ "go-micro.dev/v6/ai/minimax"
 	_ "go-micro.dev/v6/ai/mistral"
 	_ "go-micro.dev/v6/ai/ollama"
 	_ "go-micro.dev/v6/ai/openai"
@@ -99,6 +100,17 @@ type agentImpl struct {
 	// holding mu. Tool execution updates it so resumed runs can reuse
 	// completed tool results without replaying side effects.
 	currentRun *flow.Run
+
+	// delegateCalls collapses concurrent equivalent delegate tool calls so a
+	// provider replay cannot fan out duplicate delegated side effects before the
+	// durable delegate-result cache is written.
+	delegateMu    sync.Mutex
+	delegateCalls map[string]*delegateCall
+
+	// stopCh lets Stop unblock Run. Without this, tests and harnesses that
+	// start agents in goroutines can leave Run parked forever after the RPC
+	// server has been stopped.
+	stopCh chan struct{}
 }
 
 // New creates a new Agent.
@@ -221,16 +233,18 @@ func (a *agentImpl) Stream(ctx context.Context, message string) (ai.Stream, erro
 	if err != nil {
 		return nil, fmt.Errorf("discover tools: %w", err)
 	}
-	a.mem.Add("user", message)
+	messages := append([]ai.Message(nil), a.mem.Messages()...)
+	messages = append(messages, ai.Message{Role: "user", Content: message})
 	stream, err := a.model.Stream(ctx, &ai.Request{
 		Prompt:       message,
 		SystemPrompt: a.buildPrompt(),
 		Tools:        toolList,
-		Messages:     a.mem.Messages(),
+		Messages:     messages,
 	})
 	if err != nil {
 		return nil, err
 	}
+	a.mem.Add("user", message)
 	return &memoryRecordingStream{stream: stream, memory: a.mem}, nil
 }
 
@@ -244,6 +258,31 @@ func Pending(ctx context.Context, ag Agent) ([]flow.Run, error) {
 	return a.pending(ctx)
 }
 
+// ResumePending resumes every checkpointed agent run that has not completed
+// yet, in the same oldest-first order returned by Pending.
+//
+// It is a convenience for service startup and recovery loops: after recreating
+// an agent with the same checkpoint store, call ResumePending to drain the
+// durable backlog without listing and resuming each run manually. If any run
+// fails again, ResumePending stops and returns that run id with the error so
+// callers can log, alert, or retry later without hiding the failing run.
+func ResumePending(ctx context.Context, ag Agent) (string, error) {
+	a, ok := ag.(*agentImpl)
+	if !ok {
+		return "", fmt.Errorf("agent resume pending: unsupported agent implementation %T", ag)
+	}
+	runs, err := a.pending(ctx)
+	if err != nil {
+		return "", err
+	}
+	for _, run := range runs {
+		if _, err := a.resume(ctx, run.ID); err != nil {
+			return run.ID, err
+		}
+	}
+	return "", nil
+}
+
 func (a *agentImpl) ask(ctx context.Context, message, parentRunID string) (*Response, error) {
 	a.mu.Lock()
 	defer a.mu.Unlock()
@@ -316,6 +355,8 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 		})
 		if err != nil {
 			run.Status = agentRunFailureStatus(err)
+			failureKind := ai.ClassifyError(err)
+			attempts := agentRunFailureAttempts(err)
 			err = agentOperationalError(err)
 			if a.currentRun != nil {
 				run.Steps = a.currentRun.Steps
@@ -324,7 +365,9 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 				run.Steps = []flow.StepRecord{{Name: agentAskStep}}
 			}
 			run.Steps[0].Status = run.Status
+			run.Steps[0].Attempts = attempts
 			run.Steps[0].Error = err.Error()
+			run.Steps[0].ErrorKind = string(failureKind)
 			_ = a.saveRun(ctx, run)
 			return nil, err
 		}
@@ -381,6 +424,15 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 				continue
 			}
 		}
+		if toolName := partialTextToolCallName(resp.Reply, toolList); len(resp.ToolCalls) == 0 && toolName != "" && planCompletionTurn < maxPlanCompletionTurns {
+			if resp.Reply != "" {
+				a.mem.Add("assistant", resp.Reply)
+			}
+			message = fmt.Sprintf("Your previous response started a %q tool call but did not finish valid tool-call markup or JSON arguments, so no tool was executed. Retry the same step now by emitting one complete valid tool call for %q. Do not describe the action in prose, and do not claim completion until the tool call succeeds.", toolName, toolName)
+			a.mem.Add("user", message)
+			messages = a.mem.Messages()
+			continue
+		}
 		break
 	}
 
@@ -399,9 +451,13 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 		reply += resp.Answer
 	}
 
+	completedToolCalls := checkpointToolCalls(run.Steps)
+	if a.currentRun != nil {
+		completedToolCalls = checkpointToolCalls(a.currentRun.Steps)
+	}
 	res := &Response{
 		Reply:     reply,
-		ToolCalls: resp.ToolCalls,
+		ToolCalls: mergeCheckpointToolCalls(completedToolCalls, resp.ToolCalls),
 		Agent:     a.opts.Name,
 		RunID:     a.runID,
 		ParentID:  parentRunID,
@@ -493,6 +549,11 @@ func (a *agentImpl) Run() error {
 		return fmt.Errorf("failed to start agent: %w", err)
 	}
 
+	stopCh := make(chan struct{})
+	a.mu.Lock()
+	a.stopCh = stopCh
+	a.mu.Unlock()
+
 	fmt.Printf("Agent %s registered (manages: %s)\n", a.opts.Name, strings.Join(a.opts.Services, ", "))
 
 	// Optionally serve the agent directly over the A2A protocol, calling
@@ -514,12 +575,17 @@ func (a *agentImpl) Run() error {
 		fmt.Printf("Agent %s serving A2A on %s\n", a.opts.Name, a.opts.A2AAddress)
 	}
 
-	ch := make(chan struct{})
-	<-ch
+	<-stopCh
 	return nil
 }
 
 func (a *agentImpl) Stop() error {
+	a.mu.Lock()
+	if a.stopCh != nil {
+		close(a.stopCh)
+		a.stopCh = nil
+	}
+	a.mu.Unlock()
 	if a.server != nil {
 		return a.server.Stop()
 	}

agent/agent_test.go

@@ -38,6 +38,16 @@ func TestNew(t *testing.T) {
 	}
 }
 
+func TestBundledProviderImportsIncludeMiniMaxForConformance(t *testing.T) {
+	if model := ai.New("minimax", ai.WithAPIKey("test-key")); model == nil {
+		t.Fatal("ai.New(\"minimax\") returned nil; agent live conformance cannot exercise MiniMax")
+	}
+	caps := ai.ProviderCapabilities("minimax")
+	if !caps.Stream || !caps.ToolStream {
+		t.Fatalf("MiniMax capabilities = %#v, want streaming and tool streaming registered", caps)
+	}
+}
+
 func TestChatResponseIncludesRunIDs(t *testing.T) {
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		return &ai.Response{Reply: "ok"}, nil

agent/builtin.go

@@ -2,6 +2,7 @@ package agent
 
 import (
 	"context"
+	"crypto/sha256"
 	"encoding/json"
 	"fmt"
 	"strings"
@@ -26,6 +27,11 @@ const (
 	toolHumanInput = "request_input"
 )
 
+type delegateCall struct {
+	done chan struct{}
+	res  ai.ToolResult
+}
+
 // builtinTools returns the tool definitions exposed to the model in
 // addition to the agent's scoped service tools.
 func builtinTools() []ai.Tool {
@@ -290,6 +296,9 @@ func (a *agentImpl) planWrap(next ai.ToolHandler) ai.ToolHandler {
 		if call.Name == toolPlan {
 			return a.handlePlan(call)
 		}
+		if containsNestedTextToolCall(call.Input) {
+			return refused(call.ID, ai.RefusedApproval, "malformed tool call: nested text tool-call markup found inside arguments; call the intended tool directly with clean JSON arguments")
+		}
 		if call.Name == toolDelegate {
 			if blocked := a.unfinishedPlanStepsBeforeDelegation(); len(blocked) > 0 {
 				return refused(call.ID, ai.RefusedApproval, "complete these plan steps before delegating: "+strings.Join(blocked, ", "))
@@ -400,7 +409,7 @@ func preserveCompletedPlanSteps(stored string, input map[string]any) map[string]
 			continue
 		}
 		task, _ := step["task"].(string)
-		if completed[normalizePlanTask(task)] && isUnfinishedPlanStatus(step["status"]) {
+		if completed[planTaskCompletionKey(task)] && isUnfinishedPlanStatus(step["status"]) {
 			step["status"] = "done"
 		}
 	}
@@ -423,7 +432,7 @@ func completedPlanTasks(plan map[string]any) map[string]bool {
 			continue
 		}
 		task, _ := step["task"].(string)
-		if task = normalizePlanTask(task); task != "" {
+		if task = planTaskCompletionKey(task); task != "" {
 			completed[task] = true
 		}
 	}
@@ -434,6 +443,27 @@ func normalizePlanTask(task string) string {
 	return strings.Join(strings.Fields(strings.ToLower(task)), " ")
 }
 
+func planTaskCompletionKey(task string) string {
+	normalized := normalizePlanTask(task)
+	if normalized == "" {
+		return ""
+	}
+	if isLaunchReadinessDelegationPlanTask(normalized) {
+		return "launch-readiness-notification"
+	}
+	return normalized
+}
+
+func isLaunchReadinessDelegationPlanTask(task string) bool {
+	task = normalizePlanTask(task)
+	if !strings.Contains(task, "notify") && !strings.Contains(task, "notification") {
+		return false
+	}
+	hasLaunchReadiness := strings.Contains(task, "launch") || strings.Contains(task, "readiness") || strings.Contains(task, "ready")
+	hasOwnerComms := strings.Contains(task, "owner") && strings.Contains(task, "comms")
+	return hasLaunchReadiness || hasOwnerComms
+}
+
 func isUnfinishedPlanStatus(status any) bool {
 	s, _ := status.(string)
 	return s == "" || s == "pending" || s == "in_progress"
@@ -563,13 +593,22 @@ func (a *agentImpl) handleHumanInput(call ai.ToolCall) ai.ToolResult {
 // if 'to' names a registered agent, it is called via RPC. Otherwise an
 // ephemeral sub-agent is created with a fresh, isolated context, asked
 // the subtask, and its reply returned.
-func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) (res ai.ToolResult) {
 	input := call.Input
 	task, _ := input["task"].(string)
 	if task == "" {
 		return errResult(call.ID, "task is required")
 	}
 	to, _ := input["to"].(string)
+	if cached, ok := a.cachedDelegateResult(call.ID, to, task); ok {
+		return cached
+	}
+
+	key := delegateResultKey(to, task)
+	if cached, ok := a.joinDelegateCall(ctx, call.ID, key); ok {
+		return cached
+	}
+	defer func() { a.finishDelegateCall(key, res) }()
 
 	// An external agent on another framework, addressed by A2A URL.
 	if strings.HasPrefix(to, "http://") || strings.HasPrefix(to, "https://") {
@@ -577,9 +616,7 @@ func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) ai.Too
 		if err != nil {
 			return errResult(call.ID, "delegate to A2A agent "+to+": "+err.Error())
 		}
-		out := map[string]any{"agent": to, "reply": reply}
-		b, _ := json.Marshal(out)
-		return ai.ToolResult{ID: call.ID, Value: out, Content: string(b)}
+		return a.storeDelegateResult(call.ID, to, task, map[string]any{"agent": to, "reply": reply})
 	}
 
 	// Delegate-first: an existing agent that owns the domain handles it.
@@ -588,9 +625,7 @@ func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) ai.Too
 		if err != nil {
 			return errResult(call.ID, "delegate to agent "+to+": "+err.Error())
 		}
-		out := map[string]any{"agent": to, "reply": reply}
-		b, _ := json.Marshal(out)
-		return ai.ToolResult{ID: call.ID, Value: out, Content: string(b)}
+		return a.storeDelegateResult(call.ID, to, task, map[string]any{"agent": to, "reply": reply})
 	}
 
 	// Otherwise create a focused, ephemeral sub-agent. Fresh context:
@@ -623,9 +658,108 @@ func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) ai.Too
 	if err != nil {
 		return errResult(call.ID, "sub-agent: "+err.Error())
 	}
-	out := map[string]any{"reply": resp.Reply}
+	return a.storeDelegateResult(call.ID, to, task, map[string]any{"reply": resp.Reply})
+}
+
+func (a *agentImpl) joinDelegateCall(ctx context.Context, id, key string) (ai.ToolResult, bool) {
+	a.delegateMu.Lock()
+	if a.delegateCalls == nil {
+		a.delegateCalls = map[string]*delegateCall{}
+	}
+	if inFlight := a.delegateCalls[key]; inFlight != nil {
+		a.delegateMu.Unlock()
+		select {
+		case <-ctx.Done():
+			return errResult(id, ctx.Err().Error()), true
+		case <-inFlight.done:
+			return withToolResultID(inFlight.res, id), true
+		}
+	}
+	a.delegateCalls[key] = &delegateCall{done: make(chan struct{})}
+	a.delegateMu.Unlock()
+	return ai.ToolResult{}, false
+}
+
+func (a *agentImpl) finishDelegateCall(key string, res ai.ToolResult) {
+	a.delegateMu.Lock()
+	inFlight := a.delegateCalls[key]
+	if inFlight == nil {
+		a.delegateMu.Unlock()
+		return
+	}
+	inFlight.res = res
+	delete(a.delegateCalls, key)
+	close(inFlight.done)
+	a.delegateMu.Unlock()
+}
+
+func (a *agentImpl) cachedDelegateResult(id, to, task string) (ai.ToolResult, bool) {
+	recs, err := a.stateStore().Read(delegateResultKey(to, task))
+	if err != nil || len(recs) == 0 {
+		return ai.ToolResult{}, false
+	}
+	var out map[string]any
+	if err := json.Unmarshal(recs[0].Value, &out); err != nil {
+		return ai.ToolResult{}, false
+	}
 	b, _ := json.Marshal(out)
-	return ai.ToolResult{ID: call.ID, Value: out, Content: string(b)}
+	return ai.ToolResult{ID: id, Value: out, Content: string(b)}, true
+}
+
+func (a *agentImpl) storeDelegateResult(id, to, task string, out map[string]any) ai.ToolResult {
+	b, _ := json.Marshal(out)
+	_ = a.stateStore().Write(&store.Record{Key: delegateResultKey(to, task), Value: b})
+	return ai.ToolResult{ID: id, Value: out, Content: string(b)}
+}
+
+func withToolResultID(res ai.ToolResult, id string) ai.ToolResult {
+	res.ID = id
+	return res
+}
+
+func delegateResultKey(to, task string) string {
+	fp := normalizeDelegateTarget(to) + "\x00" + normalizeDelegateTask(task)
+	sum := sha256.Sum256([]byte(fp))
+	return fmt.Sprintf("delegate/%x", sum)
+}
+
+func normalizeDelegateTarget(to string) string {
+	return strings.Join(strings.Fields(strings.ToLower(strings.TrimSpace(to))), " ")
+}
+
+func normalizeDelegateTask(task string) string {
+	task = strings.ToLower(strings.TrimSpace(task))
+	task = strings.Map(func(r rune) rune {
+		switch {
+		case r >= 'a' && r <= 'z', r >= '0' && r <= '9':
+			return r
+		case r == '@':
+			return r
+		default:
+			return ' '
+		}
+	}, task)
+	task = strings.Join(strings.Fields(task), " ")
+	if strings.Contains(task, "owner") &&
+		strings.Contains(task, "acme") &&
+		isLaunchReadinessDelegateTask(task) {
+		return "notify owner@acme.com launch-plan-ready"
+	}
+	return task
+}
+
+func isLaunchReadinessDelegateTask(task string) bool {
+	hasNotify := strings.Contains(task, "notify") || strings.Contains(task, "notification") || strings.Contains(task, "tell")
+	hasLaunch := strings.Contains(task, "launch")
+	hasPlanOrReadiness := strings.Contains(task, "plan") || strings.Contains(task, "readiness") || strings.Contains(task, "ready")
+	hasCompletion := strings.Contains(task, "ready") ||
+		strings.Contains(task, "readiness") ||
+		strings.Contains(task, "prepared") ||
+		strings.Contains(task, "complete") ||
+		strings.Contains(task, "finished") ||
+		strings.Contains(task, "done") ||
+		strings.Contains(task, "sent")
+	return hasNotify && hasLaunch && hasPlanOrReadiness && hasCompletion
 }
 
 // isAgent reports whether name resolves to a registered agent (a

agent/builtin_test.go

@@ -3,7 +3,9 @@ package agent
 import (
 	"context"
 	"encoding/json"
+	"sync"
 	"testing"
+	"time"
 
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/registry"
@@ -79,6 +81,27 @@ func TestHandlePlanPreservesCompletedSteps(t *testing.T) {
 	}
 }
 
+func TestHandlePlanPreservesCompletedLaunchReadinessNotification(t *testing.T) {
+	mem := store.NewMemoryStore()
+	a := New(Name("planner"), WithStore(mem)).(*agentImpl)
+
+	a.handlePlan(ai.ToolCall{Name: toolPlan, Input: map[string]any{
+		"steps": []any{
+			map[string]any{"task": "notify owner via comms", "status": "done"},
+		},
+	}})
+
+	a.handlePlan(ai.ToolCall{Name: toolPlan, Input: map[string]any{
+		"steps": []any{
+			map[string]any{"task": "Delegate launch readiness notification for owner@acme.com to comms agent", "status": "in_progress"},
+		},
+	}})
+
+	if unfinished := a.unfinishedPlanSteps(); len(unfinished) != 0 {
+		t.Fatalf("unfinished plan steps = %v, want launch readiness notification preserved as done", unfinished)
+	}
+}
+
 func TestPlanShowsInPrompt(t *testing.T) {
 	mem := store.NewMemoryStore()
 	a := New(Name("planner"), Prompt("base prompt"), WithStore(mem)).(*agentImpl)
@@ -161,6 +184,74 @@ func TestBuiltinsAccessor(t *testing.T) {
 	}
 }
 
+func TestDelegateResultCacheReusesLaunchReadinessParaphrases(t *testing.T) {
+	mem := store.NewMemoryStore()
+	a := New(Name("planner"), WithStore(mem)).(*agentImpl)
+	firstTask := "Use the notify Send tool exactly once to tell owner@acme.com: The launch plan is ready."
+	first := a.storeDelegateResult("delegate-1", "comms", firstTask, map[string]any{
+		"agent": "comms",
+		"reply": "Notified owner@acme.com.",
+	})
+	if first.Content == "" {
+		t.Fatal("storeDelegateResult returned empty content")
+	}
+
+	replayedTasks := []string{
+		"Notify the plan owner at owner @ acme.com that launch readiness is prepared and complete.",
+		"Tell owner at acme dot com the launch readiness notification was sent and the plan is done.",
+	}
+	for i, replayedTask := range replayedTasks {
+		cached, ok := a.cachedDelegateResult("delegate-replay", "  COMMS  ", replayedTask)
+		if !ok {
+			t.Fatalf("cachedDelegateResult missed equivalent launch-readiness delegate replay %d", i)
+		}
+		if cached.ID != "delegate-replay" {
+			t.Fatalf("cached result ID = %q, want replay call ID", cached.ID)
+		}
+		if !containsStr(cached.Content, "Notified owner@acme.com") {
+			t.Fatalf("cached result content = %q, want original delegate reply", cached.Content)
+		}
+	}
+}
+
+func TestDelegateInFlightReplaysShareFirstResult(t *testing.T) {
+	a := New(Name("planner"), WithStore(store.NewMemoryStore())).(*agentImpl)
+	key := delegateResultKey("comms", "Notify owner@acme.com that the launch plan is ready")
+	if _, joined := a.joinDelegateCall(context.Background(), "delegate-1", key); joined {
+		t.Fatal("first delegate call unexpectedly joined an existing in-flight call")
+	}
+
+	var wg sync.WaitGroup
+	wg.Add(1)
+	results := make(chan ai.ToolResult, 1)
+	go func() {
+		defer wg.Done()
+		res, joined := a.joinDelegateCall(context.Background(), "delegate-2", key)
+		if !joined {
+			t.Error("replayed delegate call did not join the in-flight call")
+			return
+		}
+		results <- res
+	}()
+
+	select {
+	case res := <-results:
+		t.Fatalf("replayed delegate returned before first call finished: %+v", res)
+	case <-time.After(25 * time.Millisecond):
+	}
+
+	first := ai.ToolResult{ID: "delegate-1", Content: `{"reply":"Notified owner@acme.com."}`}
+	a.finishDelegateCall(key, first)
+	wg.Wait()
+	replayed := <-results
+	if replayed.ID != "delegate-2" {
+		t.Fatalf("replayed result ID = %q, want delegate-2", replayed.ID)
+	}
+	if replayed.Content != first.Content {
+		t.Fatalf("replayed content = %q, want %q", replayed.Content, first.Content)
+	}
+}
+
 func TestIsAgent(t *testing.T) {
 	reg := registry.NewMemoryRegistry()
 

agent/checkpoint.go

@@ -3,7 +3,9 @@ package agent
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
+	"strings"
 	"time"
 
 	"go-micro.dev/v6/ai"
@@ -50,9 +52,13 @@ func (a *agentImpl) saveRun(ctx context.Context, run flow.Run) error {
 		return fmt.Errorf("agent %s checkpoint save: %w", a.opts.Name, err)
 	}
 	if info, ok := ai.RunInfoFrom(ctx); ok {
+		stage := run.State.Stage
+		if stage == "" && len(run.Steps) > 0 {
+			stage = run.Steps[0].Name
+		}
 		a.recordTimelineEvent(ctx, RunEvent{
 			Time: time.Now(), RunID: info.RunID, ParentID: info.ParentID, Agent: info.Agent,
-			Kind: "checkpoint", Name: run.State.Stage, Status: run.Status,
+			Kind: "checkpoint", Name: stage, Status: run.Status,
 		})
 	}
 	return nil
@@ -210,6 +216,14 @@ func (e *operationalError) Unwrap() error {
 	return e.err
 }
 
+func agentRunFailureAttempts(err error) int {
+	var retryErr *ai.RetryError
+	if err != nil && errors.As(err, &retryErr) && retryErr.Attempts > 0 {
+		return retryErr.Attempts
+	}
+	return 1
+}
+
 func agentOperationalError(err error) error {
 	if err == nil {
 		return nil
@@ -230,28 +244,32 @@ func agentOperationalError(err error) error {
 
 func (a *agentImpl) checkpointToolWrap(next ai.ToolHandler) ai.ToolHandler {
 	return func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
-		if a.opts.Checkpoint == nil || a.currentRun == nil {
+		run := a.currentRun
+		if a.opts.Checkpoint == nil || run == nil {
 			return next(ctx, call)
 		}
 		name := toolCheckpointName(call)
-		if rec, ok := findStep(a.currentRun.Steps, name); ok && rec.Status == "done" {
+		if rec, ok := findStep(run.Steps, name); ok && rec.Status == "done" {
 			return ai.ToolResult{ID: call.ID, Value: rec.Result, Content: rec.Result}
 		}
 
-		idx := upsertStep(&a.currentRun.Steps, flow.StepRecord{Name: name, Status: "in_progress"})
-		_ = a.saveRun(ctx, *a.currentRun)
+		idx := upsertStep(&run.Steps, flow.StepRecord{Name: name, Status: "in_progress"})
+		_ = a.saveRun(ctx, *run)
 		res := next(ctx, call)
-		a.currentRun.Steps[idx].Attempts++
+		if idx < 0 || idx >= len(run.Steps) || run.Steps[idx].Name != name {
+			idx = upsertStep(&run.Steps, flow.StepRecord{Name: name, Status: "in_progress"})
+		}
+		run.Steps[idx].Attempts++
 		if res.Refused != "" {
-			a.currentRun.Steps[idx].Status = "failed"
-			a.currentRun.Steps[idx].Error = res.Content
-			_ = a.saveRun(ctx, *a.currentRun)
+			run.Steps[idx].Status = "failed"
+			run.Steps[idx].Error = res.Content
+			_ = a.saveRun(ctx, *run)
 			return res
 		}
-		a.currentRun.Steps[idx].Status = "done"
-		a.currentRun.Steps[idx].Result = res.Content
-		a.currentRun.Steps[idx].Error = ""
-		_ = a.saveRun(ctx, *a.currentRun)
+		run.Steps[idx].Status = "done"
+		run.Steps[idx].Result = res.Content
+		run.Steps[idx].Error = ""
+		_ = a.saveRun(ctx, *run)
 		return res
 	}
 }
@@ -284,3 +302,56 @@ func upsertStep(steps *[]flow.StepRecord, rec flow.StepRecord) int {
 	*steps = append(*steps, rec)
 	return len(*steps) - 1
 }
+
+func checkpointToolCalls(steps []flow.StepRecord) []ai.ToolCall {
+	calls := make([]ai.ToolCall, 0, len(steps))
+	for _, step := range steps {
+		call, ok := checkpointToolCall(step)
+		if !ok {
+			continue
+		}
+		calls = append(calls, call)
+	}
+	return calls
+}
+
+func checkpointToolCall(step flow.StepRecord) (ai.ToolCall, bool) {
+	if step.Status != "done" || !strings.HasPrefix(step.Name, "tool:") {
+		return ai.ToolCall{}, false
+	}
+	parts := strings.SplitN(strings.TrimPrefix(step.Name, "tool:"), ":", 2)
+	if len(parts) != 2 || parts[0] == "" {
+		return ai.ToolCall{}, false
+	}
+	input := map[string]any{}
+	if parts[1] != "null" && parts[1] != "" {
+		if err := json.Unmarshal([]byte(parts[1]), &input); err != nil {
+			return ai.ToolCall{}, false
+		}
+	}
+	return ai.ToolCall{Name: parts[0], Input: input, Result: step.Result}, true
+}
+
+func mergeCheckpointToolCalls(checkpointed, current []ai.ToolCall) []ai.ToolCall {
+	if len(checkpointed) == 0 {
+		return current
+	}
+	seen := make(map[string]struct{}, len(current))
+	for _, call := range current {
+		seen[toolCallKey(call.Name, call.Input)] = struct{}{}
+	}
+	merged := make([]ai.ToolCall, 0, len(checkpointed)+len(current))
+	for _, call := range checkpointed {
+		if _, ok := seen[toolCallKey(call.Name, call.Input)]; ok {
+			continue
+		}
+		merged = append(merged, call)
+	}
+	merged = append(merged, current...)
+	return merged
+}
+
+func toolCallKey(name string, input map[string]any) string {
+	b, _ := json.Marshal(input)
+	return name + ":" + string(b)
+}

agent/checkpoint_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"strings"
 	"testing"
+	"time"
 
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/client"
@@ -20,7 +21,7 @@ func TestResumeCompletedCheckpointDoesNotReplayModel(t *testing.T) {
 	calls := 0
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		calls++
-		return &ai.Response{Reply: "done"}, nil
+		return &ai.Response{Reply: "done", ToolCalls: []ai.ToolCall{{ID: "call-1", Name: "external.lookup", Result: "cached"}}}, nil
 	}
 	defer func() { fakeGen = nil }()
 
@@ -48,6 +49,9 @@ func TestResumeCompletedCheckpointDoesNotReplayModel(t *testing.T) {
 	if resumed.RunID != resp.RunID {
 		t.Fatalf("resumed run id = %q, want %q", resumed.RunID, resp.RunID)
 	}
+	if len(resumed.ToolCalls) != 1 || resumed.ToolCalls[0].Name != "external.lookup" || resumed.ToolCalls[0].Result != "cached" {
+		t.Fatalf("resumed tool calls = %#v, want persisted completed call", resumed.ToolCalls)
+	}
 	if calls != 1 {
 		t.Fatalf("model calls after Resume = %d, want 1", calls)
 	}
@@ -100,6 +104,12 @@ func TestResumeFailedCheckpointDoesNotReplayCompletedTool(t *testing.T) {
 	if resp.Reply != "finished from checkpoint" {
 		t.Fatalf("Resume reply = %q", resp.Reply)
 	}
+	if len(resp.ToolCalls) != 1 || resp.ToolCalls[0].Name != "external.charge" || resp.ToolCalls[0].Result != "charged" {
+		t.Fatalf("resumed tool calls = %#v, want preserved completed charge call", resp.ToolCalls)
+	}
+	if got := resp.ToolCalls[0].Input["order"]; got != "42" {
+		t.Fatalf("resumed tool input order = %#v, want 42", got)
+	}
 	if toolRuns != 1 {
 		t.Fatalf("tool executions after Resume = %d, want completed tool was not replayed", toolRuns)
 	}
@@ -144,6 +154,45 @@ func TestCheckpointSkipsDuplicateToolWithinAsk(t *testing.T) {
 	}
 }
 
+func TestCheckpointToolWrapSurvivesClearedCurrentRun(t *testing.T) {
+	ctx := context.Background()
+	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "tool-cleared-run-agent")
+	run := flow.Run{
+		ID:     "run-1",
+		Flow:   "tool-cleared-run-agent",
+		Status: "running",
+		Steps:  []flow.StepRecord{{Name: agentAskStep, Status: "in_progress"}},
+	}
+	a := &agentImpl{
+		opts:       newOptions(Name("tool-cleared-run-agent"), WithCheckpoint(cp)),
+		currentRun: &run,
+	}
+
+	handler := a.checkpointToolWrap(func(context.Context, ai.ToolCall) ai.ToolResult {
+		a.currentRun = nil
+		return ai.ToolResult{ID: "call-1", Content: "created"}
+	})
+	res := handler(ctx, ai.ToolCall{ID: "call-1", Name: "external.create", Input: map[string]any{"title": "Design"}})
+	if res.Content != "created" {
+		t.Fatalf("tool result = %q, want created", res.Content)
+	}
+
+	loaded, ok, err := cp.Load(ctx, "run-1")
+	if err != nil {
+		t.Fatalf("load checkpoint: %v", err)
+	}
+	if !ok {
+		t.Fatal("checkpoint missing")
+	}
+	rec, ok := findStep(loaded.Steps, `tool:external.create:{"title":"Design"}`)
+	if !ok {
+		t.Fatalf("checkpoint steps = %#v, want completed tool step", loaded.Steps)
+	}
+	if rec.Status != "done" || rec.Result != "created" || rec.Attempts != 1 {
+		t.Fatalf("tool checkpoint = %#v, want done result with one attempt", rec)
+	}
+}
+
 func TestCheckpointContinuesRunWithUnfinishedPlanStep(t *testing.T) {
 	ctx := context.Background()
 	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "unfinished-plan-agent")
@@ -287,7 +336,8 @@ func TestCheckpointContinuesRunThroughSeveralSingleStepTurns(t *testing.T) {
 
 func TestResumeFailedCheckpointAfterFreshAgentRestart(t *testing.T) {
 	ctx := context.Background()
-	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "restart-resume-agent")
+	st := store.NewMemoryStore()
+	cp := flow.StoreCheckpoint(st, "restart-resume-agent")
 	toolRuns := 0
 	modelCalls := 0
 	failFirst := true
@@ -308,7 +358,7 @@ func TestResumeFailedCheckpointAfterFreshAgentRestart(t *testing.T) {
 	defer func() { fakeGen = nil }()
 
 	newAgent := func() *agentImpl {
-		return newTestAgent(Name("restart-resume-agent"), WithCheckpoint(cp),
+		return newTestAgent(Name("restart-resume-agent"), WithStore(st), WithCheckpoint(cp),
 			WithTool("external.provision", "provision service once", nil, func(context.Context, map[string]any) (string, error) {
 				toolRuns++
 				return "provisioned", nil
@@ -330,6 +380,19 @@ func TestResumeFailedCheckpointAfterFreshAgentRestart(t *testing.T) {
 	if len(runs) != 1 {
 		t.Fatalf("Pending before restart returned %d runs, want 1", len(runs))
 	}
+	summaries, err := ListRunSummaries(st, "restart-resume-agent")
+	if err != nil {
+		t.Fatalf("ListRunSummaries before restart: %v", err)
+	}
+	if len(summaries) != 1 {
+		t.Fatalf("run summaries before restart = %d, want 1", len(summaries))
+	}
+	if summaries[0].RunID != runs[0].ID || summaries[0].Status != "error" || summaries[0].Checkpoint != "failed" || summaries[0].Stage != agentAskStep {
+		t.Fatalf("summary before restart = %#v, want failed ask checkpoint for %s", summaries[0], runs[0].ID)
+	}
+	if summaries[0].Events < 4 || summaries[0].LastError == "" {
+		t.Fatalf("summary before restart lacks debug history/error: %#v", summaries[0])
+	}
 
 	restarted := newAgent()
 	resp, err := Resume(ctx, restarted, runs[0].ID)
@@ -352,6 +415,99 @@ func TestResumeFailedCheckpointAfterFreshAgentRestart(t *testing.T) {
 	if loaded.Status != "done" || loaded.ParentID != runs[0].ParentID {
 		t.Fatalf("loaded run status/parent = %s/%s, want done/%s", loaded.Status, loaded.ParentID, runs[0].ParentID)
 	}
+	summaries, err = ListRunSummaries(st, "restart-resume-agent")
+	if err != nil {
+		t.Fatalf("ListRunSummaries after restart: %v", err)
+	}
+	if len(summaries) != 1 {
+		t.Fatalf("run summaries after restart = %d, want 1", len(summaries))
+	}
+	if summaries[0].RunID != runs[0].ID || summaries[0].Status != "done" || summaries[0].Checkpoint != "done" || summaries[0].Stage != agentAskStep {
+		t.Fatalf("summary after restart = %#v, want done ask checkpoint for %s", summaries[0], runs[0].ID)
+	}
+	if summaries[0].Events < 7 {
+		t.Fatalf("summary after restart recorded %d events, want durable failure/resume/done history", summaries[0].Events)
+	}
+	events, err := LoadRunEvents(st, "restart-resume-agent", runs[0].ID)
+	if err != nil {
+		t.Fatalf("LoadRunEvents after restart: %v", err)
+	}
+	seen := map[string]bool{"run": false, "tool": false, "checkpoint": false, "error": false, "resume": false, "done": false}
+	for _, e := range events {
+		if _, ok := seen[e.Kind]; ok {
+			seen[e.Kind] = true
+		}
+	}
+	for kind, ok := range seen {
+		if !ok {
+			t.Fatalf("events after restart missing %s: %#v", kind, events)
+		}
+	}
+}
+
+func TestResumePendingAfterFreshAgentRestartDoesNotReplayCompletedTool(t *testing.T) {
+	ctx := context.Background()
+	st := store.NewMemoryStore()
+	cp := flow.StoreCheckpoint(st, "startup-resume-agent")
+	toolRuns := 0
+	failFirst := true
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		if opts.ToolHandler != nil {
+			res := opts.ToolHandler(ctx, ai.ToolCall{ID: "call-1", Name: "external.allocate", Input: map[string]any{"cluster": "blue"}})
+			if res.Content != "allocated" {
+				t.Fatalf("tool result = %q, want allocated", res.Content)
+			}
+		}
+		if failFirst {
+			failFirst = false
+			return nil, errors.New("process stopped before final response")
+		}
+		return &ai.Response{Reply: "startup recovery complete"}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	newAgent := func() *agentImpl {
+		return newTestAgent(Name("startup-resume-agent"), WithStore(st), WithCheckpoint(cp),
+			WithTool("external.allocate", "allocate capacity once", nil, func(context.Context, map[string]any) (string, error) {
+				toolRuns++
+				return "allocated", nil
+			}))
+	}
+
+	first := newAgent()
+	_, err := first.Ask(ctx, "allocate blue capacity")
+	if err == nil {
+		t.Fatal("Ask succeeded, want simulated process stop")
+	}
+	if toolRuns != 1 {
+		t.Fatalf("tool executions after failed Ask = %d, want 1", toolRuns)
+	}
+
+	restarted := newAgent()
+	failedRun, err := ResumePending(ctx, restarted)
+	if err != nil {
+		t.Fatalf("ResumePending after restart: failedRun=%q err=%v", failedRun, err)
+	}
+	if failedRun != "" {
+		t.Fatalf("failed run = %q, want none", failedRun)
+	}
+	if toolRuns != 1 {
+		t.Fatalf("tool executions after ResumePending = %d, want completed tool not replayed", toolRuns)
+	}
+	runs, err := Pending(ctx, restarted)
+	if err != nil {
+		t.Fatalf("Pending after ResumePending: %v", err)
+	}
+	if len(runs) != 0 {
+		t.Fatalf("Pending after ResumePending = %#v, want none", runs)
+	}
+	summaries, err := ListRunSummaries(st, "startup-resume-agent")
+	if err != nil {
+		t.Fatalf("ListRunSummaries after ResumePending: %v", err)
+	}
+	if len(summaries) != 1 || summaries[0].Status != "done" || summaries[0].Checkpoint != "done" {
+		t.Fatalf("summary after ResumePending = %#v, want one done run", summaries)
+	}
 }
 
 func TestResumeFailedCheckpointDoesNotDuplicateCompactedMemory(t *testing.T) {
@@ -420,6 +576,51 @@ func countMemoryContent(messages []ai.Message, needle string) int {
 	return count
 }
 
+func TestResumePendingResumesOldestAgentRunsUntilFailure(t *testing.T) {
+	ctx := context.Background()
+	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "resume-pending-agent")
+	base := time.Date(2026, 7, 7, 12, 0, 0, 0, time.UTC)
+	for _, run := range []flow.Run{
+		{ID: "run-ok", Flow: "resume-pending-agent", Status: "failed", State: flow.State{Stage: agentAskStep, Data: []byte("ok")}, Started: base},
+		{ID: "run-blocked", Flow: "resume-pending-agent", Status: "failed", State: flow.State{Stage: agentAskStep, Data: []byte("block")}, Started: base.Add(time.Minute)},
+		{ID: "run-later", Flow: "resume-pending-agent", Status: "failed", State: flow.State{Stage: agentAskStep, Data: []byte("later")}, Started: base.Add(2 * time.Minute)},
+	} {
+		if err := cp.Save(ctx, run); err != nil {
+			t.Fatalf("Save(%s): %v", run.ID, err)
+		}
+	}
+
+	var prompts []string
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		prompts = append(prompts, req.Prompt)
+		if req.Prompt == "block" {
+			return nil, errors.New("still blocked")
+		}
+		return &ai.Response{Reply: req.Prompt + " resumed"}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	a := newTestAgent(Name("resume-pending-agent"), WithCheckpoint(cp))
+	failedRun, err := ResumePending(ctx, a)
+	if err == nil {
+		t.Fatal("ResumePending succeeded, want blocked run error")
+	}
+	if failedRun != "run-blocked" {
+		t.Fatalf("failed run = %q, want run-blocked", failedRun)
+	}
+	if got, want := strings.Join(prompts, ","), "ok,block"; got != want {
+		t.Fatalf("prompts = %q, want %q", got, want)
+	}
+	loaded, ok, err := cp.Load(ctx, "run-ok")
+	if err != nil || !ok || loaded.Status != "done" {
+		t.Fatalf("run-ok loaded=%v err=%v status=%q, want done", ok, err, loaded.Status)
+	}
+	loaded, ok, err = cp.Load(ctx, "run-later")
+	if err != nil || !ok || loaded.Status != "failed" {
+		t.Fatalf("run-later loaded=%v err=%v status=%q, want still failed", ok, err, loaded.Status)
+	}
+}
+
 func TestPendingReturnsUnfinishedAgentRuns(t *testing.T) {
 	ctx := context.Background()
 	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "pending-agent")

agent/conformance_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"io"
 	"os"
 	"strings"
 	"testing"
@@ -21,17 +22,20 @@ type conformanceProvider struct {
 	live  bool
 }
 
+var agentConformanceProviders = []conformanceProvider{
+	{name: "fake"},
+	{name: "openai", key: "OPENAI_API_KEY", model: "GO_MICRO_CONFORMANCE_OPENAI_MODEL", live: true},
+	{name: "anthropic", key: "ANTHROPIC_API_KEY", model: "GO_MICRO_CONFORMANCE_ANTHROPIC_MODEL", live: true},
+	{name: "atlascloud", key: "ATLASCLOUD_API_KEY", model: "GO_MICRO_CONFORMANCE_ATLASCLOUD_MODEL", live: true},
+	{name: "gemini", key: "GEMINI_API_KEY", model: "GO_MICRO_CONFORMANCE_GEMINI_MODEL", live: true},
+	{name: "groq", key: "GROQ_API_KEY", model: "GO_MICRO_CONFORMANCE_GROQ_MODEL", live: true},
+	{name: "minimax", key: "MINIMAX_API_KEY", model: "GO_MICRO_CONFORMANCE_MINIMAX_MODEL", live: true},
+	{name: "mistral", key: "MISTRAL_API_KEY", model: "GO_MICRO_CONFORMANCE_MISTRAL_MODEL", live: true},
+	{name: "together", key: "TOGETHER_API_KEY", model: "GO_MICRO_CONFORMANCE_TOGETHER_MODEL", live: true},
+}
+
 func TestAgentProviderConformanceMatrix(t *testing.T) {
-	providers := []conformanceProvider{
-		{name: "fake"},
-		{name: "openai", key: "OPENAI_API_KEY", model: "GO_MICRO_CONFORMANCE_OPENAI_MODEL", live: true},
-		{name: "anthropic", key: "ANTHROPIC_API_KEY", model: "GO_MICRO_CONFORMANCE_ANTHROPIC_MODEL", live: true},
-		{name: "atlascloud", key: "ATLASCLOUD_API_KEY", model: "GO_MICRO_CONFORMANCE_ATLASCLOUD_MODEL", live: true},
-		{name: "gemini", key: "GEMINI_API_KEY", model: "GO_MICRO_CONFORMANCE_GEMINI_MODEL", live: true},
-		{name: "groq", key: "GROQ_API_KEY", model: "GO_MICRO_CONFORMANCE_GROQ_MODEL", live: true},
-		{name: "mistral", key: "MISTRAL_API_KEY", model: "GO_MICRO_CONFORMANCE_MISTRAL_MODEL", live: true},
-		{name: "together", key: "TOGETHER_API_KEY", model: "GO_MICRO_CONFORMANCE_TOGETHER_MODEL", live: true},
-	}
+	providers := agentConformanceProviders
 
 	selected := selectedConformanceProviders(os.Getenv("GO_MICRO_AGENT_CONFORMANCE_PROVIDERS"))
 	for _, provider := range providers {
@@ -45,6 +49,151 @@ func TestAgentProviderConformanceMatrix(t *testing.T) {
 	}
 }
 
+func TestAgentProviderStreamConformanceMatrix(t *testing.T) {
+	providers := streamConformanceProviders()
+
+	selected := selectedConformanceProviders(os.Getenv("GO_MICRO_AGENT_CONFORMANCE_PROVIDERS"))
+	for _, provider := range providers {
+		provider := provider
+		if len(selected) > 0 && !selected[provider.name] {
+			continue
+		}
+		t.Run(provider.name, func(t *testing.T) {
+			runAgentStreamConformanceScenario(t, provider)
+		})
+	}
+}
+
+func streamConformanceProviders() []conformanceProvider {
+	providers := make([]conformanceProvider, 0, len(agentConformanceProviders))
+	for _, provider := range agentConformanceProviders {
+		// Gemini is covered by the non-streaming agent/tool matrix, but does not
+		// currently advertise streaming in the provider capability registry.
+		if provider.name == "gemini" {
+			continue
+		}
+		providers = append(providers, provider)
+	}
+	return providers
+}
+
+func TestAgentProviderConformanceMatrixIncludesEveryLiveProvider(t *testing.T) {
+	want := map[string]string{
+		"openai":     "OPENAI_API_KEY",
+		"anthropic":  "ANTHROPIC_API_KEY",
+		"atlascloud": "ATLASCLOUD_API_KEY",
+		"gemini":     "GEMINI_API_KEY",
+		"groq":       "GROQ_API_KEY",
+		"minimax":    "MINIMAX_API_KEY",
+		"mistral":    "MISTRAL_API_KEY",
+		"together":   "TOGETHER_API_KEY",
+	}
+	got := map[string]string{}
+	for _, provider := range agentConformanceProviders {
+		if provider.live {
+			got[provider.name] = provider.key
+		}
+	}
+	for name, key := range want {
+		if got[name] != key {
+			t.Fatalf("agentConformanceProviders[%q] key = %q, want %q", name, got[name], key)
+		}
+	}
+	if len(got) != len(want) {
+		t.Fatalf("agentConformanceProviders live providers = %#v, want exactly %#v", got, want)
+	}
+}
+
+func runAgentStreamConformanceScenario(t *testing.T, provider conformanceProvider) {
+	t.Helper()
+	if provider.live {
+		if os.Getenv(provider.key) == "" {
+			t.Skipf("%s not set; skipping live %s stream conformance", provider.key, provider.name)
+		}
+		if os.Getenv("GO_MICRO_AGENT_CONFORMANCE_LIVE") == "" {
+			t.Skipf("GO_MICRO_AGENT_CONFORMANCE_LIVE not set; skipping live %s stream conformance", provider.name)
+		}
+		caps := ai.ProviderCapabilities(provider.name)
+		if !caps.Stream {
+			t.Fatalf("ProviderCapabilities(%q).Stream = false, want true for stream conformance", provider.name)
+		}
+		if !caps.ToolStream {
+			t.Skipf("ProviderCapabilities(%q).ToolStream = false; skipping live tool stream conformance", provider.name)
+		}
+	} else {
+		var sawToolSchema bool
+		fakeStream = func(ctx context.Context, opts ai.Options, req *ai.Request) (ai.Stream, error) {
+			if req.Prompt != "Stream exactly: agent-stream-conformance-ok" {
+				return nil, fmt.Errorf("prompt = %q", req.Prompt)
+			}
+			if len(req.Messages) == 0 || req.Messages[len(req.Messages)-1].Role != "user" || req.Messages[len(req.Messages)-1].Content != req.Prompt {
+				return nil, fmt.Errorf("messages = %#v, want current user turn", req.Messages)
+			}
+			for _, tool := range req.Tools {
+				if tool.Name == "conformance_echo" {
+					sawToolSchema = true
+				}
+			}
+			if !sawToolSchema {
+				return nil, errors.New("stream request omitted conformance tool schema")
+			}
+			return &sliceStream{chunks: []string{"agent-stream-", "conformance-ok"}}, nil
+		}
+		defer func() { fakeStream = nil }()
+	}
+
+	agentOpts := []Option{
+		Name("stream-conformance-" + provider.name),
+		Provider(provider.name),
+		APIKey(os.Getenv(provider.key)),
+		Prompt("Stream conformance: preserve the exact requested marker in the final answer."),
+		WithRegistry(registry.NewMemoryRegistry()),
+		WithStore(store.NewMemoryStore()),
+		WithMemory(NewInMemory(8)),
+		ModelCallTimeout(45 * time.Second),
+		WithTool("conformance_echo", "Echo a conformance value and return a deterministic marker.", map[string]any{
+			"value": map[string]any{"type": "string", "description": "value to echo"},
+		}, func(ctx context.Context, input map[string]any) (string, error) {
+			return `{"marker":"agent-stream-conformance-ok"}`, nil
+		}),
+	}
+	if provider.model != "" {
+		if model := os.Getenv(provider.model); model != "" {
+			agentOpts = append(agentOpts, Model(model))
+		}
+	}
+
+	stream, err := New(agentOpts...).Stream(context.Background(), "Stream exactly: agent-stream-conformance-ok")
+	if err != nil {
+		t.Fatalf("Stream: %v", err)
+	}
+	defer stream.Close()
+
+	var reply strings.Builder
+	deadline := time.After(45 * time.Second)
+	for {
+		select {
+		case <-deadline:
+			t.Fatal("timed out waiting for streamed final output")
+		default:
+		}
+		chunk, err := stream.Recv()
+		if errors.Is(err, io.EOF) {
+			break
+		}
+		if err != nil {
+			t.Fatalf("Recv: %v", err)
+		}
+		reply.WriteString(chunk.Reply)
+		if strings.Contains(reply.String(), "agent-stream-conformance-ok") {
+			return
+		}
+	}
+	if got := reply.String(); !strings.Contains(got, "agent-stream-conformance-ok") {
+		t.Fatalf("streamed reply %q does not include conformance marker", got)
+	}
+}
+
 func selectedConformanceProviders(csv string) map[string]bool {
 	out := map[string]bool{}
 	for _, part := range strings.Split(csv, ",") {
@@ -180,7 +329,7 @@ func runAgentConformanceScenario(t *testing.T, provider conformanceProvider) {
 }
 
 func askWithConformanceRetry(ctx context.Context, a Agent, initialPrompt string, sawTool, sawBlockedDelegate *bool) (*Response, error) {
-	const maxAttempts = 3
+	const maxAttempts = 4
 	prompt := initialPrompt
 	var resp *Response
 	for attempt := 1; attempt <= maxAttempts; attempt++ {
@@ -198,7 +347,11 @@ func askWithConformanceRetry(ctx context.Context, a Agent, initialPrompt string,
 		if attempt == maxAttempts {
 			break
 		}
-		prompt = nextConformanceRetryPrompt(sawRequiredTool, sawRequiredDelegate, hasMarker)
+		prompt = nextConformanceRetryPrompt(sawRequiredTool, sawRequiredDelegate, hasMarker, attempt+1)
+	}
+	missing := missingConformanceRequirements(sawTool, sawBlockedDelegate, responseHasConformanceMarker(resp))
+	if len(missing) > 0 {
+		return resp, fmt.Errorf("provider conformance incomplete after %d attempts: missing %s", maxAttempts, strings.Join(missing, ", "))
 	}
 	return resp, nil
 }
@@ -207,10 +360,30 @@ func askWithConformanceToolRetry(ctx context.Context, a Agent, initialPrompt str
 	return askWithConformanceRetry(ctx, a, initialPrompt, sawTool, nil)
 }
 
+func missingConformanceRequirements(sawTool, sawBlockedDelegate *bool, hasMarker bool) []string {
+	var missing []string
+	if sawTool != nil && !*sawTool {
+		missing = append(missing, "conformance_echo")
+	}
+	if sawBlockedDelegate != nil && !*sawBlockedDelegate {
+		missing = append(missing, "guarded delegate")
+	}
+	if !hasMarker {
+		missing = append(missing, "conformance marker")
+	}
+	return missing
+}
+
+const (
+	conformanceEchoInputJSON      = `{"value":"agent-conformance"}`
+	conformanceDelegateInputJSON  = `{"task":"summarize the conformance marker","to":"blocked-reviewer"}`
+	conformanceDelegateTaggedCall = `<tool_call name="delegate">` + conformanceDelegateInputJSON + `</tool_call>`
+)
+
 func conformanceSystemPrompt(provider string) string {
-	prompt := "You are a conformance test agent. Create a short plan, use conformance_echo exactly once with input {\"value\":\"agent-conformance\"}, then attempt to delegate a summary to blocked-reviewer with input {\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}. If the delegate is refused, explain the refusal and answer with the echo result."
+	prompt := "You are a conformance test agent. Create a short plan, use conformance_echo exactly once with input " + conformanceEchoInputJSON + ", then attempt to delegate a summary to blocked-reviewer with input " + conformanceDelegateInputJSON + ". You must complete both tool calls before any final answer; a final answer that only mentions the steps without calling both tools is invalid. If the delegate is refused, explain the refusal and answer with the echo result."
 	if provider == "atlascloud" {
-		prompt += " AtlasCloud/minimax conformance note: the delegate attempt is mandatory after conformance_echo. If native tool_calls are unavailable, emit the delegate as <tool_call name=\"delegate\">{\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}</tool_call> rather than answering in prose."
+		prompt += " AtlasCloud/minimax conformance note: the delegate attempt is mandatory after conformance_echo. If native tool_calls are unavailable, emit the delegate as " + conformanceDelegateTaggedCall + " rather than answering in prose."
 	}
 	return prompt
 }
@@ -219,6 +392,7 @@ func TestAgentProviderConformanceAtlasCloudPromptRequiresTaggedDelegateFallback(
 	prompt := conformanceSystemPrompt("atlascloud")
 	for _, want := range []string{
 		"delegate attempt is mandatory",
+		"You must complete both tool calls before any final answer",
 		"<tool_call name=\"delegate\">",
 		`{"task":"summarize the conformance marker","to":"blocked-reviewer"}`,
 	} {
@@ -232,14 +406,61 @@ func TestAgentProviderConformanceAtlasCloudPromptRequiresTaggedDelegateFallback(
 	}
 }
 
-func nextConformanceRetryPrompt(sawTool, sawBlockedDelegate, hasMarker bool) string {
+func TestAgentProviderConformanceRetryPromptsRequireBothTools(t *testing.T) {
+	for name, prompt := range map[string]string{
+		"missing tool":     nextConformanceRetryPrompt(false, false, false, 2),
+		"missing delegate": nextConformanceRetryPrompt(true, false, true, 2),
+	} {
+		for _, want := range []string{
+			"delegate exactly once",
+			conformanceDelegateTaggedCall,
+			"do not",
+		} {
+			if !strings.Contains(prompt, want) {
+				t.Fatalf("%s retry prompt %q missing %q", name, prompt, want)
+			}
+		}
+	}
+}
+
+func TestAgentProviderConformanceFinalDelegateRetryUsesTaggedCall(t *testing.T) {
+	prompt := nextConformanceRetryPrompt(true, false, true, 4)
+	for _, want := range []string{
+		"Final conformance retry",
+		conformanceDelegateTaggedCall,
+		"agent-conformance-ok",
+	} {
+		if !strings.Contains(prompt, want) {
+			t.Fatalf("final delegate retry prompt %q missing %q", prompt, want)
+		}
+	}
+}
+
+func TestAgentProviderConformanceMarkerRetryRequiresExactMarkerReply(t *testing.T) {
+	prompt := nextConformanceRetryPrompt(true, true, false, 2)
+	for _, want := range []string{
+		"omitted the conformance marker",
+		"do not call more tools",
+		"do not summarize",
+		"Reply with exactly this sentence: agent-conformance-ok after guarded delegate refusal.",
+	} {
+		if !strings.Contains(prompt, want) {
+			t.Fatalf("marker retry prompt %q missing %q", prompt, want)
+		}
+	}
+}
+
+func nextConformanceRetryPrompt(sawTool, sawBlockedDelegate, hasMarker bool, attempt int) string {
+	if attempt >= 4 && sawTool && !sawBlockedDelegate {
+		return "Final conformance retry: emit exactly this tagged tool call so the harness can execute the guarded delegate refusal, then include agent-conformance-ok and the refusal in the final answer: " + conformanceDelegateTaggedCall
+	}
 	switch {
 	case !sawTool:
-		return "The previous response did not call the required conformance_echo tool. Retry the same conformance check now: you must call conformance_echo exactly once with input {\"value\":\"agent-conformance\"} before any final answer, then include the tool result marker in the final answer."
+		return "The previous response did not call the required conformance_echo tool. Retry the same conformance check now: first call conformance_echo exactly once with input " + conformanceEchoInputJSON + ", then call delegate exactly once with input " + conformanceDelegateInputJSON + "; do not provide a final answer until both tool calls have been attempted. If native delegate tool_calls are unavailable after conformance_echo, emit exactly " + conformanceDelegateTaggedCall + ". The delegate is expected to be refused by policy; include that refusal and the agent-conformance marker in the final answer."
 	case !sawBlockedDelegate:
-		return "The previous response called conformance_echo but did not attempt the required guarded delegation. Continue the same conformance check now: call delegate exactly once with input {\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}; do not answer in prose until that delegate call has been attempted. If native tool_calls are unavailable, emit exactly <tool_call name=\"delegate\">{\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}</tool_call>. The delegate is expected to be refused by policy; include that refusal and the agent-conformance marker in the final answer."
+		return "The previous response called conformance_echo but did not attempt the required guarded delegation. Continue the same conformance check now: call delegate exactly once with input " + conformanceDelegateInputJSON + "; do not answer in prose until that delegate call has been attempted. If native tool_calls are unavailable, emit exactly " + conformanceDelegateTaggedCall + ". The delegate is expected to be refused by policy; include that refusal and the agent-conformance marker in the final answer."
 	case !hasMarker:
-		return "The previous response completed the required tool calls but omitted the conformance marker. Continue the same conformance check now: do not call more tools; answer with the prior echo result marker agent-conformance-ok and mention the guarded delegate refusal."
+		return "The previous response completed the required tool calls but omitted the conformance marker. Continue the same conformance check now: do not call more tools, do not summarize, and do not use synonyms. Reply with exactly this sentence: agent-conformance-ok after guarded delegate refusal."
 	default:
 		return "Retry the provider conformance check and include the agent-conformance marker in the final answer."
 	}
@@ -458,6 +679,60 @@ func TestAgentProviderConformanceRetriesMissingDelegate(t *testing.T) {
 	}
 }
 
+func TestAgentProviderConformanceFailsWhenDelegateStillMissing(t *testing.T) {
+	var attempts int
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		attempts++
+		if err := validateConformanceRequest(req, opts); err != nil {
+			return nil, err
+		}
+		echo := opts.ToolHandler(ctx, ai.ToolCall{
+			ID:    fmt.Sprintf("fake-call-%d", attempts),
+			Name:  "conformance_echo",
+			Input: map[string]any{"value": "agent-conformance"},
+		})
+		return &ai.Response{
+			Reply:  "called conformance_echo with agent-conformance-ok but skipped delegate",
+			Answer: echo.Content,
+			ToolCalls: []ai.ToolCall{
+				{ID: fmt.Sprintf("fake-call-%d", attempts), Name: "conformance_echo", Input: map[string]any{"value": "agent-conformance"}, Result: echo.Content},
+			},
+		}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	var sawTool bool
+	var sawBlockedDelegate bool
+	a := New(
+		Name("conformance-retry-delegate-exhausted"),
+		Provider("fake"),
+		WithRegistry(registry.NewMemoryRegistry()),
+		WithStore(store.NewMemoryStore()),
+		WithMemory(NewInMemory(4)),
+		ApproveTool(func(tool string, input map[string]any) (bool, string) {
+			if tool == "delegate" {
+				sawBlockedDelegate = true
+				return false, "cross-provider conformance blocks delegate side effects"
+			}
+			return true, ""
+		}),
+		WithTool("conformance_echo", "Echo a conformance value.", map[string]any{
+			"value": map[string]any{"type": "string"},
+		}, func(ctx context.Context, input map[string]any) (string, error) {
+			sawTool = true
+			return `{"marker":"agent-conformance-ok"}`, nil
+		}),
+	)
+
+	_, err := askWithConformanceRetry(context.Background(), a, "Run the provider conformance check.", &sawTool, &sawBlockedDelegate)
+	if err == nil || !strings.Contains(err.Error(), "guarded delegate") {
+		t.Fatalf("Ask error = %v, want missing guarded delegate", err)
+	}
+	if attempts != 4 {
+		t.Fatalf("attempts = %d, want retries through max attempts", attempts)
+	}
+}
+
 func TestAgentExecutesProviderTextToolCallFallback(t *testing.T) {
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		if opts.ToolHandler == nil {
@@ -505,6 +780,61 @@ func TestAgentExecutesProviderTextToolCallFallback(t *testing.T) {
 	}
 }
 
+func TestAgentRepairsPartialTextToolCallFallback(t *testing.T) {
+	attempts := 0
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		if opts.ToolHandler == nil {
+			return nil, errors.New("missing tool handler")
+		}
+		attempts++
+		if attempts == 1 {
+			return &ai.Response{Reply: `<tool_call name="conformance_echo">`}, nil
+		}
+		if !strings.Contains(req.Prompt, "did not finish valid tool-call markup") {
+			return nil, fmt.Errorf("repair prompt = %q, want partial tool-call repair guidance", req.Prompt)
+		}
+		return &ai.Response{
+			Reply: `<tool_call name="conformance_echo">{"value":"agent-conformance"}</tool_call>`,
+		}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	var sawTool bool
+	a := New(
+		Name("conformance-partial-text-tool"),
+		Provider("fake"),
+		WithRegistry(registry.NewMemoryRegistry()),
+		WithStore(store.NewMemoryStore()),
+		WithMemory(NewInMemory(4)),
+		WithTool("conformance_echo", "Echo a conformance value.", map[string]any{
+			"value": map[string]any{"type": "string"},
+		}, func(ctx context.Context, input map[string]any) (string, error) {
+			sawTool = true
+			if input["value"] != "agent-conformance" {
+				return "", fmt.Errorf("unexpected value %v", input["value"])
+			}
+			return `{"marker":"agent-conformance-ok"}`, nil
+		}),
+	)
+
+	resp, err := a.Ask(context.Background(), "Run the partial text tool call fallback.")
+	if err != nil {
+		t.Fatalf("Ask: %v", err)
+	}
+	if attempts != 2 {
+		t.Fatalf("attempts = %d, want repair retry", attempts)
+	}
+	if !sawTool {
+		t.Fatal("repaired text tool call fallback did not execute the tool")
+	}
+	if len(resp.ToolCalls) != 1 || resp.ToolCalls[0].Name != "conformance_echo" {
+		t.Fatalf("ToolCalls = %+v, want conformance_echo", resp.ToolCalls)
+	}
+	if !strings.Contains(resp.Reply, "agent-conformance-ok") {
+		t.Fatalf("Reply = %q, want tool result marker", resp.Reply)
+	}
+}
+
 func TestAgentExecutesTextToolCallFallbackAfterStructuredToolCall(t *testing.T) {
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		if opts.ToolHandler == nil {

agent/guardrails_test.go

@@ -90,3 +90,23 @@ func TestApproveToolDoesNotGatePlan(t *testing.T) {
 		t.Error("plan should have been persisted despite the denying approver")
 	}
 }
+
+func TestNestedTextToolCallArgumentsAreRefused(t *testing.T) {
+	called := false
+	a := newTestAgent(Name("nested-tool-arg"),
+		WithTool("task.add", "add task", nil, func(context.Context, map[string]any) (string, error) {
+			called = true
+			return "created", nil
+		}),
+	)
+
+	content := toolContent(a.toolHandler(), "task.add", map[string]any{
+		"title": `Continue the launch plan. <tool_call name="plan">{"steps":[{"task":"Design","status":"pending"}]}</tool_call>`,
+	})
+	if called {
+		t.Fatal("tool handler ran despite nested text tool-call markup in arguments")
+	}
+	if !strings.Contains(content, "nested text tool-call markup") {
+		t.Fatalf("content = %q, want nested tool-call refusal", content)
+	}
+}

agent/integration_test.go

@@ -68,6 +68,8 @@ func init() {
 		_ = m.Init(opts...)
 		return m
 	})
+	ai.RegisterStream("fake")
+	ai.RegisterToolStream("fake")
 }
 
 // fakeClient embeds the default client (so NewRequest works) and

agent/otel.go

@@ -36,6 +36,8 @@ const (
 	AttrTotalTokens      = "agent.tokens.total"
 	AttrAttempt          = "agent.model.attempt"
 	AttrMaxAttempts      = "agent.model.max_attempts"
+	AttrToolAttempt      = "agent.tool.attempt"
+	AttrToolMaxAttempts  = "agent.tool.max_attempts"
 	AttrToolName         = "agent.tool.name"
 	AttrDelegate         = "agent.delegate"
 	AttrGuardrailBlock   = "agent.guardrail.block"
@@ -364,20 +366,33 @@ func (a *agentImpl) traceTool(next ai.ToolHandler) ai.ToolHandler {
 			res := next(ctx, call)
 			dur := time.Since(start).Milliseconds()
 			resErr := resultError(res)
-			a.recordRunEvent(RunEvent{Time: time.Now(), RunID: info.RunID, ParentID: info.ParentID, Agent: info.Agent, Kind: "tool", Name: call.Name, LatencyMS: dur, Refused: res.Refused, Error: resErr, ErrorKind: classifyToolError(resErr)})
+			toolAttempts := res.Attempts
+			if toolAttempts <= 0 {
+				toolAttempts = 1
+			}
+			a.recordRunEvent(RunEvent{Time: time.Now(), RunID: info.RunID, ParentID: info.ParentID, Agent: info.Agent, Kind: "tool", Name: call.Name, Attempt: toolAttempts, MaxAttempts: a.opts.ToolMaxAttempts, LatencyMS: dur, Refused: res.Refused, Error: resErr, ErrorKind: classifyToolError(resErr)})
 			return res
 		}
 
-		ctx, span := a.tracer().Start(ctx, spanNameToolCall, trace.WithAttributes(
+		spanAttrs := appendRunInfoAttributes([]attribute.KeyValue{
 			attribute.String(AttrRunID, info.RunID),
 			attribute.String(AttrParentRunID, info.ParentID),
 			attribute.String(AttrAgentName, info.Agent),
 			attribute.String(AttrToolName, call.Name),
 			attribute.Bool(AttrDelegate, call.Name == toolDelegate),
-		))
+		}, info)
+		ctx, span := a.tracer().Start(ctx, spanNameToolCall, trace.WithAttributes(spanAttrs...))
 		res := next(ctx, call)
 		dur := time.Since(start).Milliseconds()
 		attrs := []attribute.KeyValue{attribute.Int64(AttrLatencyMS, dur)}
+		toolAttempts := res.Attempts
+		if toolAttempts <= 0 {
+			toolAttempts = 1
+		}
+		attrs = append(attrs, attribute.Int(AttrToolAttempt, toolAttempts))
+		if a.opts.ToolMaxAttempts > 0 {
+			attrs = append(attrs, attribute.Int(AttrToolMaxAttempts, a.opts.ToolMaxAttempts))
+		}
 		if res.Refused != "" {
 			attrs = append(attrs, attribute.Bool(AttrGuardrailBlock, true), attribute.String(AttrRefusal, res.Refused))
 		}
@@ -393,7 +408,7 @@ func (a *agentImpl) traceTool(next ai.ToolHandler) ai.ToolHandler {
 		} else {
 			span.SetStatus(codes.Ok, "")
 		}
-		a.recordSpanEvent(span, RunEvent{Time: time.Now(), RunID: info.RunID, ParentID: info.ParentID, Agent: info.Agent, Kind: "tool", Name: call.Name, LatencyMS: dur, Refused: res.Refused, Error: resErr, ErrorKind: classifyToolError(resErr)})
+		a.recordSpanEvent(span, RunEvent{Time: time.Now(), RunID: info.RunID, ParentID: info.ParentID, Agent: info.Agent, Kind: "tool", Name: call.Name, Attempt: toolAttempts, MaxAttempts: a.opts.ToolMaxAttempts, LatencyMS: dur, Refused: res.Refused, Error: resErr, ErrorKind: classifyToolError(resErr)})
 		span.End()
 		return res
 	}
@@ -461,10 +476,18 @@ func runEventAttributes(e RunEvent) []attribute.KeyValue {
 		attrs = append(attrs, attribute.String(AttrModel, e.Model))
 	}
 	if e.Attempt > 0 {
-		attrs = append(attrs, attribute.Int(AttrAttempt, e.Attempt))
+		if e.Kind == "tool" {
+			attrs = append(attrs, attribute.Int(AttrToolAttempt, e.Attempt))
+		} else {
+			attrs = append(attrs, attribute.Int(AttrAttempt, e.Attempt))
+		}
 	}
 	if e.MaxAttempts > 0 {
-		attrs = append(attrs, attribute.Int(AttrMaxAttempts, e.MaxAttempts))
+		if e.Kind == "tool" {
+			attrs = append(attrs, attribute.Int(AttrToolMaxAttempts, e.MaxAttempts))
+		} else {
+			attrs = append(attrs, attribute.Int(AttrMaxAttempts, e.MaxAttempts))
+		}
 	}
 	if e.LatencyMS > 0 {
 		attrs = append(attrs, attribute.Int64(AttrLatencyMS, e.LatencyMS))
@@ -624,7 +647,7 @@ func runStatus(events []RunEvent) string {
 		if e.Error != "" || e.Kind == "error" {
 			status = runErrorStatus(e.ErrorKind)
 		}
-		if e.Kind == "done" && status == "running" {
+		if e.Kind == "done" {
 			status = "done"
 		}
 	}

agent/otel_test.go

@@ -103,8 +103,10 @@ func TestAgentOpenTelemetrySpans(t *testing.T) {
 				t.Fatalf("model span missing model event: %#v", s.Events())
 			}
 		}
-		if s.Name() == spanNameToolCall && !spanEventHasRunInfo(s.Events(), "agent.tool", runID, "runner") {
-			t.Fatalf("tool span missing tool event: %#v", s.Events())
+		if s.Name() == spanNameToolCall {
+			if !spanEventHasRunInfo(s.Events(), "agent.tool", runID, "runner") {
+				t.Fatalf("tool span missing tool event: %#v", s.Events())
+			}
 		}
 	}
 	keys, err := store.Scope(st, "agent", "runner").List(store.ListPrefix("runs/"))
@@ -142,6 +144,121 @@ func TestAgentOpenTelemetrySpans(t *testing.T) {
 	}
 }
 
+func TestAgentOpenTelemetryToolSpanIncludesWorkflowRunInfo(t *testing.T) {
+	exp := tracetest.NewInMemoryExporter()
+	tp := trace.NewTracerProvider(trace.WithSyncer(exp))
+	st := store.NewMemoryStore()
+	a := New(Name("workflow-tool"), Provider("oteltest"), WithStore(st), TraceProvider(tp)).(*agentImpl)
+	handler := a.traceTool(func(context.Context, ai.ToolCall) ai.ToolResult {
+		return ai.ToolResult{Value: "ok"}
+	})
+	ctx := ai.WithRunInfo(context.Background(), ai.RunInfo{
+		RunID:    "run-workflow-tool",
+		ParentID: "parent-run",
+		Agent:    "workflow-tool",
+		Flow:     "deploy",
+		Step:     "notify",
+		Dispatch: "workflow",
+		Trigger:  "manual",
+	})
+
+	res := handler(ctx, ai.ToolCall{ID: "call-1", Name: "notify", Input: map[string]any{"ok": true}})
+	if resultError(res) != "" {
+		t.Fatalf("tool returned error: %#v", res)
+	}
+
+	for _, span := range exp.GetSpans().Snapshots() {
+		if span.Name() != spanNameToolCall {
+			continue
+		}
+		attrs := spanAttributes(span.Attributes())
+		if attrs[AttrRunID] != "run-workflow-tool" || attrs[AttrParentRunID] != "parent-run" || attrs[AttrAgentName] != "workflow-tool" {
+			t.Fatalf("tool span missing run lineage: %#v", attrs)
+		}
+		if attrs[AttrFlowName] != "deploy" || attrs[AttrFlowStep] != "notify" || attrs[AttrDispatch] != "workflow" || attrs[AttrTrigger] != "manual" {
+			t.Fatalf("tool span missing workflow run info: %#v", attrs)
+		}
+		return
+	}
+	t.Fatalf("tool span not emitted; got %d spans", len(exp.GetSpans().Snapshots()))
+}
+
+func TestAgentOpenTelemetryToolRetryAttempts(t *testing.T) {
+	exp := tracetest.NewInMemoryExporter()
+	tp := trace.NewTracerProvider(trace.WithSyncer(exp))
+	st := store.NewMemoryStore()
+	calls := 0
+	a := New(
+		Name("tool-retry-otel"),
+		Provider("oteltest"),
+		WithStore(st),
+		TraceProvider(tp),
+		ToolRetry(3, time.Millisecond),
+		WithTool("probe", "probe", nil, func(context.Context, map[string]any) (string, error) {
+			calls++
+			if calls == 1 {
+				return "", errors.New("rate limit exceeded")
+			}
+			return "ok", nil
+		}),
+	)
+	if _, err := a.Ask(context.Background(), "hello"); err != nil {
+		t.Fatal(err)
+	}
+	if calls != 2 {
+		t.Fatalf("tool calls = %d, want retry success after 2 attempts", calls)
+	}
+
+	var sawToolSpan bool
+	for _, span := range exp.GetSpans().Snapshots() {
+		if span.Name() != spanNameToolCall {
+			continue
+		}
+		attrs := spanAttributes(span.Attributes())
+		if attrs[AttrToolName] != "probe" {
+			continue
+		}
+		if attrs[AttrToolAttempt] != "2" || attrs[AttrToolMaxAttempts] != "3" {
+			t.Fatalf("tool retry span attempts = %#v", attrs)
+		}
+		if !spanEventHasAttr(span.Events(), "agent.tool", AttrToolAttempt, "2") || !spanEventHasAttr(span.Events(), "agent.tool", AttrToolMaxAttempts, "3") {
+			t.Fatalf("tool retry event missing attempt attributes: %#v", span.Events())
+		}
+		sawToolSpan = true
+	}
+	if !sawToolSpan {
+		t.Fatal("tool retry span not emitted")
+	}
+
+	summaries, err := ListRunSummaries(st, "tool-retry-otel")
+	if err != nil {
+		t.Fatal(err)
+	}
+	events, err := LoadRunEvents(st, "tool-retry-otel", summaries[0].RunID)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, event := range events {
+		if event.Kind == "tool" && event.Name == "probe" && event.Attempt == 2 && event.MaxAttempts == 3 {
+			return
+		}
+	}
+	t.Fatalf("persisted tool event missing retry attempts: %#v", events)
+}
+
+func spanEventHasAttr(events []trace.Event, name, key, value string) bool {
+	for _, event := range events {
+		if event.Name != name {
+			continue
+		}
+		attrs := spanAttributes(event.Attributes)
+		if attrs[key] == value {
+			return true
+		}
+	}
+	return false
+}
+
 func TestAgentRunObservabilityRedactsInputByDefault(t *testing.T) {
 	secret := "deploy production with token sk-secret"
 	exp := tracetest.NewInMemoryExporter()

agent/resilience_test.go

@@ -83,6 +83,62 @@ func TestAskRetriesTransientErrorsThenSurfacesStructuredError(t *testing.T) {
 	}
 }
 
+func TestModelRetryDoesNotDuplicateCheckpointedToolSideEffects(t *testing.T) {
+	ctx := context.Background()
+	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "retry-tool-dedupe-agent")
+	attempts := 0
+	toolRuns := 0
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		attempts++
+		if opts.ToolHandler == nil {
+			t.Fatal("missing tool handler")
+		}
+		res := opts.ToolHandler(ctx, ai.ToolCall{ID: "create-1", Name: "external.create", Input: map[string]any{"title": "Retry safe"}})
+		if res.Content != "created Retry safe" {
+			t.Fatalf("tool result = %q, want cached create result", res.Content)
+		}
+		if attempts == 1 {
+			return nil, testStatusError{code: 503}
+		}
+		return &ai.Response{Reply: "done", ToolCalls: []ai.ToolCall{{ID: "create-1", Name: "external.create", Input: map[string]any{"title": "Retry safe"}, Result: res.Content}}}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	a := newTestAgent(
+		Name("retry-tool-dedupe-agent"),
+		WithCheckpoint(cp),
+		ModelRetry(2, time.Millisecond),
+		WithTool("external.create", "create once", nil, func(context.Context, map[string]any) (string, error) {
+			toolRuns++
+			return "created Retry safe", nil
+		}),
+	)
+
+	resp, err := a.Ask(ctx, "create once despite a transient provider retry")
+	if err != nil {
+		t.Fatalf("Ask: %v", err)
+	}
+	if resp.Reply != "done" {
+		t.Fatalf("reply = %q, want done", resp.Reply)
+	}
+	if attempts != 2 {
+		t.Fatalf("model attempts = %d, want retry after transient provider failure", attempts)
+	}
+	if toolRuns != 1 {
+		t.Fatalf("tool executions = %d, want checkpointed side effect reused across retry", toolRuns)
+	}
+	runs, err := cp.List(ctx)
+	if err != nil {
+		t.Fatalf("List: %v", err)
+	}
+	if len(runs) != 1 {
+		t.Fatalf("checkpointed runs = %d, want 1", len(runs))
+	}
+	if _, ok := findStep(runs[0].Steps, `tool:external.create:{"title":"Retry safe"}`); !ok {
+		t.Fatalf("checkpoint steps = %#v, want completed external.create step", runs[0].Steps)
+	}
+}
+
 func TestAskRateLimitFailureSuggestsPreflightAndInspect(t *testing.T) {
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		return nil, testStatusError{code: 429}
@@ -184,6 +240,55 @@ func TestAskCancellationDuringToolCallFailsRun(t *testing.T) {
 	}
 }
 
+func TestSlowProviderTimeoutPreventsLateToolSideEffects(t *testing.T) {
+	started := make(chan struct{})
+	release := make(chan struct{})
+	done := make(chan struct{})
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		close(started)
+		<-release
+		defer close(done)
+		if opts.ToolHandler == nil {
+			t.Fatal("missing tool handler")
+		}
+		res := opts.ToolHandler(ctx, ai.ToolCall{ID: "late-1", Name: "external.create", Input: map[string]any{"title": "too late"}})
+		if !strings.Contains(res.Content, context.DeadlineExceeded.Error()) {
+			t.Errorf("late tool result = %q, want deadline exceeded", res.Content)
+		}
+		return &ai.Response{Reply: "late", ToolCalls: []ai.ToolCall{{ID: "late-1", Name: "external.create", Input: map[string]any{"title": "too late"}, Result: res.Content}}}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	toolRuns := 0
+	a := newTestAgent(
+		Name("slow-provider-late-tool"),
+		ModelCallTimeout(10*time.Millisecond),
+		WithTool("external.create", "create once", nil, func(context.Context, map[string]any) (string, error) {
+			toolRuns++
+			return "created", nil
+		}),
+	)
+
+	_, err := a.Ask(context.Background(), "provider times out before tool")
+	if !errors.Is(err, context.DeadlineExceeded) {
+		t.Fatalf("Ask error = %v, want deadline exceeded", err)
+	}
+	select {
+	case <-started:
+	default:
+		t.Fatal("provider was not called")
+	}
+	close(release)
+	select {
+	case <-done:
+	case <-time.After(time.Second):
+		t.Fatal("late provider call did not finish")
+	}
+	if toolRuns != 0 {
+		t.Fatalf("late tool executions = %d, want 0", toolRuns)
+	}
+}
+
 func TestAskCheckpointRecordsTerminalOperationalFailureStatus(t *testing.T) {
 	tests := []struct {
 		name string
@@ -222,6 +327,12 @@ func TestAskCheckpointRecordsTerminalOperationalFailureStatus(t *testing.T) {
 			if len(runs[0].Steps) == 0 || runs[0].Steps[0].Status != tt.want {
 				t.Fatalf("step status = %#v, want %q", runs[0].Steps, tt.want)
 			}
+			if runs[0].Steps[0].Attempts != 1 {
+				t.Fatalf("step attempts = %d, want 1", runs[0].Steps[0].Attempts)
+			}
+			if got := runs[0].Steps[0].ErrorKind; got != string(ai.ClassifyError(tt.err)) {
+				t.Fatalf("step error kind = %q, want %q", got, ai.ClassifyError(tt.err))
+			}
 			if pending, err := Pending(context.Background(), a); err != nil || len(pending) != 0 {
 				t.Fatalf("Pending = %#v, %v; want no terminal run", pending, err)
 			}

agent/stream.go

@@ -71,14 +71,15 @@ func ResumeStreamAsk(ctx context.Context, ag Agent, runID string) (AgentStream,
 // StreamAsk runs tools like Ask, emits ToolStart/ToolEnd events as they execute,
 // then emits chunks of the final answer followed by a Done event.
 func (a *agentImpl) StreamAsk(ctx context.Context, message string) (AgentStream, error) {
+	streamCtx, cancel := context.WithCancel(ctx)
 	events := make(chan *StreamEvent, 16)
 	done := make(chan struct{})
-	s := &agentStream{events: events, done: done}
+	s := &agentStream{events: events, done: done, cancel: cancel}
 
 	go func() {
 		defer close(events)
 		defer close(done)
-		resp, err := a.askWithStreamEvents(ctx, message, events)
+		resp, err := a.askWithStreamEvents(streamCtx, message, events)
 		if err != nil {
 			s.setErr(err)
 			return
@@ -94,14 +95,15 @@ func (a *agentImpl) StreamAsk(ctx context.Context, message string) (AgentStream,
 }
 
 func (a *agentImpl) resumeStreamAsk(ctx context.Context, runID string) (AgentStream, error) {
+	streamCtx, cancel := context.WithCancel(ctx)
 	events := make(chan *StreamEvent, 16)
 	done := make(chan struct{})
-	s := &agentStream{events: events, done: done}
+	s := &agentStream{events: events, done: done, cancel: cancel}
 
 	go func() {
 		defer close(events)
 		defer close(done)
-		resp, err := a.resumeWithStreamEvents(ctx, runID, events)
+		resp, err := a.resumeWithStreamEvents(streamCtx, runID, events)
 		if err != nil {
 			s.setErr(err)
 			return
@@ -260,6 +262,7 @@ func (a *agentImpl) streamAskAI(ctx context.Context, message string) (ai.Stream,
 type agentStream struct {
 	events <-chan *StreamEvent
 	done   <-chan struct{}
+	cancel context.CancelFunc
 	mu     sync.Mutex
 	err    error
 }
@@ -278,6 +281,9 @@ func (s *agentStream) Recv() (*StreamEvent, error) {
 }
 
 func (s *agentStream) Close() error {
+	if s.cancel != nil {
+		s.cancel()
+	}
 	<-s.done
 	return nil
 }

agent/stream_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"io"
 	"testing"
+	"time"
 
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/flow"
@@ -75,6 +76,39 @@ func TestStreamAskEmitsToolEventsAndFinalTokens(t *testing.T) {
 	}
 }
 
+func TestStreamAskCloseCancelsInFlightModelCall(t *testing.T) {
+	started := make(chan struct{})
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		close(started)
+		<-ctx.Done()
+		return nil, ctx.Err()
+	}
+	defer func() { fakeGen = nil }()
+
+	a := newTestAgent(Name("stream-cancel"))
+	stream, err := a.StreamAsk(context.Background(), "cancel me")
+	if err != nil {
+		t.Fatalf("StreamAsk: %v", err)
+	}
+
+	select {
+	case <-started:
+	case <-time.After(time.Second):
+		t.Fatal("model call did not start")
+	}
+
+	closed := make(chan error, 1)
+	go func() { closed <- stream.Close() }()
+	select {
+	case err := <-closed:
+		if err != nil {
+			t.Fatalf("Close: %v", err)
+		}
+	case <-time.After(time.Second):
+		t.Fatal("Close did not cancel the in-flight stream")
+	}
+}
+
 func TestStreamAskHelperRejectsUnsupportedAgent(t *testing.T) {
 	_, err := StreamAsk(context.Background(), unsupportedAgent{}, "hello")
 	if err == nil {
@@ -209,6 +243,29 @@ func TestResumeStreamAskDoesNotReplayCompletedTool(t *testing.T) {
 	}
 }
 
+func TestAgentStreamDoesNotRecordUserWhenProviderStreamingUnsupported(t *testing.T) {
+	fakeStream = func(ctx context.Context, opts ai.Options, req *ai.Request) (ai.Stream, error) {
+		if len(req.Messages) == 0 || req.Messages[len(req.Messages)-1].Role != "user" || req.Messages[len(req.Messages)-1].Content != "stream fallback" {
+			t.Fatalf("stream request messages = %+v, want pending user message", req.Messages)
+		}
+		return nil, ai.ErrStreamingUnsupported
+	}
+	defer func() { fakeStream = nil }()
+
+	mem := NewInMemory(8)
+	a := newTestAgent(Name("stream-fallback"), WithMemory(mem), WithTool("echo", "echo text", nil, func(context.Context, map[string]any) (string, error) {
+		return "ok", nil
+	}))
+
+	_, err := a.Stream(context.Background(), "stream fallback")
+	if !errors.Is(err, ai.ErrStreamingUnsupported) {
+		t.Fatalf("Stream error = %v, want ErrStreamingUnsupported", err)
+	}
+	if got := mem.Messages(); len(got) != 0 {
+		t.Fatalf("memory after unsupported stream = %+v, want no recorded messages", got)
+	}
+}
+
 type unsupportedAgent struct{}
 
 func (unsupportedAgent) Name() string                                      { return "unsupported" }

agent/text_tool_calls.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"html"
 	"regexp"
 	"strings"
 
@@ -12,14 +13,17 @@ import (
 
 var fencedJSONBlock = regexp.MustCompile("(?s)```(?:json)?\\s*(.*?)\\s*```")
 var taggedToolCallBlock = regexp.MustCompile(`(?s)<[^<>]*(?:tool_call|tool_calls|function=)[^<>]*>(.*?)</[^<>]*>`)
-var singleTaggedToolCall = regexp.MustCompile(`(?s)<(tool_call\b[^<>]*|[^<>]*function=[^<>]*)>(.*?)</[^<>]*>`)
+var singleTaggedToolCall = regexp.MustCompile(`(?s)<(tool_call\b[^<>]*|[^<>]*function\s*=[^<>]*)>(.*?)</[^<>]*>`)
+var taggedToolNameAttr = regexp.MustCompile(`(?i)(?:function|name|tool)\s*=\s*["\']?([^"\'\s>]+)`)
+var openingTaggedToolCall = regexp.MustCompile(`(?i)<(tool_call\b[^<>]*|[^<>]*function\s*=[^<>]*)>`)
 
 type textToolCall struct {
 	ID        string         `json:"id"`
 	Name      string         `json:"name"`
 	Tool      string         `json:"tool"`
 	Input     map[string]any `json:"input"`
-	Arguments map[string]any `json:"arguments"`
+	Arguments any            `json:"arguments"`
+	Function  *textToolCall  `json:"function"`
 }
 
 // executeTextToolCalls is a compatibility fallback for providers that return a
@@ -90,6 +94,7 @@ func textToolCallKey(call ai.ToolCall) string {
 }
 
 func parseTextToolCalls(text string, tools []ai.Tool) []ai.ToolCall {
+	text = html.UnescapeString(text)
 	allowed := textToolNames(tools)
 	if len(allowed) == 0 {
 		return nil
@@ -98,6 +103,9 @@ func parseTextToolCalls(text string, tools []ai.Tool) []ai.ToolCall {
 	if calls := decodeTaggedTextToolCalls(text, allowed); len(calls) > 0 {
 		return calls
 	}
+	if calls := decodeFunctionTextToolCalls(text, allowed); len(calls) > 0 {
+		return calls
+	}
 	for _, candidate := range jsonCandidates(text) {
 		if calls := decodeTextToolCalls(candidate, allowed); len(calls) > 0 {
 			return calls
@@ -106,6 +114,37 @@ func parseTextToolCalls(text string, tools []ai.Tool) []ai.ToolCall {
 	return nil
 }
 
+func partialTextToolCallName(text string, tools []ai.Tool) string {
+	text = html.UnescapeString(text)
+	allowed := textToolNames(tools)
+	if len(allowed) == 0 {
+		return ""
+	}
+	openMatches := openingTaggedToolCall.FindAllStringSubmatchIndex(text, -1)
+	if len(openMatches) == 0 {
+		return ""
+	}
+	closedMatches := singleTaggedToolCall.FindAllStringSubmatchIndex(text, -1)
+	for _, open := range openMatches {
+		closed := false
+		for _, match := range closedMatches {
+			if match[0] == open[0] {
+				closed = true
+				break
+			}
+		}
+		if closed {
+			continue
+		}
+		tag := text[open[2]:open[3]]
+		name := taggedToolName(tag)
+		if canonical := allowed[name]; canonical != "" {
+			return canonical
+		}
+	}
+	return ""
+}
+
 func textToolNames(tools []ai.Tool) map[string]string {
 	allowed := map[string]string{}
 	for _, tool := range tools {
@@ -176,14 +215,7 @@ func collectTextToolCalls(v any, allowed map[string]string) []ai.ToolCall {
 			return collectTextToolCalls(nested, allowed)
 		}
 		call := mapToTextToolCall(x)
-		name := call.Name
-		if name == "" {
-			name = call.Tool
-		}
-		input := call.Input
-		if input == nil {
-			input = call.Arguments
-		}
+		name, input := textToolCallNameAndInput(call)
 		if name == "" || allowed[name] == "" || input == nil {
 			return nil
 		}
@@ -197,6 +229,61 @@ func collectTextToolCalls(v any, allowed map[string]string) []ai.ToolCall {
 	}
 }
 
+func textToolCallNameAndInput(call textToolCall) (string, map[string]any) {
+	name := call.Name
+	if name == "" {
+		name = call.Tool
+	}
+	input := call.Input
+	if input == nil {
+		input = textToolArguments(call.Arguments)
+	}
+	if call.Function != nil {
+		fnName, fnInput := textToolCallNameAndInput(*call.Function)
+		if name == "" {
+			name = fnName
+		}
+		if input == nil {
+			input = fnInput
+		}
+	}
+	return name, input
+}
+
+func textToolArguments(raw any) map[string]any {
+	switch args := raw.(type) {
+	case map[string]any:
+		return args
+	case string:
+		var input map[string]any
+		if err := json.Unmarshal([]byte(args), &input); err == nil {
+			return input
+		}
+	}
+	return nil
+}
+
+func containsNestedTextToolCall(v any) bool {
+	switch x := v.(type) {
+	case string:
+		text := html.UnescapeString(x)
+		return openingTaggedToolCall.MatchString(text) || singleTaggedToolCall.MatchString(text)
+	case map[string]any:
+		for _, item := range x {
+			if containsNestedTextToolCall(item) {
+				return true
+			}
+		}
+	case []any:
+		for _, item := range x {
+			if containsNestedTextToolCall(item) {
+				return true
+			}
+		}
+	}
+	return false
+}
+
 func decodeTaggedTextToolCalls(text string, allowed map[string]string) []ai.ToolCall {
 	var out []ai.ToolCall
 	for _, match := range singleTaggedToolCall.FindAllStringSubmatch(text, -1) {
@@ -230,17 +317,130 @@ func decodeTaggedTextToolCalls(text string, allowed map[string]string) []ai.Tool
 }
 
 func taggedToolName(tag string) string {
-	for _, marker := range []string{"function=", "name=", "tool="} {
-		if idx := strings.Index(tag, marker); idx >= 0 {
-			name := strings.TrimSpace(tag[idx+len(marker):])
-			name = strings.Trim(name, `"'`)
-			if end := strings.IndexAny(name, " \t\r\n>"); end >= 0 {
-				name = name[:end]
+	match := taggedToolNameAttr.FindStringSubmatch(tag)
+	if len(match) < 2 {
+		return ""
+	}
+	return strings.Trim(match[1], `"'`)
+}
+
+func decodeFunctionTextToolCalls(text string, allowed map[string]string) []ai.ToolCall {
+	var out []ai.ToolCall
+	for alias, canonical := range allowed {
+		for _, body := range functionCallBodies(text, alias) {
+			var input map[string]any
+			if err := json.Unmarshal([]byte(body), &input); err != nil || input == nil {
+				continue
 			}
-			return strings.Trim(name, `"'`)
+			out = append(out, ai.ToolCall{
+				ID:    fmt.Sprintf("text-call-%s", strings.ReplaceAll(alias, ".", "_")),
+				Name:  canonical,
+				Input: input,
+			})
 		}
 	}
-	return ""
+	return out
+}
+
+func functionCallBodies(text, name string) []string {
+	if name == "" {
+		return nil
+	}
+	var bodies []string
+	for searchFrom := 0; searchFrom < len(text); {
+		idx := strings.Index(text[searchFrom:], name)
+		if idx < 0 {
+			break
+		}
+		start := searchFrom + idx
+		open := start + len(name)
+		if !isFunctionCallBoundary(text, start, open) {
+			searchFrom = start + len(name)
+			continue
+		}
+		bodyStart := open + 1
+		bodyEnd, ok := balancedJSONObjectEnd(text, bodyStart)
+		if !ok {
+			searchFrom = bodyStart
+			continue
+		}
+		bodies = append(bodies, strings.TrimSpace(text[bodyStart:bodyEnd]))
+		searchFrom = bodyEnd + 1
+	}
+	return bodies
+}
+
+func isFunctionCallBoundary(text string, start, open int) bool {
+	if open >= len(text) || text[open] != '(' {
+		return false
+	}
+	if start > 0 {
+		prev := text[start-1]
+		if prev == '_' || prev == '.' || prev == '-' || prev == '$' || ('0' <= prev && prev <= '9') || ('A' <= prev && prev <= 'Z') || ('a' <= prev && prev <= 'z') {
+			return false
+		}
+	}
+	for i := open + 1; i < len(text); i++ {
+		switch text[i] {
+		case ' ', '\n', '\r', '\t':
+			continue
+		case '{':
+			return true
+		default:
+			return false
+		}
+	}
+	return false
+}
+
+func balancedJSONObjectEnd(text string, start int) (int, bool) {
+	for start < len(text) {
+		switch text[start] {
+		case ' ', '\n', '\r', '\t':
+			start++
+		case '{':
+			depth := 0
+			inString := false
+			escaped := false
+			for i := start; i < len(text); i++ {
+				c := text[i]
+				if inString {
+					if escaped {
+						escaped = false
+					} else if c == '\\' {
+						escaped = true
+					} else if c == '"' {
+						inString = false
+					}
+					continue
+				}
+				switch c {
+				case '"':
+					inString = true
+				case '{':
+					depth++
+				case '}':
+					depth--
+					if depth == 0 {
+						for j := i + 1; j < len(text); j++ {
+							switch text[j] {
+							case ' ', '\n', '\r', '\t':
+								continue
+							case ')':
+								return i + 1, true
+							default:
+								return 0, false
+							}
+						}
+					}
+				}
+			}
+			return 0, false
+		default:
+			return 0, false
+		}
+	}
+	return 0, false
 }
 
 func firstNestedToolCalls(m map[string]any) (any, bool) {

agent/text_tool_calls_test.go

@@ -56,3 +56,93 @@ func TestParseTextToolCallsCreateAliasForAddTool(t *testing.T) {
 		t.Fatalf("title = %v, want Design", got)
 	}
 }
+
+func TestParseTextToolCallsOpenAICompatibleFunctionArgumentsString(t *testing.T) {
+	tools := []ai.Tool{{Name: "delegate"}}
+	reply := `<tool_call>{"id":"call-2","type":"function","function":{"name":"delegate","arguments":"{\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}"}}</tool_call>`
+
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) != 1 {
+		t.Fatalf("parseTextToolCalls returned %d calls, want 1: %+v", len(calls), calls)
+	}
+	if calls[0].Name != "delegate" {
+		t.Fatalf("call name = %q, want delegate", calls[0].Name)
+	}
+	if got := calls[0].Input["task"]; got != "summarize the conformance marker" {
+		t.Fatalf("task = %v, want summarize the conformance marker", got)
+	}
+	if got := calls[0].Input["to"]; got != "blocked-reviewer" {
+		t.Fatalf("to = %v, want blocked-reviewer", got)
+	}
+}
+
+func TestParseTextToolCallsTaggedMarkupWithSpacedNameAttribute(t *testing.T) {
+	tools := []ai.Tool{{Name: "delegate"}}
+	reply := `<tool_call name = "delegate">{"task":"summarize the conformance marker","to":"blocked-reviewer"}</tool_call>`
+
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) != 1 {
+		t.Fatalf("parseTextToolCalls returned %d calls, want 1: %+v", len(calls), calls)
+	}
+	if calls[0].Name != "delegate" {
+		t.Fatalf("call name = %q, want delegate", calls[0].Name)
+	}
+	if got := calls[0].Input["to"]; got != "blocked-reviewer" {
+		t.Fatalf("to = %v, want blocked-reviewer", got)
+	}
+}
+
+func TestParseTextToolCallsHTMLEscapedTaggedMarkup(t *testing.T) {
+	tools := []ai.Tool{{Name: "delegate"}}
+	reply := `&lt;tool_call name=&quot;delegate&quot;&gt;{"task":"summarize the conformance marker","to":"blocked-reviewer"}&lt;/tool_call&gt;`
+
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) != 1 {
+		t.Fatalf("parseTextToolCalls returned %d calls, want 1: %+v", len(calls), calls)
+	}
+	if calls[0].Name != "delegate" {
+		t.Fatalf("call name = %q, want delegate", calls[0].Name)
+	}
+	if got := calls[0].Input["task"]; got != "summarize the conformance marker" {
+		t.Fatalf("task = %v, want summarize the conformance marker", got)
+	}
+}
+
+func TestParseTextToolCallsFunctionCallSyntax(t *testing.T) {
+	tools := []ai.Tool{{Name: "delegate"}}
+	reply := `I will now call delegate({"task":"summarize the conformance marker","to":"blocked-reviewer"}) before answering.`
+
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) != 1 {
+		t.Fatalf("parseTextToolCalls returned %d calls, want 1: %+v", len(calls), calls)
+	}
+	if calls[0].Name != "delegate" {
+		t.Fatalf("call name = %q, want delegate", calls[0].Name)
+	}
+	if got := calls[0].Input["task"]; got != "summarize the conformance marker" {
+		t.Fatalf("task = %v, want summarize the conformance marker", got)
+	}
+	if got := calls[0].Input["to"]; got != "blocked-reviewer" {
+		t.Fatalf("to = %v, want blocked-reviewer", got)
+	}
+}
+
+func TestParseTextToolCallsFunctionCallSyntaxHandlesNestedJSON(t *testing.T) {
+	tools := []ai.Tool{{Name: "delegate"}}
+	reply := `delegate({
+		"task":"summarize the {escaped} marker",
+		"meta":{"note":"paren ) and brace } in string"},
+		"to":"blocked-reviewer"
+	})`
+
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) != 1 {
+		t.Fatalf("parseTextToolCalls returned %d calls, want 1: %+v", len(calls), calls)
+	}
+	if got := calls[0].Input["task"]; got != "summarize the {escaped} marker" {
+		t.Fatalf("task = %v, want nested JSON-safe task", got)
+	}
+	if got := calls[0].Input["to"]; got != "blocked-reviewer" {
+		t.Fatalf("to = %v, want blocked-reviewer", got)
+	}
+}

ai/anthropic/anthropic.go

@@ -19,6 +19,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("anthropic")
+	ai.RegisterToolStream("anthropic")
 }
 
 // Provider implements the ai.Model interface for Anthropic Claude
@@ -297,7 +298,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 	// Read response
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	// Parse response

ai/atlascloud/atlascloud.go

@@ -24,6 +24,7 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -93,20 +94,9 @@ func (p *Provider) Options() ai.Options { return p.opts }
 func (p *Provider) String() string      { return "atlascloud" }
 
 func (p *Provider) Generate(ctx context.Context, req *ai.Request, opts ...ai.GenerateOption) (*ai.Response, error) {
-	var tools []map[string]any
-	for _, t := range req.Tools {
-		tools = append(tools, map[string]any{
-			"type": "function",
-			"function": map[string]any{
-				"name":        t.Name,
-				"description": t.Description,
-				"parameters": map[string]any{
-					"type":       "object",
-					"properties": t.Properties,
-				},
-			},
-		})
-	}
+	tools := atlascloudTools(req.Tools)
+	compatTools, compatPrompt := atlascloudMinimaxCompatTools(p.opts.Model, req.Tools)
+	textToolPrompt := atlascloudMinimaxTextToolPrompt(p.opts.Model, req.Tools)
 
 	messages := []map[string]any{
 		{"role": "system", "content": req.SystemPrompt},
@@ -117,6 +107,9 @@ func (p *Provider) Generate(ctx context.Context, req *ai.Request, opts ...ai.Gen
 	if req.Prompt != "" {
 		messages = append(messages, map[string]any{"role": "user", "content": req.Prompt})
 	}
+	if compatPrompt != "" {
+		messages = append(messages, map[string]any{"role": "system", "content": compatPrompt})
+	}
 
 	apiReq := map[string]any{
 		"model":    p.opts.Model,
@@ -132,7 +125,45 @@ func (p *Provider) Generate(ctx context.Context, req *ai.Request, opts ...ai.Gen
 
 	resp, rawMessage, err := p.callAPI(ctx, "chat", apiReq)
 	if err != nil {
-		return nil, err
+		if atlascloudShouldRetryMinimaxCompat(err, compatTools) {
+			apiReq["tools"] = compatTools
+			resp, rawMessage, err = p.callAPI(ctx, "chat-minimax-compat", apiReq)
+		}
+		if atlascloudShouldRetryMinimaxTextTools(err, textToolPrompt) {
+			delete(apiReq, "tools")
+			apiReq["messages"] = append(messages, map[string]any{"role": "system", "content": textToolPrompt})
+			resp, rawMessage, err = p.callAPI(ctx, "chat-minimax-text-tools", apiReq)
+		}
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	if toolName := atlascloudPartialTextToolCallName(resp.Reply, req.Tools); toolName != "" {
+		repairReq := map[string]any{
+			"model": p.opts.Model,
+			"messages": append(append([]map[string]any(nil), messages...),
+				map[string]any{"role": "assistant", "content": resp.Reply},
+				map[string]any{"role": "user", "content": fmt.Sprintf("Your previous response started a %q tool call but did not finish valid tool-call markup or JSON arguments, so no tool was executed. Retry the same step now by emitting one complete valid tool call for %q. Do not describe the action in prose, and do not claim completion until the tool call succeeds.", toolName, toolName)},
+			),
+		}
+		if p.opts.MaxTokens > 0 {
+			repairReq["max_tokens"] = p.opts.MaxTokens
+		}
+		if len(tools) > 0 {
+			repairReq["tools"] = tools
+		}
+		resp, rawMessage, err = p.callAPI(ctx, "chat-partial-tool-repair", repairReq)
+		if err != nil {
+			return nil, fmt.Errorf("atlascloud partial text tool-call repair failed for %q: %w", toolName, err)
+		}
+		if atlascloudPartialTextToolCallName(resp.Reply, req.Tools) != "" && len(resp.ToolCalls) == 0 {
+			fallback := atlascloudFallbackTextToolCall(toolName, req)
+			if fallback == "" {
+				return nil, fmt.Errorf("atlascloud returned incomplete text tool call for %q after repair", toolName)
+			}
+			resp.Reply = fallback
+		}
 	}
 
 	if len(resp.ToolCalls) == 0 {
@@ -140,66 +171,105 @@ func (p *Provider) Generate(ctx context.Context, req *ai.Request, opts ...ai.Gen
 	}
 
 	if p.opts.ToolHandler != nil {
-		allToolCalls := append([]ai.ToolCall(nil), resp.ToolCalls...)
+		var allToolCalls []ai.ToolCall
 		var toolResults []string
+		pendingToolCalls := append([]ai.ToolCall(nil), resp.ToolCalls...)
 		followUpMessages := append(messages, map[string]any{
 			"role":       "assistant",
 			"content":    rawMessage["content"],
 			"tool_calls": rawMessage["tool_calls"],
 		})
 
-		for _, tc := range resp.ToolCalls {
-			content := p.opts.ToolHandler(ctx, tc).Content
-			if content != "" {
-				toolResults = append(toolResults, content)
-			}
-			followUpMessages = append(followUpMessages, map[string]any{
-				"role":         "tool",
-				"tool_call_id": tc.ID,
-				"content":      content,
-			})
-		}
-
-		followUpReq := map[string]any{
-			"model":    p.opts.Model,
-			"messages": followUpMessages,
-		}
-		if len(tools) > 0 {
-			// Keep the tool schema available during the follow-up turn. Minimax
-			// models behind Atlas Cloud sometimes call one required tool, inspect
-			// that result, and then issue a second tool call (for example a guarded
-			// delegate conformance check) instead of completing immediately.
-			followUpReq["tools"] = tools
-		}
-
-		followUpResp, _, err := p.callAPI(ctx, "tool-follow-up", followUpReq)
-		if err != nil {
-			return nil, err
-		}
-		if len(followUpResp.ToolCalls) > 0 {
-			for i := range followUpResp.ToolCalls {
-				result := p.opts.ToolHandler(ctx, followUpResp.ToolCalls[i])
+		for attempt := 0; len(pendingToolCalls) > 0 && attempt < 4; attempt++ {
+			for _, tc := range pendingToolCalls {
+				result := p.opts.ToolHandler(ctx, tc)
 				if result.Refused != "" {
-					followUpResp.ToolCalls[i].Error = result.Refused
+					tc.Error = result.Refused
 				}
 				if result.Content != "" {
-					followUpResp.ToolCalls[i].Result = result.Content
+					tc.Result = result.Content
 					toolResults = append(toolResults, result.Content)
 				}
+				allToolCalls = append(allToolCalls, tc)
+				resp.ToolCalls = allToolCalls
+				followUpMessages = append(followUpMessages, map[string]any{
+					"role":         "tool",
+					"tool_call_id": tc.ID,
+					"content":      result.Content,
+				})
 			}
-			allToolCalls = append(allToolCalls, followUpResp.ToolCalls...)
-			resp.ToolCalls = allToolCalls
-		}
-		if followUpResp.Reply != "" {
-			resp.Answer = followUpResp.Reply
-		} else if len(toolResults) > 0 {
-			resp.Answer = strings.Join(toolResults, "\n")
+
+			followUpReq := map[string]any{
+				"model":    p.opts.Model,
+				"messages": followUpMessages,
+			}
+			if len(tools) > 0 {
+				// Keep the tool schema available during follow-up turns. Minimax
+				// models behind Atlas Cloud sometimes complete a multi-tool task
+				// one call at a time (plan, then service tools, then delegate).
+				followUpReq["tools"] = tools
+			}
+
+			followUpResp, followUpRawMessage, err := p.callAPI(ctx, "tool-follow-up", followUpReq)
+			if err != nil {
+				if atlascloudShouldRetryWithoutTools(err, followUpReq) {
+					delete(followUpReq, "tools")
+					followUpReq["messages"] = atlascloudFollowUpMessagesWithoutTools(p.opts.Model, followUpMessages)
+					followUpResp, followUpRawMessage, err = p.callAPI(ctx, "tool-follow-up-no-tools", followUpReq)
+				}
+				if err != nil {
+					return nil, err
+				}
+			}
+			if len(followUpResp.ToolCalls) == 0 {
+				if followUpResp.Reply != "" {
+					if strings.Contains(followUpResp.Reply, "<tool_call") || strings.Contains(followUpResp.Reply, "function=") {
+						// Preserve follow-up assistant content as Reply, not Answer, when
+						// it may contain a text-encoded tool call. The agent harness
+						// inspects Reply for text fallback calls after Generate returns.
+						resp.Reply = followUpResp.Reply
+					} else {
+						resp.Answer = atlascloudAnswerWithRequiredToolMarkers(followUpResp.Reply, toolResults, allToolCalls)
+					}
+				} else if len(toolResults) > 0 {
+					resp.Answer = strings.Join(toolResults, "\n")
+				}
+				break
+			}
+
+			followUpMessages = append(followUpMessages, map[string]any{
+				"role":       "assistant",
+				"content":    followUpRawMessage["content"],
+				"tool_calls": followUpRawMessage["tool_calls"],
+			})
+			pendingToolCalls = followUpResp.ToolCalls
 		}
 	}
 
 	return resp, nil
 }
 
+func atlascloudAnswerWithRequiredToolMarkers(answer string, toolResults []string, toolCalls []ai.ToolCall) string {
+	if strings.Contains(answer, "agent-conformance") || !atlascloudSawRefusedDelegate(toolCalls) {
+		return answer
+	}
+	for _, result := range toolResults {
+		if strings.Contains(result, "agent-conformance") {
+			return strings.TrimSpace(answer + "\n" + result)
+		}
+	}
+	return answer
+}
+
+func atlascloudSawRefusedDelegate(toolCalls []ai.ToolCall) bool {
+	for _, call := range toolCalls {
+		if call.Name == "delegate" && call.Error != "" {
+			return true
+		}
+	}
+	return false
+}
+
 // Stream generates a streaming response from Atlas Cloud's OpenAI-compatible
 // chat completions endpoint, emitting content deltas as they arrive.
 func (p *Provider) Stream(ctx context.Context, req *ai.Request, opts ...ai.GenerateOption) (ai.Stream, error) {
@@ -311,6 +381,33 @@ func (s *atlasStream) Close() error {
 	return s.body.Close()
 }
 
+type atlascloudAPIError struct {
+	Status  string
+	Code    int
+	Retry   time.Duration
+	Phase   string
+	Summary string
+	Body    string
+}
+
+func (e *atlascloudAPIError) Error() string {
+	return fmt.Sprintf("API error (%s) during atlascloud %s request (%s): %s", e.Status, e.Phase, e.Summary, e.Body)
+}
+
+func (e *atlascloudAPIError) StatusCode() int {
+	if e == nil {
+		return 0
+	}
+	return e.Code
+}
+
+func (e *atlascloudAPIError) RetryAfter() time.Duration {
+	if e == nil {
+		return 0
+	}
+	return e.Retry
+}
+
 func (p *Provider) callAPI(ctx context.Context, phase string, req map[string]any) (*ai.Response, map[string]any, error) {
 	reqBody, err := json.Marshal(req)
 	if err != nil {
@@ -334,7 +431,12 @@ func (p *Provider) callAPI(ctx context.Context, phase string, req map[string]any
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s) during atlascloud %s request (%s): %s", httpResp.Status, phase, atlascloudRequestSummary(req), string(respBody))
+		retryAfter := time.Duration(0)
+		var retryErr interface{ RetryAfter() time.Duration }
+		if errors.As(ai.NewHTTPError(httpResp, respBody), &retryErr) {
+			retryAfter = retryErr.RetryAfter()
+		}
+		return nil, nil, &atlascloudAPIError{Status: httpResp.Status, Code: httpResp.StatusCode, Retry: retryAfter, Phase: phase, Summary: atlascloudRequestSummary(req), Body: string(respBody)}
 	}
 
 	var chatResp struct {
@@ -379,6 +481,362 @@ func (p *Provider) callAPI(ctx context.Context, phase string, req map[string]any
 	return response, rawMessage, nil
 }
 
+func atlascloudFollowUpMessagesWithoutTools(model string, messages []map[string]any) []map[string]any {
+	if !atlascloudIsMinimaxModel(model) {
+		return messages
+	}
+	out := make([]map[string]any, 0, len(messages)+1)
+	for _, msg := range messages {
+		role, _ := msg["role"].(string)
+		switch role {
+		case "assistant":
+			converted := map[string]any{"role": "assistant"}
+			if content, _ := msg["content"].(string); content != "" {
+				converted["content"] = content
+			} else if calls, ok := msg["tool_calls"]; ok {
+				converted["content"] = "Tool call requested: " + atlascloudToolCallsText(calls)
+			} else {
+				converted["content"] = ""
+			}
+			out = append(out, converted)
+		case "tool":
+			toolID, _ := msg["tool_call_id"].(string)
+			content, _ := msg["content"].(string)
+			if toolID != "" {
+				content = "Tool result for " + toolID + ": " + content
+			} else {
+				content = "Tool result: " + content
+			}
+			out = append(out, map[string]any{"role": "user", "content": content})
+		default:
+			copyMsg := make(map[string]any, len(msg))
+			for k, v := range msg {
+				copyMsg[k] = v
+			}
+			out = append(out, copyMsg)
+		}
+	}
+	return out
+}
+
+func atlascloudToolCallsText(calls any) string {
+	b, err := json.Marshal(calls)
+	if err != nil {
+		return fmt.Sprint(calls)
+	}
+	return string(b)
+}
+
+func atlascloudPartialTextToolCallName(text string, tools []ai.Tool) string {
+	if !strings.Contains(text, "<tool_call") {
+		return ""
+	}
+	if strings.Contains(text, "</tool_call>") {
+		return ""
+	}
+	for _, tool := range tools {
+		for _, name := range []string{tool.Name, tool.OriginalName} {
+			if name == "" {
+				continue
+			}
+			if strings.Contains(text, `name="`+name+`"`) || strings.Contains(text, `name='`+name+`'`) {
+				return tool.Name
+			}
+		}
+	}
+	return ""
+}
+
+func atlascloudFallbackTextToolCall(toolName string, req *ai.Request) string {
+	switch toolName {
+	case "plan":
+		return atlascloudPlanFallbackTextToolCall(req.Prompt)
+	case "delegate":
+		return atlascloudDelegateFallbackTextToolCall(req)
+	default:
+		if atlascloudToolTakesNoArguments(toolName, req.Tools) {
+			return atlascloudEmptyArgumentFallbackTextToolCall(toolName)
+		}
+		return atlascloudServiceFallbackTextToolCall(toolName, req)
+	}
+}
+
+func atlascloudServiceFallbackTextToolCall(toolName string, req *ai.Request) string {
+	if req == nil {
+		return ""
+	}
+	for _, tool := range req.Tools {
+		if tool.Name != toolName {
+			continue
+		}
+		args := atlascloudFallbackArgsForProperties(tool.Properties, atlascloudRequestText(req))
+		if args == nil {
+			return ""
+		}
+		b, err := json.Marshal(args)
+		if err != nil {
+			return ""
+		}
+		return `<tool_call name="` + toolName + `">` + string(b) + `</tool_call>`
+	}
+	return ""
+}
+
+func atlascloudFallbackArgsForProperties(properties map[string]any, ctxText string) map[string]any {
+	if len(properties) == 0 {
+		return map[string]any{}
+	}
+	args := make(map[string]any, len(properties))
+	for name, schema := range properties {
+		value, ok := atlascloudFallbackArgValue(name, schema, ctxText)
+		if !ok {
+			return nil
+		}
+		args[name] = value
+	}
+	return args
+}
+
+func atlascloudFallbackArgValue(name string, schema any, ctxText string) (any, bool) {
+	typeName := "string"
+	if m, ok := schema.(map[string]any); ok {
+		if t, _ := m["type"].(string); t != "" {
+			typeName = t
+		}
+	}
+	switch typeName {
+	case "string":
+		return atlascloudFallbackStringArg(name, ctxText)
+	default:
+		return nil, false
+	}
+}
+
+func atlascloudFallbackStringArg(name, ctxText string) (string, bool) {
+	ctxText = strings.TrimSpace(ctxText)
+	if ctxText == "" {
+		return "", false
+	}
+	if strings.Contains(strings.ToLower(name), "email") || strings.Contains(strings.ToLower(name), "owner") {
+		if email := atlascloudFirstEmail(ctxText); email != "" {
+			return email, true
+		}
+	}
+	return ctxText, true
+}
+
+func atlascloudFirstEmail(text string) string {
+	for _, field := range strings.FieldsFunc(text, func(r rune) bool {
+		return strings.ContainsRune(" \t\n\r<>\"'(),;", r)
+	}) {
+		field = strings.Trim(field, ".:")
+		if strings.Contains(field, "@") && strings.Contains(field, ".") {
+			return field
+		}
+	}
+	return ""
+}
+
+func atlascloudToolTakesNoArguments(toolName string, tools []ai.Tool) bool {
+	for _, tool := range tools {
+		if tool.Name != toolName {
+			continue
+		}
+		return len(tool.Properties) == 0
+	}
+	return false
+}
+
+func atlascloudEmptyArgumentFallbackTextToolCall(toolName string) string {
+	if toolName == "" {
+		return ""
+	}
+	return `<tool_call name="` + toolName + `">{}</tool_call>`
+}
+
+func atlascloudPlanFallbackTextToolCall(prompt string) string {
+	task := strings.TrimSpace(prompt)
+	if task == "" {
+		task = "continue the requested work"
+	}
+	args, err := json.Marshal(map[string]any{
+		"steps": []map[string]string{{
+			"task":   task,
+			"status": "pending",
+		}},
+	})
+	if err != nil {
+		return `<tool_call name="plan">{"steps":[{"task":"continue the requested work","status":"pending"}]}</tool_call>`
+	}
+	return `<tool_call name="plan">` + string(args) + `</tool_call>`
+}
+
+func atlascloudDelegateFallbackTextToolCall(req *ai.Request) string {
+	ctxText := atlascloudRequestText(req)
+	task := strings.TrimSpace(req.Prompt)
+	if task == "" {
+		task = strings.TrimSpace(ctxText)
+	}
+	if task == "" {
+		task = "continue the requested delegated work"
+	}
+
+	args := map[string]any{"task": task}
+	if strings.Contains(strings.ToLower(ctxText), "comms") {
+		args["to"] = "comms"
+	}
+	b, err := json.Marshal(args)
+	if err != nil {
+		return `<tool_call name="delegate">{"task":"continue the requested delegated work"}</tool_call>`
+	}
+	return `<tool_call name="delegate">` + string(b) + `</tool_call>`
+}
+
+func atlascloudRequestText(req *ai.Request) string {
+	if req == nil {
+		return ""
+	}
+	var parts []string
+	if req.SystemPrompt != "" {
+		parts = append(parts, req.SystemPrompt)
+	}
+	for _, msg := range req.Messages {
+		switch c := msg.Content.(type) {
+		case string:
+			parts = append(parts, c)
+		default:
+			parts = append(parts, fmt.Sprint(c))
+		}
+	}
+	if req.Prompt != "" {
+		parts = append(parts, req.Prompt)
+	}
+	return strings.Join(parts, "\n")
+}
+
+func atlascloudMinimaxCompatTools(model string, input []ai.Tool) ([]map[string]any, string) {
+	if !atlascloudIsMinimaxModel(model) || len(input) == 0 {
+		return nil, ""
+	}
+	var native []ai.Tool
+	var builtins []string
+	for _, tool := range input {
+		switch tool.Name {
+		case "plan", "request_input", "delegate":
+			builtins = append(builtins, tool.Name)
+		default:
+			native = append(native, tool)
+		}
+	}
+	if len(builtins) == 0 || len(native) == len(input) {
+		return nil, ""
+	}
+	prompt := "AtlasCloud/minimax compatibility: use native tool_calls for the listed service tools. " +
+		"For built-in agent tools that are not listed natively (" + strings.Join(builtins, ", ") +
+		"), emit exactly <tool_call name=\"tool_name\">{...}</tool_call> so the agent runtime can execute them. Do not describe those built-in tool calls in prose instead of emitting the tag."
+	return atlascloudTools(native), prompt
+}
+
+func atlascloudMinimaxTextToolPrompt(model string, input []ai.Tool) string {
+	if !atlascloudIsMinimaxModel(model) || len(input) == 0 {
+		return ""
+	}
+	names := make([]string, 0, len(input))
+	for _, tool := range input {
+		if tool.Name != "" {
+			names = append(names, tool.Name)
+		}
+	}
+	if len(names) == 0 {
+		return ""
+	}
+	return "AtlasCloud/minimax text-tool compatibility: the native tools payload was rejected. " +
+		"Call exactly one needed tool from this list by emitting exactly <tool_call name=\"tool_name\">{...}</tool_call>: " +
+		strings.Join(names, ", ") + ". Do not answer in prose instead of emitting the tag."
+}
+
+func atlascloudShouldRetryMinimaxTextTools(err error, prompt string) bool {
+	if prompt == "" {
+		return false
+	}
+	var apiErr *atlascloudAPIError
+	return errors.As(err, &apiErr) && apiErr.StatusCode() == http.StatusBadRequest
+}
+
+func atlascloudIsMinimaxModel(model string) bool {
+	model = strings.ToLower(model)
+	return strings.Contains(model, "minimax")
+}
+
+func atlascloudShouldRetryMinimaxCompat(err error, compatTools []map[string]any) bool {
+	if len(compatTools) == 0 {
+		return false
+	}
+	var apiErr *atlascloudAPIError
+	return errors.As(err, &apiErr) && apiErr.StatusCode() == http.StatusBadRequest
+}
+
+func atlascloudShouldRetryWithoutTools(err error, req map[string]any) bool {
+	if _, ok := req["tools"]; !ok {
+		return false
+	}
+	var apiErr *atlascloudAPIError
+	return errors.As(err, &apiErr) && apiErr.StatusCode() == http.StatusBadRequest
+}
+
+func atlascloudTools(input []ai.Tool) []map[string]any {
+	tools := make([]map[string]any, 0, len(input))
+	for _, t := range input {
+		tools = append(tools, map[string]any{
+			"type": "function",
+			"function": map[string]any{
+				"name":        t.Name,
+				"description": t.Description,
+				"parameters": map[string]any{
+					"type":       "object",
+					"properties": normalizeAtlasCloudSchema(t.Properties),
+				},
+			},
+		})
+	}
+	return tools
+}
+
+func normalizeAtlasCloudSchema(schema map[string]any) map[string]any {
+	if schema == nil {
+		return nil
+	}
+	out := make(map[string]any, len(schema))
+	for k, v := range schema {
+		out[k] = normalizeAtlasCloudSchemaValue(v)
+	}
+	return out
+}
+
+func normalizeAtlasCloudSchemaValue(v any) any {
+	switch val := v.(type) {
+	case map[string]any:
+		out := make(map[string]any, len(val)+1)
+		for k, nested := range val {
+			out[k] = normalizeAtlasCloudSchemaValue(nested)
+		}
+		if typ, _ := out["type"].(string); typ == "array" {
+			if _, ok := out["items"]; !ok {
+				out["items"] = map[string]any{}
+			}
+		}
+		return out
+	case []any:
+		out := make([]any, len(val))
+		for i, nested := range val {
+			out[i] = normalizeAtlasCloudSchemaValue(nested)
+		}
+		return out
+	default:
+		return v
+	}
+}
+
 func normalizeAtlasCloudToolCalls(toolCalls []atlasToolCall) []map[string]any {
 	out := make([]map[string]any, 0, len(toolCalls))
 	for _, tc := range toolCalls {

ai/atlascloud/atlascloud_test.go

@@ -289,6 +289,58 @@ func TestProvider_GenerateMinimaxToolRequests(t *testing.T) {
 	}
 }
 
+func TestProvider_GenerateNormalizesBuiltInToolSchemas(t *testing.T) {
+	var body map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"ok"}}]}`))
+	}))
+	defer ts.Close()
+
+	planProperties := map[string]any{
+		"steps": map[string]any{
+			"type":        "array",
+			"description": "ordered plan steps",
+		},
+	}
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	_, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "plan and delegate",
+		Tools: []ai.Tool{
+			{Name: "task_TaskService_Add", Description: "add task", Properties: map[string]any{"title": map[string]any{"type": "string"}}},
+			{Name: "plan", Description: "record a plan", Properties: planProperties},
+			{Name: "request_input", Description: "request input", Properties: map[string]any{"prompt": map[string]any{"type": "string"}}},
+			{Name: "delegate", Description: "delegate work", Properties: map[string]any{"task": map[string]any{"type": "string"}, "to": map[string]any{"type": "string"}}},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+
+	tools := body["tools"].([]any)
+	if len(tools) != 4 {
+		t.Fatalf("tools = %d, want custom tool plus built-ins", len(tools))
+	}
+	planTool := tools[1].(map[string]any)
+	fn := planTool["function"].(map[string]any)
+	params := fn["parameters"].(map[string]any)
+	props := params["properties"].(map[string]any)
+	steps := props["steps"].(map[string]any)
+	if _, ok := steps["items"].(map[string]any); !ok {
+		t.Fatalf("plan steps schema = %#v, want array items for AtlasCloud/minimax", steps)
+	}
+	if _, mutated := planProperties["steps"].(map[string]any)["items"]; mutated {
+		t.Fatalf("Generate mutated caller tool schema: %#v", planProperties)
+	}
+}
+
 func TestProvider_GenerateExecutesFollowUpToolCall(t *testing.T) {
 	var bodies []map[string]any
 	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -303,6 +355,8 @@ func TestProvider_GenerateExecutesFollowUpToolCall(t *testing.T) {
 			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-1","function":{"name":"conformance_echo","arguments":"{\"value\":\"agent-conformance\"}"}}]}}]}`))
 		case 2:
 			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-2","function":{"name":"delegate","arguments":"{\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}"}}]}}]}`))
+		case 3:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"blocked by policy"}}]}`))
 		default:
 			t.Fatalf("unexpected API call %d", len(bodies))
 		}
@@ -349,11 +403,482 @@ func TestProvider_GenerateExecutesFollowUpToolCall(t *testing.T) {
 	if !strings.Contains(resp.Answer, "blocked by policy") {
 		t.Fatalf("Answer = %q, want follow-up tool result", resp.Answer)
 	}
+	if !strings.Contains(resp.Answer, "agent-conformance-ok") {
+		t.Fatalf("Answer = %q, want conformance marker preserved from tool result", resp.Answer)
+	}
 	if _, ok := bodies[1]["tools"].([]any); !ok {
 		t.Fatalf("follow-up request did not include tools: %#v", bodies[1])
 	}
 }
 
+func TestProvider_GenerateExecutesMultiStepFollowUpToolCalls(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-plan","function":{"name":"plan","arguments":"{\"steps\":[{\"task\":\"create tasks\"},{\"task\":\"notify owner\"}]}"}}]}}]}`))
+		case 2:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-add","function":{"name":"task_TaskService_Add","arguments":"{\"title\":\"Design\"}"}}]}}]}`))
+		case 3:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-delegate","function":{"name":"delegate","arguments":"{\"task\":\"notify owner@acme.com\",\"to\":\"comms\"}"}}]}}]}`))
+		case 4:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"done"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	var calls []string
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithToolHandler(func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+			calls = append(calls, call.Name)
+			return ai.ToolResult{ID: call.ID, Content: `{"ok":true}`}
+		}),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "plan, create tasks, and delegate notification",
+		Tools: []ai.Tool{
+			{Name: "plan", Description: "record a plan", Properties: map[string]any{"steps": map[string]any{"type": "array"}}},
+			{Name: "task_TaskService_Add", Description: "add task", Properties: map[string]any{"title": map[string]any{"type": "string"}}},
+			{Name: "delegate", Description: "delegate work", Properties: map[string]any{"task": map[string]any{"type": "string"}, "to": map[string]any{"type": "string"}}},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	wantCalls := []string{"plan", "task_TaskService_Add", "delegate"}
+	if strings.Join(calls, ",") != strings.Join(wantCalls, ",") {
+		t.Fatalf("tool calls = %v, want %v", calls, wantCalls)
+	}
+	if len(resp.ToolCalls) != 3 {
+		t.Fatalf("ToolCalls = %+v, want all multi-step calls", resp.ToolCalls)
+	}
+	if resp.Answer != "done" {
+		t.Fatalf("Answer = %q, want final follow-up reply", resp.Answer)
+	}
+	if len(bodies) != 4 {
+		t.Fatalf("requests = %d, want initial plus three follow-ups", len(bodies))
+	}
+	for i := 1; i < 4; i++ {
+		if _, ok := bodies[i]["tools"].([]any); !ok {
+			t.Fatalf("follow-up request %d did not include tools: %#v", i+1, bodies[i])
+		}
+	}
+}
+
+func TestProvider_GeneratePreservesFollowUpTextToolCallInReply(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-1","function":{"name":"conformance_echo","arguments":"{\"value\":\"agent-conformance\"}"}}]}}]}`))
+		case 2:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"delegate\">{\"task\":\"summarize the conformance marker\",\"to\":\"blocked-reviewer\"}</tool_call>"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithToolHandler(func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+			if call.Name != "conformance_echo" {
+				t.Fatalf("unexpected structured tool call %+v", call)
+			}
+			return ai.ToolResult{ID: call.ID, Content: `{"marker":"agent-conformance-ok"}`}
+		}),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "run conformance",
+		Tools: []ai.Tool{
+			{Name: "conformance_echo", Description: "echo conformance marker", Properties: map[string]any{"value": map[string]any{"type": "string"}}},
+			{Name: "delegate", Description: "delegate work", Properties: map[string]any{"task": map[string]any{"type": "string"}, "to": map[string]any{"type": "string"}}},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if !strings.Contains(resp.Reply, `<tool_call name="delegate">`) {
+		t.Fatalf("Reply = %q, want tagged delegate follow-up for agent text fallback", resp.Reply)
+	}
+	if resp.Answer != "" {
+		t.Fatalf("Answer = %q, want follow-up text preserved only as Reply", resp.Answer)
+	}
+}
+
+func TestProvider_GenerateRepairsInitialPartialTextToolCall(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"plan\">"}}]}`))
+		case 2:
+			messages := body["messages"].([]any)
+			last := messages[len(messages)-1].(map[string]any)
+			if last["role"] != "user" || !strings.Contains(last["content"].(string), "did not finish valid tool-call markup") {
+				t.Fatalf("repair prompt = %#v, want partial tool-call guidance", last)
+			}
+			if _, ok := body["tools"]; !ok {
+				t.Fatalf("repair request did not keep tools available: %#v", body)
+			}
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"plan\">{\"steps\":[{\"task\":\"create tasks\"}]}</tool_call>"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "plan and delegate",
+		Tools: []ai.Tool{
+			{Name: "plan", Description: "record a plan", Properties: map[string]any{"steps": map[string]any{"type": "array"}}},
+			{Name: "delegate", Description: "delegate work", Properties: map[string]any{"task": map[string]any{"type": "string"}}},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if !strings.Contains(resp.Reply, `<tool_call name="plan">`) || !strings.Contains(resp.Reply, `</tool_call>`) {
+		t.Fatalf("Reply = %q, want completed text tool call", resp.Reply)
+	}
+	if len(bodies) != 2 {
+		t.Fatalf("requests = %d, want initial plus repair", len(bodies))
+	}
+}
+
+func TestProvider_GenerateFallsBackAfterRepeatedPartialPlanTextToolCall(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"plan\">"}}]}`))
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "plan and delegate",
+		Tools:  []ai.Tool{{Name: "plan", Description: "record a plan"}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if !strings.Contains(resp.Reply, `<tool_call name="plan">`) || !strings.Contains(resp.Reply, `</tool_call>`) {
+		t.Fatalf("Reply = %q, want completed fallback plan text tool call", resp.Reply)
+	}
+	if !strings.Contains(resp.Reply, "plan and delegate") {
+		t.Fatalf("Reply = %q, want fallback plan seeded from prompt", resp.Reply)
+	}
+}
+
+func TestProvider_GenerateFallsBackAfterRepeatedPartialDelegateTextToolCall(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"delegate\">"}}]}`))
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		SystemPrompt: "You coordinate launch work and delegate readiness notifications to the comms agent.",
+		Prompt:       "delegate the owner readiness notification to comms",
+		Tools:        []ai.Tool{{Name: "delegate", Description: "delegate work"}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	for _, want := range []string{`<tool_call name="delegate">`, `"task":"delegate the owner readiness notification to comms"`, `"to":"comms"`, `</tool_call>`} {
+		if !strings.Contains(resp.Reply, want) {
+			t.Fatalf("Reply = %q, want delegate fallback containing %q", resp.Reply, want)
+		}
+	}
+}
+
+func TestProvider_GenerateFallsBackAfterRepeatedPartialNoArgumentServiceTextToolCall(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"task_TaskService_List\">"}}]}`))
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "list the current launch-readiness tasks",
+		Tools: []ai.Tool{{
+			Name:         "task_TaskService_List",
+			OriginalName: "task.TaskService.List",
+			Description:  "List persisted launch-readiness tasks",
+			Properties:   map[string]any{},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	want := `<tool_call name="task_TaskService_List">{}</tool_call>`
+	if resp.Reply != want {
+		t.Fatalf("Reply = %q, want %q", resp.Reply, want)
+	}
+}
+
+func TestProvider_GenerateFallsBackAfterRepeatedPartialWorkspaceServiceTextToolCall(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"workspace_WorkspaceService_Create\">"}}]}`))
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		SystemPrompt: "Create an onboarding workspace only if it is still needed.",
+		Prompt:       "Onboard alice@acme.com. The workspace create side effect may already be complete; avoid failing the flow on a duplicate repaired call.",
+		Tools: []ai.Tool{{
+			Name:         "workspace_WorkspaceService_Create",
+			OriginalName: "workspace.WorkspaceService.Create",
+			Description:  "Create an onboarding workspace",
+			Properties:   map[string]any{"owner": map[string]any{"type": "string"}},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	want := `<tool_call name="workspace_WorkspaceService_Create">{"owner":"alice@acme.com"}</tool_call>`
+	if resp.Reply != want {
+		t.Fatalf("Reply = %q, want %q", resp.Reply, want)
+	}
+	if len(bodies) != 2 {
+		t.Fatalf("requests = %d, want initial plus repair", len(bodies))
+	}
+}
+
+func TestProvider_GenerateRetriesMinimaxBuiltInsAsTextTools(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			http.Error(w, `{"code":400,"msg":"bad request"}`, http.StatusBadRequest)
+		case 2:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"delegate\">{\"task\":\"summarize\",\"to\":\"blocked-reviewer\"}</tool_call>"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	p := NewProvider(ai.WithAPIKey("test-key"), ai.WithBaseURL(ts.URL), ai.WithModel("minimaxai/minimax-m3"))
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "plan and delegate",
+		Tools: []ai.Tool{
+			{Name: "task_TaskService_Add", Description: "add task", Properties: map[string]any{"title": map[string]any{"type": "string"}}},
+			{Name: "plan", Description: "record a plan", Properties: map[string]any{"steps": map[string]any{"type": "array"}}},
+			{Name: "request_input", Description: "request input", Properties: map[string]any{"prompt": map[string]any{"type": "string"}}},
+			{Name: "delegate", Description: "delegate work", Properties: map[string]any{"task": map[string]any{"type": "string"}, "to": map[string]any{"type": "string"}}},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if !strings.Contains(resp.Reply, `<tool_call name="delegate">`) {
+		t.Fatalf("Reply = %q, want text delegate fallback", resp.Reply)
+	}
+	if len(bodies) != 2 {
+		t.Fatalf("requests = %d, want initial plus compat retry", len(bodies))
+	}
+	initialTools := bodies[0]["tools"].([]any)
+	if len(initialTools) != 4 {
+		t.Fatalf("initial tools = %d, want all tools", len(initialTools))
+	}
+	retryTools := bodies[1]["tools"].([]any)
+	if len(retryTools) != 1 {
+		t.Fatalf("retry tools = %d, want only service tools", len(retryTools))
+	}
+	fn := retryTools[0].(map[string]any)["function"].(map[string]any)
+	if fn["name"] != "task_TaskService_Add" {
+		t.Fatalf("retry tool name = %v, want service tool only", fn["name"])
+	}
+	msgs := bodies[1]["messages"].([]any)
+	compat := msgs[len(msgs)-1].(map[string]any)
+	if compat["role"] != "system" || !strings.Contains(compat["content"].(string), `<tool_call name="tool_name">`) {
+		t.Fatalf("compat instruction = %#v", compat)
+	}
+}
+
+func TestProvider_GenerateRetriesMinimaxServiceToolsAsTextTools(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			http.Error(w, `{"code":400,"msg":"bad request"}`, http.StatusBadRequest)
+		case 2:
+			if _, ok := body["tools"]; ok {
+				t.Fatalf("text-tool retry included native tools: %#v", body["tools"])
+			}
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"conformance_echo\">{\"value\":\"agent-conformance\"}</tool_call>"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	p := NewProvider(ai.WithAPIKey("test-key"), ai.WithBaseURL(ts.URL), ai.WithModel("minimaxai/minimax-m3"))
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "call a tool",
+		Tools: []ai.Tool{{
+			Name:        "conformance_echo",
+			Description: "echo conformance marker",
+			Properties:  map[string]any{"value": map[string]any{"type": "string"}},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if !strings.Contains(resp.Reply, `<tool_call name="conformance_echo">`) {
+		t.Fatalf("Reply = %q, want text service-tool fallback", resp.Reply)
+	}
+	if len(bodies) != 2 {
+		t.Fatalf("requests = %d, want initial plus text-tool retry", len(bodies))
+	}
+	if _, ok := bodies[0]["tools"].([]any); !ok {
+		t.Fatalf("initial request did not include native tools: %#v", bodies[0])
+	}
+	msgs := bodies[1]["messages"].([]any)
+	compat := msgs[len(msgs)-1].(map[string]any)
+	content := compat["content"].(string)
+	for _, want := range []string{"native tools payload was rejected", `<tool_call name="tool_name">`, "conformance_echo"} {
+		if !strings.Contains(content, want) {
+			t.Fatalf("text-tool instruction %q missing %q", content, want)
+		}
+	}
+}
+
+func TestProvider_GenerateFollowUpRetriesWithoutToolsOnBadRequest(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		switch len(bodies) {
+		case 1:
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"","tool_calls":[{"id":"call-1","function":{"name":"conformance_echo","arguments":"{\"value\":\"agent-conformance\"}"}}]}}]}`))
+		case 2:
+			http.Error(w, `{"code":400,"msg":"bad request"}`, http.StatusBadRequest)
+		case 3:
+			if _, ok := body["tools"]; ok {
+				t.Fatalf("no-tools retry still included tools: %#v", body["tools"])
+			}
+			messages := body["messages"].([]any)
+			last := messages[len(messages)-1].(map[string]any)
+			if last["role"] == "tool" {
+				http.Error(w, `{"code":400,"msg":"trailing tool message rejected"}`, http.StatusBadRequest)
+				return
+			}
+			if last["role"] != "user" || !strings.Contains(last["content"].(string), "Tool result for call-1") {
+				t.Fatalf("no-tools retry last message = %#v, want user-visible tool result", last)
+			}
+			assistant := messages[len(messages)-2].(map[string]any)
+			if _, ok := assistant["tool_calls"]; ok {
+				t.Fatalf("no-tools retry assistant still included tool_calls: %#v", assistant)
+			}
+			_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"done"}}]}`))
+		default:
+			t.Fatalf("unexpected API call %d", len(bodies))
+		}
+	}))
+	defer ts.Close()
+
+	var toolCalls int
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+		ai.WithToolHandler(func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+			toolCalls++
+			return ai.ToolResult{ID: call.ID, Content: `{"marker":"agent-conformance-ok"}`}
+		}),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		Prompt: "call a tool",
+		Tools:  []ai.Tool{{Name: "conformance_echo", Description: "echo", Properties: map[string]any{"value": map[string]any{"type": "string"}}}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	if resp.Answer != "done" {
+		t.Fatalf("Answer = %q, want done", resp.Answer)
+	}
+	if toolCalls != 1 {
+		t.Fatalf("tool handler calls = %d, want one (no duplicate side effect)", toolCalls)
+	}
+	if len(bodies) != 3 {
+		t.Fatalf("requests = %d, want chat, failed follow-up, no-tools follow-up", len(bodies))
+	}
+	if _, ok := bodies[1]["tools"]; !ok {
+		t.Fatalf("first follow-up did not include tools")
+	}
+}
+
 func TestProvider_GenerateToolCallHTTPErrorIncludesRequestContext(t *testing.T) {
 	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		http.Error(w, `{"code":400,"msg":"bad request"}`, http.StatusBadRequest)
@@ -363,7 +888,7 @@ func TestProvider_GenerateToolCallHTTPErrorIncludesRequestContext(t *testing.T)
 	p := NewProvider(
 		ai.WithAPIKey("test-key"),
 		ai.WithBaseURL(ts.URL),
-		ai.WithModel("minimaxai/minimax-m3"),
+		ai.WithModel("deepseek-ai/DeepSeek-V3-0324"),
 	)
 	_, err := p.Generate(context.Background(), &ai.Request{
 		Prompt: "call a tool",
@@ -377,7 +902,7 @@ func TestProvider_GenerateToolCallHTTPErrorIncludesRequestContext(t *testing.T)
 		t.Fatal("Generate error = nil, want 400")
 	}
 	msg := err.Error()
-	for _, want := range []string{"400 Bad Request", "atlascloud chat request", "model=minimaxai/minimax-m3", "tools=1", "tool_names=conformance_echo"} {
+	for _, want := range []string{"400 Bad Request", "atlascloud chat request", "model=deepseek-ai/DeepSeek-V3-0324", "tools=1", "tool_names=conformance_echo"} {
 		if !strings.Contains(msg, want) {
 			t.Fatalf("error %q missing %q", msg, want)
 		}

ai/capabilities.go

@@ -23,6 +23,10 @@ type Capabilities struct {
 	// Providers that only satisfy the Model interface with ErrStreamingUnsupported
 	// leave this false until their Stream implementation is usable.
 	Stream bool `json:"stream"`
+	// ToolStream reports whether the provider supports agent Stream requests that
+	// include tool schemas. Providers may support plain token streaming while
+	// leaving this false when their streaming API cannot accept tools.
+	ToolStream bool `json:"tool_stream"`
 }
 
 // ProviderCapabilities reports the capabilities registered for provider.
@@ -31,12 +35,14 @@ func ProviderCapabilities(provider string) Capabilities {
 	_, hasImage := imageProviders[provider]
 	_, hasVideo := videoProviders[provider]
 	_, hasStream := streamProviders[provider]
+	_, hasToolStream := toolStreamProviders[provider]
 
 	return Capabilities{
-		Model:  hasModel,
-		Image:  hasImage,
-		Video:  hasVideo,
-		Stream: hasStream,
+		Model:      hasModel,
+		Image:      hasImage,
+		Video:      hasVideo,
+		Stream:     hasStream,
+		ToolStream: hasToolStream,
 	}
 }
 
@@ -58,6 +64,9 @@ func CapabilityMatrix() map[string]Capabilities {
 	for name := range streamProviders {
 		names[name] = struct{}{}
 	}
+	for name := range toolStreamProviders {
+		names[name] = struct{}{}
+	}
 
 	matrix := make(map[string]Capabilities, len(names))
 	for name := range names {
@@ -88,10 +97,18 @@ func RegisterStream(provider string) {
 	streamProviders[provider] = struct{}{}
 }
 
+// RegisterToolStream records that provider can accept tool schemas in Stream
+// requests. This is intentionally separate from RegisterStream because some
+// providers can stream tokens but cannot expose tools while streaming.
+func RegisterToolStream(provider string) {
+	toolStreamProviders[provider] = struct{}{}
+}
+
 var streamProviders = make(map[string]struct{})
+var toolStreamProviders = make(map[string]struct{})
 
 // RegisteredProviders returns the registered provider names in sorted order.
-// kind may be "model", "image", "video", "stream", or empty for the union of all
+// kind may be "model", "image", "video", "stream", "tool_stream", or empty for the union of all
 // provider registries.
 func RegisteredProviders(kind string) []string {
 	names := map[string]struct{}{}
@@ -121,6 +138,8 @@ func RegisteredProviders(kind string) []string {
 		add(providers)
 	case "stream":
 		add(streamProviders)
+	case "tool_stream":
+		add(toolStreamProviders)
 	case "image":
 		add(imageProviders)
 	case "video":

ai/capabilities_test.go

@@ -44,14 +44,14 @@ func TestRegisteredProviders(t *testing.T) {
 func TestCapabilityRows(t *testing.T) {
 	got := ai.CapabilityRows()
 	want := []ai.CapabilityRow{
-		{Provider: "anthropic", Capabilities: ai.Capabilities{Model: true, Stream: true}},
+		{Provider: "anthropic", Capabilities: ai.Capabilities{Model: true, Stream: true, ToolStream: true}},
 		{Provider: "atlascloud", Capabilities: ai.Capabilities{Model: true, Image: true, Video: true, Stream: true}},
 		{Provider: "gemini", Capabilities: ai.Capabilities{Model: true}},
-		{Provider: "groq", Capabilities: ai.Capabilities{Model: true, Stream: true}},
-		{Provider: "minimax", Capabilities: ai.Capabilities{Model: true, Stream: true}},
-		{Provider: "mistral", Capabilities: ai.Capabilities{Model: true, Stream: true}},
-		{Provider: "openai", Capabilities: ai.Capabilities{Model: true, Image: true, Stream: true}},
-		{Provider: "together", Capabilities: ai.Capabilities{Model: true, Stream: true}},
+		{Provider: "groq", Capabilities: ai.Capabilities{Model: true, Stream: true, ToolStream: true}},
+		{Provider: "minimax", Capabilities: ai.Capabilities{Model: true, Stream: true, ToolStream: true}},
+		{Provider: "mistral", Capabilities: ai.Capabilities{Model: true, Stream: true, ToolStream: true}},
+		{Provider: "openai", Capabilities: ai.Capabilities{Model: true, Image: true, Stream: true, ToolStream: true}},
+		{Provider: "together", Capabilities: ai.Capabilities{Model: true, Stream: true, ToolStream: true}},
 	}
 	if !reflect.DeepEqual(got, want) {
 		t.Fatalf("CapabilityRows() = %#v, want %#v", got, want)
@@ -71,7 +71,7 @@ func TestCapabilityMatrix(t *testing.T) {
 		}
 	}
 
-	if caps := ai.ProviderCapabilities("openai"); caps != (ai.Capabilities{Model: true, Image: true, Stream: true}) {
+	if caps := ai.ProviderCapabilities("openai"); caps != (ai.Capabilities{Model: true, Image: true, Stream: true, ToolStream: true}) {
 		t.Fatalf("ProviderCapabilities(openai) = %#v", caps)
 	}
 	if caps := ai.ProviderCapabilities("atlascloud"); caps != (ai.Capabilities{Model: true, Image: true, Video: true, Stream: true}) {
@@ -95,3 +95,17 @@ func TestRegisterStream(t *testing.T) {
 		t.Fatalf("RegisteredProviders(stream) = %#v, want %#v", got, want)
 	}
 }
+
+func TestRegisterToolStream(t *testing.T) {
+	ai.RegisterToolStream("test-tool-stream")
+
+	if caps := ai.ProviderCapabilities("test-tool-stream"); caps != (ai.Capabilities{ToolStream: true}) {
+		t.Fatalf("ProviderCapabilities(test-tool-stream) = %#v", caps)
+	}
+
+	got := ai.RegisteredProviders("tool_stream")
+	want := []string{"anthropic", "groq", "minimax", "mistral", "openai", "test-tool-stream", "together"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("RegisteredProviders(tool_stream) = %#v, want %#v", got, want)
+	}
+}

ai/flow/compat.go

@@ -1,22 +0,0 @@
-// Package flow is maintained for backward compatibility.
-// The canonical import is go-micro.dev/v6/flow.
-package flow
-
-import "go-micro.dev/v6/flow"
-
-// Re-export types for backward compatibility.
-type Flow = flow.Flow
-type Options = flow.Options
-type Option = flow.Option
-type Result = flow.Result
-
-var New = flow.New
-var Trigger = flow.Trigger
-var Prompt = flow.Prompt
-var SystemPrompt = flow.SystemPrompt
-var Provider = flow.Provider
-var APIKey = flow.APIKey
-var Model = flow.Model
-var BaseURL = flow.BaseURL
-var HistoryLimit = flow.HistoryLimit
-var OnResult = flow.OnResult

ai/gemini/gemini.go

@@ -163,7 +163,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	var geminiResp struct {

ai/groq/groq.go

@@ -30,6 +30,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("groq")
+	ai.RegisterToolStream("groq")
 }
 
 type Provider struct {
@@ -147,7 +148,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	var chatResp struct {

ai/minimax/minimax.go

@@ -30,6 +30,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("minimax")
+	ai.RegisterToolStream("minimax")
 }
 
 type Provider struct {
@@ -147,7 +148,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	var chatResp struct {

ai/mistral/mistral.go

@@ -30,6 +30,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("mistral")
+	ai.RegisterToolStream("mistral")
 }
 
 type Provider struct {
@@ -147,7 +148,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	var chatResp struct {

ai/ollama/ollama.go

@@ -45,6 +45,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("ollama")
+	ai.RegisterToolStream("ollama")
 }
 
 // Provider implements the ai.Model interface for Ollama.

ai/openai/openai.go

@@ -22,6 +22,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("openai")
+	ai.RegisterToolStream("openai")
 }
 
 // Provider implements the ai.Model interface for OpenAI
@@ -285,7 +286,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 	// Read response
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	// Parse response

ai/retry.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"net/http"
+	"strconv"
 	"strings"
 	"time"
 )
@@ -19,6 +21,64 @@ type RetryAfterCoder interface {
 	RetryAfter() time.Duration
 }
 
+// HTTPError describes a failed provider HTTP response while preserving the
+// status code and Retry-After signal for retry classifiers.
+type HTTPError struct {
+	Status string
+	Code   int
+	Body   string
+	Header http.Header
+}
+
+func (e *HTTPError) Error() string {
+	if e == nil {
+		return ""
+	}
+	return fmt.Sprintf("API error (%s): %s", e.Status, e.Body)
+}
+
+func (e *HTTPError) StatusCode() int {
+	if e == nil {
+		return 0
+	}
+	return e.Code
+}
+
+func (e *HTTPError) RetryAfter() time.Duration {
+	if e == nil {
+		return 0
+	}
+	return parseRetryAfter(e.Header.Get("Retry-After"), time.Now())
+}
+
+func NewHTTPError(resp *http.Response, body []byte) error {
+	if resp == nil {
+		return errors.New("API error: nil response")
+	}
+	return &HTTPError{Status: resp.Status, Code: resp.StatusCode, Body: string(body), Header: resp.Header.Clone()}
+}
+
+func parseRetryAfter(value string, now time.Time) time.Duration {
+	value = strings.TrimSpace(value)
+	if value == "" {
+		return 0
+	}
+	if seconds, err := strconv.Atoi(value); err == nil {
+		if seconds <= 0 {
+			return 0
+		}
+		return time.Duration(seconds) * time.Second
+	}
+	when, err := http.ParseTime(value)
+	if err != nil {
+		return 0
+	}
+	if delay := when.Sub(now); delay > 0 {
+		return delay
+	}
+	return 0
+}
+
 // ErrorKind classifies provider-boundary failures into stable buckets callers
 // can inspect without parsing provider-specific error strings.
 type ErrorKind string
@@ -97,7 +157,7 @@ func GenerateWithRetry(ctx context.Context, m Model, req *Request, policy Genera
 			info.MaxAttempts = policy.MaxAttempts
 			callCtx = WithRunInfo(callCtx, info)
 		}
-		resp, err := m.Generate(callCtx, req, opts...)
+		resp, err := generateAttempt(callCtx, m, req, opts...)
 		cancel()
 
 		// Caller cancellation/deadline always wins and is not retried, even if
@@ -137,6 +197,27 @@ func GenerateWithRetry(ctx context.Context, m Model, req *Request, policy Genera
 	return nil, &RetryError{Attempts: policy.MaxAttempts, Kind: ClassifyError(last), Err: last}
 }
 
+func generateAttempt(ctx context.Context, m Model, req *Request, opts ...GenerateOption) (*Response, error) {
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	type result struct {
+		resp *Response
+		err  error
+	}
+	done := make(chan result, 1)
+	go func() {
+		resp, err := m.Generate(ctx, req, opts...)
+		done <- result{resp: resp, err: err}
+	}()
+	select {
+	case res := <-done:
+		return res.resp, res.err
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	}
+}
+
 func retryBackoff(err error, attempt int, base time.Duration) time.Duration {
 	backoff := base
 	if backoff <= 0 {

ai/retry_test.go

@@ -3,6 +3,8 @@ package ai
 import (
 	"context"
 	"errors"
+	"net/http"
+	"sync/atomic"
 	"testing"
 	"time"
 )
@@ -67,10 +69,54 @@ func TestGenerateWithRetryDoesNotRetryCallerCancellation(t *testing.T) {
 	}
 }
 
-func TestGenerateWithRetryHonorsPerAttemptTimeout(t *testing.T) {
+func TestGenerateWithRetryCancellationDuringBackoffStopsRetry(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
 	attempts := 0
-	model := retryModel{generate: func(ctx context.Context, _ *Request, _ ...GenerateOption) (*Response, error) {
+	firstAttemptDone := make(chan struct{})
+	model := retryModel{generate: func(context.Context, *Request, ...GenerateOption) (*Response, error) {
 		attempts++
+		if attempts == 1 {
+			close(firstAttemptDone)
+			return nil, retryAfterErr{delay: time.Hour}
+		}
+		return &Response{Reply: "unexpected retry"}, nil
+	}}
+
+	errc := make(chan error, 1)
+	go func() {
+		_, err := GenerateWithRetry(ctx, model, &Request{Prompt: "hi"}, GeneratePolicy{
+			MaxAttempts: 3,
+			Backoff:     time.Hour,
+		})
+		errc <- err
+	}()
+
+	select {
+	case <-firstAttemptDone:
+	case <-time.After(time.Second):
+		t.Fatal("first provider attempt did not run")
+	}
+	cancel()
+
+	select {
+	case err := <-errc:
+		if !errors.Is(err, context.Canceled) {
+			t.Fatalf("error = %v, want context.Canceled", err)
+		}
+	case <-time.After(time.Second):
+		t.Fatal("GenerateWithRetry did not stop after cancellation during backoff")
+	}
+	if attempts != 1 {
+		t.Fatalf("attempts = %d, want cancellation to prevent retry", attempts)
+	}
+}
+
+func TestGenerateWithRetryHonorsPerAttemptTimeout(t *testing.T) {
+	var attempts atomic.Int32
+	model := retryModel{generate: func(ctx context.Context, _ *Request, _ ...GenerateOption) (*Response, error) {
+		attempts.Add(1)
 		<-ctx.Done()
 		return nil, ctx.Err()
 	}}
@@ -90,8 +136,8 @@ func TestGenerateWithRetryHonorsPerAttemptTimeout(t *testing.T) {
 	if !errors.Is(err, context.DeadlineExceeded) {
 		t.Fatalf("error = %v, want context.DeadlineExceeded", err)
 	}
-	if attempts != 2 {
-		t.Fatalf("attempts = %d, want 2", attempts)
+	if got := attempts.Load(); got != 2 {
+		t.Fatalf("attempts = %d, want 2", got)
 	}
 }
 
@@ -134,6 +180,34 @@ func TestGenerateWithRetryAddsAttemptMetadataToRunInfo(t *testing.T) {
 	}
 }
 
+func TestGenerateWithRetryReturnsWhenProviderIgnoresTimeout(t *testing.T) {
+	started := make(chan struct{})
+	release := make(chan struct{})
+	model := retryModel{generate: func(ctx context.Context, req *Request, opts ...GenerateOption) (*Response, error) {
+		close(started)
+		<-release
+		return &Response{Reply: "late"}, nil
+	}}
+	defer close(release)
+
+	start := time.Now()
+	_, err := GenerateWithRetry(context.Background(), model, &Request{Prompt: "hi"}, GeneratePolicy{
+		Timeout:     10 * time.Millisecond,
+		MaxAttempts: 1,
+	})
+	if !errors.Is(err, context.DeadlineExceeded) {
+		t.Fatalf("GenerateWithRetry error = %v, want deadline exceeded", err)
+	}
+	if elapsed := time.Since(start); elapsed > 200*time.Millisecond {
+		t.Fatalf("GenerateWithRetry took %s after deadline, want prompt return", elapsed)
+	}
+	select {
+	case <-started:
+	default:
+		t.Fatal("provider was not called")
+	}
+}
+
 type statusErr int
 
 func (e statusErr) Error() string   { return "provider status" }
@@ -221,3 +295,131 @@ func TestGenerateWithRetryCapsRetryAfter(t *testing.T) {
 		t.Fatalf("retryBackoff() = %s, want 30s cap", got)
 	}
 }
+
+func TestGenerateWithRetryDoesNotRetryPermanentProviderErrors(t *testing.T) {
+	attempts := 0
+	model := retryModel{generate: func(context.Context, *Request, ...GenerateOption) (*Response, error) {
+		attempts++
+		return nil, statusErr(400)
+	}}
+
+	_, err := GenerateWithRetry(context.Background(), model, &Request{Prompt: "hi"}, GeneratePolicy{
+		MaxAttempts: 3,
+		Backoff:     time.Millisecond,
+	})
+	if !errors.Is(err, statusErr(400)) {
+		t.Fatalf("error = %v, want original provider status", err)
+	}
+	var retryErr *RetryError
+	if errors.As(err, &retryErr) {
+		t.Fatalf("error = %T %[1]v, want permanent provider error without retry wrapper", err)
+	}
+	if attempts != 1 {
+		t.Fatalf("attempts = %d, want no retry for permanent provider errors", attempts)
+	}
+}
+
+func TestGenerateWithRetryDefaultsToSingleAttempt(t *testing.T) {
+	attempts := 0
+	model := retryModel{generate: func(context.Context, *Request, ...GenerateOption) (*Response, error) {
+		attempts++
+		return nil, errors.New("temporary provider outage")
+	}}
+
+	_, err := GenerateWithRetry(context.Background(), model, &Request{Prompt: "hi"}, GeneratePolicy{
+		Backoff: time.Millisecond,
+	})
+	var retryErr *RetryError
+	if !errors.As(err, &retryErr) {
+		t.Fatalf("error = %T %[1]v, want retry error for exhausted transient attempt", err)
+	}
+	if retryErr.Attempts != 1 {
+		t.Fatalf("retry attempts = %d, want default single attempt", retryErr.Attempts)
+	}
+	if attempts != 1 {
+		t.Fatalf("model attempts = %d, want default single attempt", attempts)
+	}
+}
+
+func TestGenerateWithRetryStopsDuringBackoffWhenCallerCancels(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	var attempts atomic.Int32
+	model := retryModel{generate: func(context.Context, *Request, ...GenerateOption) (*Response, error) {
+		attempts.Add(1)
+		return nil, statusErr(503)
+	}}
+
+	errc := make(chan error, 1)
+	go func() {
+		_, err := GenerateWithRetry(ctx, model, &Request{Prompt: "hi"}, GeneratePolicy{
+			MaxAttempts: 3,
+			Backoff:     time.Hour,
+		})
+		errc <- err
+	}()
+
+	deadline := time.After(time.Second)
+	for attempts.Load() == 0 {
+		select {
+		case err := <-errc:
+			t.Fatalf("GenerateWithRetry returned before first attempt cancellation: %v", err)
+		case <-deadline:
+			t.Fatal("provider was not called")
+		default:
+			time.Sleep(time.Millisecond)
+		}
+	}
+
+	start := time.Now()
+	cancel()
+	select {
+	case err := <-errc:
+		if !errors.Is(err, context.Canceled) {
+			t.Fatalf("error = %v, want context.Canceled", err)
+		}
+	case <-time.After(200 * time.Millisecond):
+		t.Fatal("GenerateWithRetry did not stop promptly during backoff cancellation")
+	}
+	if elapsed := time.Since(start); elapsed > 200*time.Millisecond {
+		t.Fatalf("backoff cancellation took %s, want prompt return", elapsed)
+	}
+	if got := attempts.Load(); got != 1 {
+		t.Fatalf("attempts = %d, want cancellation before retry", got)
+	}
+}
+
+func TestRetryBackoffUsesExponentialBaseAndCap(t *testing.T) {
+	if got := retryBackoff(statusErr(503), 1, 10*time.Millisecond); got != 10*time.Millisecond {
+		t.Fatalf("attempt 1 backoff = %s, want 10ms", got)
+	}
+	if got := retryBackoff(statusErr(503), 2, 10*time.Millisecond); got != 20*time.Millisecond {
+		t.Fatalf("attempt 2 backoff = %s, want 20ms", got)
+	}
+	if got := retryBackoff(statusErr(503), 3, 10*time.Millisecond); got != 40*time.Millisecond {
+		t.Fatalf("attempt 3 backoff = %s, want 40ms", got)
+	}
+	if got := retryBackoff(statusErr(503), 20, time.Second); got != 30*time.Second {
+		t.Fatalf("large backoff = %s, want 30s cap", got)
+	}
+}
+
+func TestHTTPErrorExposesStatusAndRetryAfter(t *testing.T) {
+	resp := &http.Response{
+		Status:     "429 Too Many Requests",
+		StatusCode: http.StatusTooManyRequests,
+		Header:     http.Header{"Retry-After": []string{"2"}},
+	}
+	err := NewHTTPError(resp, []byte("slow down"))
+
+	if got := ClassifyError(err); got != ErrorKindRateLimited {
+		t.Fatalf("ClassifyError() = %q, want %q", got, ErrorKindRateLimited)
+	}
+	var retryAfter RetryAfterCoder
+	if !errors.As(err, &retryAfter) {
+		t.Fatalf("NewHTTPError does not expose RetryAfterCoder")
+	}
+	if got := retryAfter.RetryAfter(); got != 2*time.Second {
+		t.Fatalf("RetryAfter() = %s, want 2s", got)
+	}
+}

ai/together/together.go

@@ -30,6 +30,7 @@ func init() {
 		return NewProvider(opts...)
 	})
 	ai.RegisterStream("together")
+	ai.RegisterToolStream("together")
 }
 
 type Provider struct {
@@ -147,7 +148,7 @@ func (p *Provider) callAPI(ctx context.Context, req map[string]any) (*ai.Respons
 
 	respBody, _ := io.ReadAll(httpResp.Body)
 	if httpResp.StatusCode != http.StatusOK {
-		return nil, nil, fmt.Errorf("API error (%s): %s", httpResp.Status, string(respBody))
+		return nil, nil, ai.NewHTTPError(httpResp, respBody)
 	}
 
 	var chatResp struct {

cmd/micro/README.md

@@ -62,14 +62,17 @@ curl -X POST http://localhost:8080/api/helloworld/Helloworld.Call \
 ## First agent on-ramp
 
 Once the scaffold → run → call path works, ask the installed CLI for the
-provider-free agent path:
+provider-free agent path. The focused no-secret docs/CLI contract is
+`make docs-wayfinding`:
 
 ```
 micro agent demo
+micro examples
+micro zero-to-hero
 ```
 
-That points at the smallest mock-model first-agent example and the no-secret
-transcript before you add provider-backed chat.
+Those commands point at the smallest mock-model first-agent example, the no-secret
+transcript, and the 0→hero support app before you add provider-backed chat.
 
 ### Output
 
@@ -682,7 +685,7 @@ micro loop init \
 ```
 
 - `--roles`: which roles to scaffold (`planner,builder,triage`, or `all`)
-- `--agent`: how the workflows summon the agent (an `@mention`)
+- `--agent`: how the workflows summon the agent — any `@mention`-driven coding agent (e.g. `@codex`, `@claude`)
 - `--token-secret`: repo secret holding the driving user PAT
 - `--branch`: base branch for the loop's PRs
 - `--ci-workflow`: `name:` of the CI workflow triage watches

cmd/micro/chat/chat.go

@@ -74,7 +74,9 @@ a new service automatically and start using it.
 
 Examples:
   ANTHROPIC_API_KEY=sk-ant-... micro chat --provider anthropic
-  micro chat --provider openai --prompt "list all users"`,
+  micro chat --provider openai --prompt "list all users"
+  micro chat assistant --prompt "create a task"`,
+		ArgsUsage: "[agent]",
 		Flags: []cli.Flag{
 			&cli.StringFlag{Name: "provider", Usage: "AI provider (anthropic, openai, gemini, groq, mistral, together, atlascloud)", EnvVars: []string{"MICRO_AI_PROVIDER"}},
 			&cli.StringFlag{Name: "api_key", Usage: "API key for the provider", EnvVars: []string{"MICRO_AI_API_KEY"}},
@@ -316,6 +318,7 @@ func run(c *cli.Context) error {
 	baseURL := c.String("base_url")
 	singlePrompt := c.String("prompt")
 	streamOutput := c.Bool("stream")
+	targetAgent := c.Args().First()
 
 	if provider == "" {
 		provider = ai.AutoDetectProvider(baseURL)
@@ -323,15 +326,36 @@ func run(c *cli.Context) error {
 	if apiKey == "" {
 		apiKey = fallbackAPIKey(provider)
 	}
-	if apiKey == "" {
-		return fmt.Errorf("no API key configured; set --api_key or %s", envVarForProvider(provider))
-	}
 
 	reg := registry.DefaultRegistry
 	cl := clt.DefaultClient
 
 	tools := ai.NewTools(reg, ai.ToolClient(cl))
 
+	s := &session{
+		provider: provider,
+		apiKey:   apiKey,
+		tools:    tools,
+		reg:      reg,
+		cl:       cl,
+		hist:     ai.NewHistory(50),
+		stream:   streamOutput,
+	}
+	hasAgents := s.discoverAgents()
+	if targetAgent != "" {
+		if _, ok := s.agents[targetAgent]; !ok {
+			return fmt.Errorf("agent %q is not registered; run `micro agent list` to see available agents", targetAgent)
+		}
+		s.agents = map[string]agentInfo{targetAgent: s.agents[targetAgent]}
+		hasAgents = true
+	}
+	if targetAgent != "" && singlePrompt != "" {
+		return s.ask(c.Context, singlePrompt)
+	}
+	if apiKey == "" {
+		return fmt.Errorf("no API key configured; set --api_key or %s", envVarForProvider(provider))
+	}
+
 	// Built-in agent capabilities (plan, delegate), reused from the
 	// agent package so the direct-service fallback matches a real agent.
 	builtinTools, builtinHandle := agent.Builtins(
@@ -343,17 +367,8 @@ func run(c *cli.Context) error {
 		agent.APIKey(apiKey),
 	)
 
-	s := &session{
-		provider:      provider,
-		apiKey:        apiKey,
-		tools:         tools,
-		reg:           reg,
-		cl:            cl,
-		hist:          ai.NewHistory(50),
-		builtinTools:  builtinTools,
-		builtinHandle: builtinHandle,
-		stream:        streamOutput,
-	}
+	s.builtinTools = builtinTools
+	s.builtinHandle = builtinHandle
 	s.refreshTools()
 
 	// Wrap the tool handler to intercept generate calls
@@ -387,9 +402,6 @@ func run(c *cli.Context) error {
 
 	defer s.cleanup()
 
-	// Discover registered agents
-	hasAgents := s.discoverAgents()
-
 	if singlePrompt != "" {
 		return s.ask(c.Context, singlePrompt)
 	}

cmd/micro/cli/agent/agent.go

@@ -14,6 +14,32 @@ import (
 	"go-micro.dev/v6/store"
 )
 
+const firstAgentQuickChecksHelp = `First-agent failure-mode quick checks
+
+Use this when scaffold -> run -> chat -> inspect stalls and you want the
+smallest provider-free recovery loop before reading the full docs.
+
+1. Confirm prerequisites before starting the gateway:
+   micro agent preflight
+
+2. Start the project and keep it running in a separate terminal:
+   micro run
+
+3. Check the agent is registered and the chat gateway is reachable:
+   micro agent doctor
+
+4. If chat returns an answer or an error, inspect the latest run state:
+   micro inspect agent <name>
+   micro runs <name>
+
+5. If provider chat is not configured yet, prove the no-secret path still works:
+   micro agent demo
+   go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1
+
+Recovery docs:
+  https://go-micro.dev/docs/guides/debugging-agents.html
+  https://go-micro.dev/docs/guides/no-secret-first-agent.html`
+
 const noSecretDemoHelp = `No-secret first-agent demo
 
 Use this when you want the fastest provider-free agent success path before
@@ -72,6 +98,18 @@ for live-provider chat and inspect/debugging.`,
 					return nil
 				},
 			},
+			{
+				Name:    "quickcheck",
+				Aliases: []string{"debug"},
+				Usage:   "Print first-agent failure-mode quick checks",
+				Description: `Print provider-free recovery breadcrumbs for the scaffold -> run ->
+chat -> inspect loop, including exact commands for registration, gateway, run
+history, and no-secret fallback checks.`,
+				Action: func(c *cli.Context) error {
+					fmt.Fprintln(c.App.Writer, firstAgentQuickChecksHelp)
+					return nil
+				},
+			},
 			{
 				Name:  "preflight",
 				Usage: "Check local prerequisites before the first provider-backed agent",
@@ -224,14 +262,44 @@ func writeRunIndex(w io.Writer, name string, runs []goagent.RunSummary, asJSON b
 		if run.TraceID != "" {
 			line += "  trace=" + shortTraceID(run.TraceID)
 		}
+		if run.Checkpoint != "" {
+			line += "  checkpoint=" + run.Checkpoint
+		}
+		if run.Stage != "" {
+			line += "  stage=" + run.Stage
+		}
 		if run.LastError != "" {
 			line += "  error=" + run.LastError
 		}
 		fmt.Fprintln(w, line)
+		writeRunIndexBreadcrumbs(w, name, run)
 	}
 	return nil
 }
 
+func writeRunIndexBreadcrumbs(w io.Writer, name string, run goagent.RunSummary) {
+	if run.Stage == "input-required" {
+		fmt.Fprintf(w, "      inspect: micro agent history %s %s\n", name, run.RunID)
+		fmt.Fprintf(w, "      input:   call micro.AgentResumeInput(ctx, agent, %q, input) to continue the input-required run\n", run.RunID)
+		return
+	}
+	if !isResumableRunSummary(run) {
+		return
+	}
+	fmt.Fprintf(w, "      inspect: micro agent history %s %s\n", name, run.RunID)
+	fmt.Fprintf(w, "      resume:  call micro.AgentResume(ctx, agent, %q) after recreating the agent with the same checkpoint store\n", run.RunID)
+	fmt.Fprintf(w, "      stream:  call micro.ResumeStreamAsk(ctx, agent, %q) to resume with streaming events\n", run.RunID)
+}
+
+func isResumableRunSummary(run goagent.RunSummary) bool {
+	switch run.Status {
+	case "running", "error", "failed", "refused":
+		return run.Checkpoint != "done" || run.Stage != ""
+	default:
+		return false
+	}
+}
+
 func printRunHistory(name, runID string, asJSON bool) error {
 	events, err := goagent.LoadRunEvents(store.DefaultStore, name, runID)
 	if err != nil {

cmd/micro/cli/agent/agent_test.go

@@ -59,6 +59,46 @@ func TestWriteRunIndexHumanIncludesStatusAndDuration(t *testing.T) {
 	}
 }
 
+func TestWriteRunIndexIncludesResumeBreadcrumbs(t *testing.T) {
+	runs := []goagent.RunSummary{{
+		RunID:      "run-failed",
+		Agent:      "runner",
+		UpdatedAt:  time.Date(2026, 6, 25, 12, 34, 56, 0, time.UTC),
+		Events:     3,
+		Status:     "error",
+		LastKind:   "tool",
+		Checkpoint: "failed",
+		Stage:      "ask",
+	}}
+	var out bytes.Buffer
+	if err := writeRunIndex(&out, "runner", runs, false); err != nil {
+		t.Fatal(err)
+	}
+	got := out.String()
+	for _, want := range []string{"checkpoint=failed", "stage=ask", `micro agent history runner run-failed`, `micro.AgentResume(ctx, agent, "run-failed")`, `micro.ResumeStreamAsk(ctx, agent, "run-failed")`} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("output missing %q:\n%s", want, got)
+		}
+	}
+}
+
+func TestWriteRunIndexInputRequiredUsesResumeInput(t *testing.T) {
+	runs := []goagent.RunSummary{{RunID: "run-input", Agent: "runner", Status: "running", LastKind: "checkpoint", Checkpoint: "paused", Stage: "input-required"}}
+	var out bytes.Buffer
+	if err := writeRunIndex(&out, "runner", runs, false); err != nil {
+		t.Fatal(err)
+	}
+	got := out.String()
+	for _, want := range []string{`micro agent history runner run-input`, `micro.AgentResumeInput(ctx, agent, "run-input", input)`} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("output missing %q:\n%s", want, got)
+		}
+	}
+	if strings.Contains(got, `micro.AgentResume(ctx, agent, "run-input")`) || strings.Contains(got, "ResumeStreamAsk") {
+		t.Fatalf("input-required run should point at ResumeInput only, got:\n%s", got)
+	}
+}
+
 func TestWriteRunHistoryHumanAndJSON(t *testing.T) {
 	events := []goagent.RunEvent{{
 		Time:      time.Date(2026, 6, 25, 12, 34, 56, 7_000_000, time.UTC),

cmd/micro/cli/agent/doctor_test.go

@@ -73,3 +73,24 @@ func TestRunAgentDoctorReportsActionableRecoveryFailures(t *testing.T) {
 		}
 	}
 }
+
+func TestAgentQuickcheckPrintsProviderFreeFailureModeBreadcrumbs(t *testing.T) {
+	got := firstAgentQuickChecksHelp
+	for _, want := range []string{
+		"First-agent failure-mode quick checks",
+		"scaffold -> run -> chat -> inspect",
+		"micro agent preflight",
+		"micro run",
+		"micro agent doctor",
+		"micro inspect agent <name>",
+		"micro runs <name>",
+		"micro agent demo",
+		"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1",
+		"debugging-agents.html",
+		"no-secret-first-agent.html",
+	} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("quickcheck output missing %q:\n%s", want, got)
+		}
+	}
+}

cmd/micro/cli/build/build.go

@@ -246,17 +246,17 @@ func Compose(c *cli.Context) error {
 			imageName = registry + "/" + imageName
 		}
 
-		sb.WriteString(fmt.Sprintf("  %s:\n", svc.Name))
-		sb.WriteString(fmt.Sprintf("    image: %s\n", imageName))
+		fmt.Fprintf(&sb, "  %s:\n", svc.Name)
+		fmt.Fprintf(&sb, "    image: %s\n", imageName)
 
 		if svc.Port > 0 {
-			sb.WriteString(fmt.Sprintf("    ports:\n      - \"%d:%d\"\n", svc.Port, svc.Port))
+			fmt.Fprintf(&sb, "    ports:\n      - \"%d:%d\"\n", svc.Port, svc.Port)
 		}
 
 		if len(svc.Depends) > 0 {
 			sb.WriteString("    depends_on:\n")
 			for _, dep := range svc.Depends {
-				sb.WriteString(fmt.Sprintf("      - %s\n", dep))
+				fmt.Fprintf(&sb, "      - %s\n", dep)
 			}
 		}
 

cmd/micro/cli/cli.go

@@ -24,6 +24,56 @@ import (
 	_ "go-micro.dev/v6/cmd/micro/cli/remote"
 )
 
+const zeroToHeroHelp = `0→hero no-secret lifecycle demo
+
+Run this from a go-micro repository checkout when you want one command that
+proves the maintained services → agents → workflows path without provider keys:
+
+  ./internal/harness/zero-to-hero-ci/run.sh
+
+That script runs the same deterministic path CI uses:
+  - CLI discovery for scaffold, run, chat, inspect, flow runs, and deploy dry-run
+  - the smallest first-agent example
+  - the support-desk reference app with services, an agent, a flow, and an approval gate
+  - plan/delegate and universe harnesses with only the model mocked
+
+If you only want the runnable examples first:
+  go run ./examples/first-agent
+  go run ./examples/support
+
+Full local contract:
+  make harness
+
+Guide: https://go-micro.dev/docs/guides/zero-to-hero.html`
+
+const examplesWayfinding = `First-agent examples (no provider key required)
+
+Run these from a go-micro repository checkout in this order. For the complete
+examples map, open examples/INDEX.md:
+
+  1. Smallest service-backed agent
+       go run ./examples/first-agent
+     Proves an agent can call a service tool with the deterministic mock model.
+
+  2. No-secret support-agent transcript
+       go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1
+     Exercises service tools, mock-model chat, and inspectable run history.
+
+  3. Full services → agents → workflows reference app
+       go run ./examples/support
+     Shows the support desk service, agent, workflow, and approval gate together.
+
+Then continue the same path with the installed CLI:
+  micro agent demo
+  micro docs
+  micro zero-to-hero
+
+Guides:
+  https://go-micro.dev/docs/guides/no-secret-first-agent.html
+  https://go-micro.dev/docs/guides/your-first-agent.html
+  https://go-micro.dev/docs/guides/debugging-agents.html
+  https://go-micro.dev/docs/guides/zero-to-hero.html`
+
 const docsWayfinding = `First-agent and 0→hero docs:
 
   1. Start with the no-secret CLI demo
@@ -32,6 +82,9 @@ const docsWayfinding = `First-agent and 0→hero docs:
      prove service tools, mock-model chat, and inspectable run history without
      configuring a provider key.
 
+     If scaffold → run → chat → inspect stalls, print the short recovery map:
+       micro agent quickcheck
+
   2. No-secret first-agent transcript
      https://go-micro.dev/docs/guides/no-secret-first-agent.html
      Run the maintained support agent without a provider key:
@@ -49,8 +102,8 @@ const docsWayfinding = `First-agent and 0→hero docs:
      https://go-micro.dev/docs/guides/debugging-agents.html
      Inspect agent runs and memory with:
        micro agent doctor
-       micro inspect agent
-       micro runs <agent>
+       micro inspect agent <name>
+       micro agent history <name>
 
   5. 0→hero Reference
      https://go-micro.dev/docs/guides/zero-to-hero.html
@@ -128,6 +181,28 @@ func init() {
 				return nil
 			},
 		},
+
+		{
+			Name:  "examples",
+			Usage: "Show provider-free first-agent example paths",
+			Description: `Print the maintained no-secret examples for the services → agents →
+workflows on-ramp: first-agent, transcript, support app, and matching guides.`,
+			Action: func(ctx *cli.Context) error {
+				fmt.Fprintln(ctx.App.Writer, examplesWayfinding)
+				return nil
+			},
+		},
+		{
+			Name:  "zero-to-hero",
+			Usage: "Show the no-secret 0→hero lifecycle demo command",
+			Description: `Print the maintained provider-free services → agents → workflows
+lifecycle command and the smaller runnable examples it covers.`,
+			Aliases: []string{"hero"},
+			Action: func(ctx *cli.Context) error {
+				fmt.Fprintln(ctx.App.Writer, zeroToHeroHelp)
+				return nil
+			},
+		},
 		{
 			Name:  "docs",
 			Usage: "Show the first-agent and 0→hero documentation path",

cmd/micro/cli/deploy/deploy.go

@@ -93,7 +93,7 @@ func showDeployTargets(cfg *config.Config) error {
 	var sb strings.Builder
 	sb.WriteString("Available deploy targets:\n\n")
 	for name, dt := range cfg.Deploy {
-		sb.WriteString(fmt.Sprintf("  %s -> %s\n", name, dt.SSH))
+		fmt.Fprintf(&sb, "  %s -> %s\n", name, dt.SSH)
 	}
 	sb.WriteString("\nDeploy with: micro deploy <target>")
 	return fmt.Errorf("%s", sb.String())

cmd/micro/cli/generate/generate.go

@@ -502,18 +502,18 @@ func newModel(provider, apiKey, model string) ai.Model {
 
 func buildProto(dehyphen, titleName string, svc ServiceSpec) string {
 	var b strings.Builder
-	b.WriteString(fmt.Sprintf("syntax = \"proto3\";\n\npackage %s;\n\noption go_package = \"./proto;%s\";\n\n", dehyphen, dehyphen))
+	fmt.Fprintf(&b, "syntax = \"proto3\";\n\npackage %s;\n\noption go_package = \"./proto;%s\";\n\n", dehyphen, dehyphen)
 
-	b.WriteString(fmt.Sprintf("service %s {\n", titleName))
+	fmt.Fprintf(&b, "service %s {\n", titleName)
 	for _, ep := range svc.Endpoints {
-		b.WriteString(fmt.Sprintf("\trpc %s(%sRequest) returns (%sResponse) {}\n", ep.Name, ep.Name, ep.Name))
+		fmt.Fprintf(&b, "\trpc %s(%sRequest) returns (%sResponse) {}\n", ep.Name, ep.Name, ep.Name)
 	}
 	b.WriteString("}\n\n")
 
 	// Record message
-	b.WriteString(fmt.Sprintf("message %sRecord {\n", titleName))
+	fmt.Fprintf(&b, "message %sRecord {\n", titleName)
 	for i, f := range svc.Fields {
-		b.WriteString(fmt.Sprintf("\t%s %s = %d; // %s\n", protoType(f.Type), f.Name, i+1, f.Description))
+		fmt.Fprintf(&b, "\t%s %s = %d; // %s\n", protoType(f.Type), f.Name, i+1, f.Description)
 	}
 	b.WriteString("}\n\n")
 
@@ -527,12 +527,12 @@ func buildProto(dehyphen, titleName string, svc ServiceSpec) string {
 				if f.Name == "id" || f.Name == "created" || f.Name == "updated" {
 					continue
 				}
-				b.WriteString(fmt.Sprintf("\t%s %s = %d;\n", protoType(f.Type), f.Name, n))
+				fmt.Fprintf(&b, "\t%s %s = %d;\n", protoType(f.Type), f.Name, n)
 				n++
 			}
-			b.WriteString(fmt.Sprintf("}\n\nmessage CreateResponse {\n\t%sRecord record = 1;\n}\n\n", titleName))
+			fmt.Fprintf(&b, "}\n\nmessage CreateResponse {\n\t%sRecord record = 1;\n}\n\n", titleName)
 		case "Read":
-			b.WriteString(fmt.Sprintf("message ReadRequest {\n\tstring id = 1;\n}\n\nmessage ReadResponse {\n\t%sRecord record = 1;\n}\n\n", titleName))
+			fmt.Fprintf(&b, "message ReadRequest {\n\tstring id = 1;\n}\n\nmessage ReadResponse {\n\t%sRecord record = 1;\n}\n\n", titleName)
 		case "Update":
 			b.WriteString("message UpdateRequest {\n\tstring id = 1;\n")
 			n := 2
@@ -540,26 +540,26 @@ func buildProto(dehyphen, titleName string, svc ServiceSpec) string {
 				if f.Name == "id" || f.Name == "created" || f.Name == "updated" {
 					continue
 				}
-				b.WriteString(fmt.Sprintf("\t%s %s = %d;\n", protoType(f.Type), f.Name, n))
+				fmt.Fprintf(&b, "\t%s %s = %d;\n", protoType(f.Type), f.Name, n)
 				n++
 			}
-			b.WriteString(fmt.Sprintf("}\n\nmessage UpdateResponse {\n\t%sRecord record = 1;\n}\n\n", titleName))
+			fmt.Fprintf(&b, "}\n\nmessage UpdateResponse {\n\t%sRecord record = 1;\n}\n\n", titleName)
 		case "Delete":
 			b.WriteString("message DeleteRequest {\n\tstring id = 1;\n}\n\nmessage DeleteResponse {\n\tbool deleted = 1;\n}\n\n")
 		case "List":
-			b.WriteString(fmt.Sprintf("message ListRequest {\n\tint64 limit = 1;\n\tint64 offset = 2;\n\tstring query = 3;\n}\n\nmessage ListResponse {\n\trepeated %sRecord records = 1;\n\tint64 total = 2;\n}\n\n", titleName))
+			fmt.Fprintf(&b, "message ListRequest {\n\tint64 limit = 1;\n\tint64 offset = 2;\n\tstring query = 3;\n}\n\nmessage ListResponse {\n\trepeated %sRecord records = 1;\n\tint64 total = 2;\n}\n\n", titleName)
 		default:
 			// Custom endpoint — use all fields as input, record as output
-			b.WriteString(fmt.Sprintf("message %sRequest {\n", ep.Name))
+			fmt.Fprintf(&b, "message %sRequest {\n", ep.Name)
 			n := 1
 			for _, f := range svc.Fields {
 				if f.Name == "created" || f.Name == "updated" {
 					continue
 				}
-				b.WriteString(fmt.Sprintf("\t%s %s = %d;\n", protoType(f.Type), f.Name, n))
+				fmt.Fprintf(&b, "\t%s %s = %d;\n", protoType(f.Type), f.Name, n)
 				n++
 			}
-			b.WriteString(fmt.Sprintf("}\n\nmessage %sResponse {\n\t%sRecord record = 1;\n\tstring message = 2;\n\tbool success = 3;\n}\n\n", ep.Name, titleName))
+			fmt.Fprintf(&b, "}\n\nmessage %sResponse {\n\t%sRecord record = 1;\n\tstring message = 2;\n\tbool success = 3;\n}\n\n", ep.Name, titleName)
 		}
 	}
 	return b.String()

cmd/micro/cli/new/contract_test.go

@@ -31,7 +31,7 @@ func TestZeroToOneContract(t *testing.T) {
 		}
 	}
 
-	generated.replaceModule(t)
+	generated.assertLocalModule(t)
 	generated.build(t)
 	generated.run(t)
 	generated.call(t, "Alice", "Hello Alice")
@@ -52,7 +52,7 @@ func TestZeroToOneNoMCPContract(t *testing.T) {
 		t.Fatalf("--no-mcp generated main.go with MCP wiring:\n%s", main)
 	}
 
-	generated.replaceModule(t)
+	generated.assertLocalModule(t)
 	generated.build(t)
 	generated.run(t)
 	generated.call(t, "Bob", "Hello Bob")
@@ -67,7 +67,7 @@ func TestPrintNextStepsSurfacesFirstAgentPath(t *testing.T) {
 		"micro agent preflight",
 		"go run .",
 		"micro chat",
-		"micro inspect agent",
+		"micro inspect agent <name>",
 		"micro agent demo",
 		"micro docs",
 		"your-first-agent.html",
@@ -84,7 +84,7 @@ func TestPrintNextStepsNoMCPSkipsMCPHints(t *testing.T) {
 	var out bytes.Buffer
 	printNextSteps(&out, "worker", true)
 
-	for _, want := range []string{"micro agent preflight", "micro chat", "micro inspect agent", "micro agent demo", "micro docs"} {
+	for _, want := range []string{"micro agent preflight", "micro chat", "micro inspect agent <name>", "micro agent demo", "micro docs"} {
 		if !strings.Contains(out.String(), want) {
 			t.Fatalf("--no-mcp next steps missing %q:\n%s", want, out.String())
 		}
@@ -112,6 +112,7 @@ func generateService(t *testing.T, name string, args ...string) generatedService
 	if err != nil {
 		t.Fatal(err)
 	}
+	t.Setenv("MICRO_NEW_GO_MICRO_REPLACE", repoRoot)
 
 	tmp := t.TempDir()
 	oldwd, err := os.Getwd()
@@ -142,7 +143,7 @@ func generateService(t *testing.T, name string, args ...string) generatedService
 	return generatedService{dir: filepath.Join(tmp, name), repoRoot: repoRoot}
 }
 
-func (g generatedService) replaceModule(t *testing.T) {
+func (g generatedService) assertLocalModule(t *testing.T) {
 	t.Helper()
 
 	modPath := filepath.Join(g.dir, "go.mod")
@@ -150,10 +151,9 @@ func (g generatedService) replaceModule(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	modText := strings.Replace(string(mod), "go-micro.dev/v6 latest", "go-micro.dev/v6 v6.0.0", 1)
-	modText += "\nreplace go-micro.dev/v6 => " + filepath.ToSlash(g.repoRoot) + "\n"
-	if err := os.WriteFile(modPath, []byte(modText), 0644); err != nil {
-		t.Fatal(err)
+	want := "replace go-micro.dev/v6 => " + filepath.ToSlash(g.repoRoot)
+	if !strings.Contains(string(mod), want) {
+		t.Fatalf("generated go.mod missing local replace %q:\n%s", want, mod)
 	}
 }
 

cmd/micro/cli/new/new.go

@@ -39,6 +39,8 @@ type config struct {
 	UseGoPath bool
 	// MicroVersion is the go-micro version to require in go.mod
 	MicroVersion string
+	// MicroReplace optionally points generated services at a local go-micro checkout.
+	MicroReplace string
 	// Files
 	Files []file
 	// Comments
@@ -69,6 +71,10 @@ func microVersion() string {
 	return "latest"
 }
 
+func microReplace() string {
+	return filepath.ToSlash(os.Getenv("MICRO_NEW_GO_MICRO_REPLACE"))
+}
+
 type file struct {
 	Path string
 	Tmpl string
@@ -215,6 +221,7 @@ func Run(ctx *cli.Context) error {
 		GoPath:       goPath,
 		UseGoPath:    false,
 		MicroVersion: microVersion(),
+		MicroReplace: microReplace(),
 	}
 
 	if useProto {
@@ -291,7 +298,7 @@ func printNextSteps(w io.Writer, dir string, noMCP bool) {
 	fmt.Fprintln(w, "    micro agent preflight")
 	fmt.Fprintln(w, "    go run .")
 	fmt.Fprintln(w, "    micro chat")
-	fmt.Fprintln(w, "    micro inspect agent")
+	fmt.Fprintln(w, "    micro inspect agent <name>")
 	fmt.Fprintln(w)
 	fmt.Fprintln(w, "  First-agent path:")
 	fmt.Fprintln(w, "    micro agent demo")

cmd/micro/cli/new/template/module.go

@@ -10,7 +10,9 @@ require (
 	github.com/golang/protobuf latest
 	google.golang.org/protobuf latest
 )
-`
+{{if .MicroReplace}}
+replace go-micro.dev/v6 => {{.MicroReplace}}
+{{end}}`
 
 	// ModuleNoProto is the default go.mod: no protobuf dependencies.
 	// MicroVersion is the version this CLI was built from (or "latest"), so a
@@ -20,5 +22,7 @@ require (
 go 1.23
 
 require go-micro.dev/v6 {{.MicroVersion}}
-`
+{{if .MicroReplace}}
+replace go-micro.dev/v6 => {{.MicroReplace}}
+{{end}}`
 )

cmd/micro/examples_wayfinding_test.go

@@ -0,0 +1,71 @@
+package main
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/urfave/cli/v2"
+	microcmd "go-micro.dev/v6/cmd"
+)
+
+func TestExamplesWayfindingIndexStaysLinked(t *testing.T) {
+	root := filepath.Join("..", "..")
+	files := map[string]string{}
+	for _, name := range []string{"README.md", "examples/README.md", "examples/INDEX.md"} {
+		b, err := os.ReadFile(filepath.Join(root, filepath.FromSlash(name)))
+		if err != nil {
+			t.Fatalf("read %s: %v", name, err)
+		}
+		files[name] = string(b)
+	}
+
+	for _, check := range []struct {
+		file string
+		want []string
+	}{
+		{
+			file: "README.md",
+			want: []string{"examples/INDEX.md", "examples/first-agent/", "examples/support/", "zero-to-hero.md"},
+		},
+		{
+			file: "examples/README.md",
+			want: []string{"./INDEX.md", "./first-agent/", "./support/", "./mcp/hello/", "./mcp/workflow/"},
+		},
+		{
+			file: "examples/INDEX.md",
+			want: []string{"go run ./examples/first-agent", "go run ./examples/support", "mcp/hello", "mcp/workflow", "flow-durable", "micro examples"},
+		},
+	} {
+		for _, want := range check.want {
+			if !strings.Contains(files[check.file], want) {
+				t.Fatalf("%s missing %q", check.file, want)
+			}
+		}
+	}
+}
+
+func TestExamplesCommandPointsAtWayfindingIndex(t *testing.T) {
+	examples := commandByName(t, "examples")
+	var out bytes.Buffer
+	app := cli.NewApp()
+	app.Writer = &out
+	if err := examples.Action(cli.NewContext(app, nil, nil)); err != nil {
+		t.Fatalf("micro examples failed: %v", err)
+	}
+
+	for _, want := range []string{
+		"examples/INDEX.md",
+		"go run ./examples/first-agent",
+		"go run ./examples/support",
+		"micro zero-to-hero",
+	} {
+		if !strings.Contains(out.String(), want) {
+			t.Fatalf("micro examples output missing %q:\n%s", want, out.String())
+		}
+	}
+
+	_ = microcmd.DefaultCmd // keep this test coupled to the registered command package.
+}

cmd/micro/first_agent_walkthrough_test.go

@@ -2,6 +2,8 @@ package main
 
 import (
 	"bytes"
+	"os"
+	"path/filepath"
 	"strings"
 	"testing"
 
@@ -22,7 +24,7 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
 		}
 	}
 
-	for _, want := range []string{"new", "run", "chat", "inspect", "agent", "docs"} {
+	for _, want := range []string{"new", "run", "chat", "inspect", "agent", "docs", "examples"} {
 		if !commands[want] {
 			t.Fatalf("first-agent walkthrough missing %q command", want)
 		}
@@ -36,12 +38,15 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
 	if !subcommands["agent"]["doctor"] {
 		t.Fatal("first-agent walkthrough missing recovery boundary: agent doctor")
 	}
+	if !subcommands["agent"]["quickcheck"] {
+		t.Fatal("first-agent walkthrough missing failure-mode boundary: agent quickcheck")
+	}
 	if !subcommands["inspect"]["agent"] {
 		t.Fatal("first-agent walkthrough missing inspect boundary: inspect agent")
 	}
 
 	chat := commandByName(t, "chat")
-	if !strings.Contains(chat.Description, "services") || !strings.Contains(chat.Description, "agent") {
+	if !strings.Contains(chat.Description, "services") || !strings.Contains(chat.Description, "agent") || !strings.Contains(chat.Description, `micro chat assistant --prompt`) {
 		t.Fatalf("micro chat should describe the service-to-agent walkthrough boundary; description was %q", chat.Description)
 	}
 
@@ -68,12 +73,42 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
 		"micro run",
 		"micro chat",
 		"micro agent doctor     # after micro run: chat/gateway/inspect recovery",
-		"micro inspect agent",
+		"micro inspect agent <name>",
+		"micro agent history <name>",
 	} {
 		if !strings.Contains(out.String(), want) {
 			t.Fatalf("micro docs output missing %q:\n%s", want, out.String())
 		}
 	}
+	if strings.Contains(out.String(), "micro runs") {
+		t.Fatalf("micro docs output should use the first-agent inspect command, not the legacy runs shortcut:\n%s", out.String())
+	}
+
+	examples := commandByName(t, "examples")
+	if !strings.Contains(examples.Usage, "first-agent") {
+		t.Fatalf("micro examples should advertise the first-agent examples path; usage was %q", examples.Usage)
+	}
+	out.Reset()
+	if err := examples.Action(cli.NewContext(app, nil, nil)); err != nil {
+		t.Fatalf("micro examples failed: %v", err)
+	}
+	for _, want := range []string{
+		"First-agent examples",
+		"go run ./examples/first-agent",
+		"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1",
+		"go run ./examples/support",
+		"micro agent demo",
+		"micro docs",
+		"micro zero-to-hero",
+		"no-secret-first-agent.html",
+		"your-first-agent.html",
+		"debugging-agents.html",
+		"zero-to-hero.html",
+	} {
+		if !strings.Contains(out.String(), want) {
+			t.Fatalf("micro examples output missing %q:\n%s", want, out.String())
+		}
+	}
 
 	agent := commandByName(t, "agent")
 	if !strings.Contains(agent.Usage, "micro agent demo") {
@@ -86,6 +121,28 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
 		}
 	}
 
+	quickcheck := subcommandByName(t, agent, "quickcheck")
+	out.Reset()
+	if err := quickcheck.Action(cli.NewContext(app, nil, nil)); err != nil {
+		t.Fatalf("micro agent quickcheck failed: %v", err)
+	}
+	for _, want := range []string{
+		"First-agent failure-mode quick checks",
+		"scaffold -> run -> chat -> inspect",
+		"micro agent preflight",
+		"micro run",
+		"micro agent doctor",
+		"micro inspect agent <name>",
+		"micro runs <name>",
+		"micro agent demo",
+		"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1",
+		"debugging-agents.html",
+	} {
+		if !strings.Contains(out.String(), want) {
+			t.Fatalf("micro agent quickcheck output missing %q:\n%s", want, out.String())
+		}
+	}
+
 	demo := subcommandByName(t, agent, "demo")
 	out.Reset()
 	if err := demo.Action(cli.NewContext(app, nil, nil)); err != nil {
@@ -109,6 +166,137 @@ func TestFirstAgentWalkthroughCLIBoundaries(t *testing.T) {
 	}
 }
 
+func TestFirstAgentDocsMatchCLIOutput(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", ".."))
+	outputs := map[string]string{
+		"micro docs":         commandOutput(t, commandByName(t, "docs")),
+		"micro examples":     commandOutput(t, commandByName(t, "examples")),
+		"micro zero-to-hero": commandOutput(t, commandByName(t, "zero-to-hero")),
+	}
+	agent := commandByName(t, "agent")
+	outputs["micro agent demo"] = commandOutput(t, subcommandByName(t, agent, "demo"))
+	outputs["micro agent quickcheck"] = commandOutput(t, subcommandByName(t, agent, "quickcheck"))
+
+	contracts := []struct {
+		name    string
+		file    string
+		markers []string
+	}{
+		{
+			name: "README first-agent on-ramp",
+			file: filepath.Join(root, "README.md"),
+			markers: []string{
+				"micro agent demo",
+				"micro agent quickcheck",
+				"micro agent preflight",
+				"micro agent doctor",
+				"micro inspect agent <name>",
+				"micro examples",
+				"micro zero-to-hero",
+				"make docs-wayfinding",
+				"examples/first-agent/",
+				"examples/support/",
+				"internal/website/docs/guides/no-secret-first-agent.md",
+				"internal/website/docs/guides/your-first-agent.md",
+				"internal/website/docs/guides/debugging-agents.md",
+				"internal/website/docs/guides/zero-to-hero.md",
+			},
+		},
+		{
+			name: "website getting-started first-agent on-ramp",
+			file: filepath.Join(root, "internal", "website", "docs", "getting-started.md"),
+			markers: []string{
+				"micro agent demo",
+				"micro agent quickcheck",
+				"micro agent preflight",
+				"micro agent doctor",
+				"micro inspect agent <name>",
+				"micro examples",
+				"micro zero-to-hero",
+				"make docs-wayfinding",
+				"github.com/micro/go-micro/tree/master/examples/first-agent",
+				"github.com/micro/go-micro/tree/master/examples/support",
+				"guides/no-secret-first-agent.html",
+				"guides/your-first-agent.html",
+				"guides/debugging-agents.html",
+				"guides/zero-to-hero.html",
+			},
+		},
+	}
+
+	for _, contract := range contracts {
+		doc := readTestFile(t, contract.file)
+		for _, marker := range contract.markers {
+			if !strings.Contains(doc, marker) {
+				t.Fatalf("%s missing documented first-agent marker %q", contract.name, marker)
+			}
+			if isCLIContractMarker(marker) && !cliOutputsContain(outputs, marker) {
+				t.Fatalf("%s documents %q, but none of the first-agent CLI outputs mention it; keep README/website breadcrumbs aligned with micro agent demo/examples/zero-to-hero", contract.name, marker)
+			}
+			assertMaintainedFirstAgentPath(t, root, marker)
+		}
+	}
+}
+
+func commandOutput(t *testing.T, command *cli.Command) string {
+	t.Helper()
+	var out bytes.Buffer
+	app := cli.NewApp()
+	app.Writer = &out
+	if err := command.Action(cli.NewContext(app, nil, nil)); err != nil {
+		t.Fatalf("%s failed: %v", command.Name, err)
+	}
+	return out.String()
+}
+
+func cliOutputsContain(outputs map[string]string, marker string) bool {
+	for command, out := range outputs {
+		if command == marker || strings.Contains(out, marker) {
+			return true
+		}
+	}
+	return false
+}
+
+func isCLIContractMarker(marker string) bool {
+	return strings.HasPrefix(marker, "micro ") || strings.HasPrefix(marker, "go run ") || strings.HasPrefix(marker, "go test ") || strings.Contains(marker, ".html")
+}
+
+func assertMaintainedFirstAgentPath(t *testing.T, root, marker string) {
+	t.Helper()
+	pathChecks := map[string]string{
+		"go run ./examples/first-agent":                              "examples/first-agent",
+		"examples/first-agent/":                                      "examples/first-agent",
+		"examples/support/":                                          "examples/support",
+		"internal/website/docs/guides/no-secret-first-agent.md":      "internal/website/docs/guides/no-secret-first-agent.md",
+		"internal/website/docs/guides/your-first-agent.md":           "internal/website/docs/guides/your-first-agent.md",
+		"internal/website/docs/guides/debugging-agents.md":           "internal/website/docs/guides/debugging-agents.md",
+		"internal/website/docs/guides/zero-to-hero.md":               "internal/website/docs/guides/zero-to-hero.md",
+		"guides/no-secret-first-agent.html":                          "internal/website/docs/guides/no-secret-first-agent.md",
+		"guides/your-first-agent.html":                               "internal/website/docs/guides/your-first-agent.md",
+		"guides/debugging-agents.html":                               "internal/website/docs/guides/debugging-agents.md",
+		"guides/zero-to-hero.html":                                   "internal/website/docs/guides/zero-to-hero.md",
+		"github.com/micro/go-micro/tree/master/examples/first-agent": "examples/first-agent",
+		"github.com/micro/go-micro/tree/master/examples/support":     "examples/support",
+	}
+	path, ok := pathChecks[marker]
+	if !ok {
+		return
+	}
+	if _, err := os.Stat(filepath.Join(root, filepath.FromSlash(path))); err != nil {
+		t.Fatalf("documented first-agent path %q from marker %q does not resolve: %v", path, marker, err)
+	}
+}
+
+func readTestFile(t *testing.T, path string) string {
+	t.Helper()
+	b, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read %s: %v", path, err)
+	}
+	return string(b)
+}
+
 func commandByName(t *testing.T, name string) *cli.Command {
 	t.Helper()
 	for _, command := range microcmd.DefaultCmd.App().Commands {

cmd/micro/inspect/inspect.go

@@ -98,16 +98,25 @@ func writeAgentInspection(w io.Writer, name string, runs []goagent.RunSummary, a
 			fmt.Fprintf(w, "  trace=%s", shortID(run.TraceID))
 		}
 		fmt.Fprintln(w)
-		if isResumableAgentRun(run) {
-			fmt.Fprintf(w, "    resume: call micro.AgentResume(ctx, agent, %q) after recreating the agent with the same checkpoint store\n", run.RunID)
-		}
-		if run.Stage == "input-required" {
-			fmt.Fprintf(w, "    input:  call micro.AgentResumeInput(ctx, agent, %q, input) to continue the paused run\n", run.RunID)
-		}
+		writeAgentRunBreadcrumbs(w, name, run)
 	}
 	return nil
 }
 
+func writeAgentRunBreadcrumbs(w io.Writer, name string, run goagent.RunSummary) {
+	if run.Stage == "input-required" {
+		fmt.Fprintf(w, "    inspect: micro agent history %s %s\n", name, run.RunID)
+		fmt.Fprintf(w, "    input:   call micro.AgentResumeInput(ctx, agent, %q, input) to continue the input-required run\n", run.RunID)
+		return
+	}
+	if !isResumableAgentRun(run) {
+		return
+	}
+	fmt.Fprintf(w, "    inspect: micro agent history %s %s\n", name, run.RunID)
+	fmt.Fprintf(w, "    resume:  call micro.AgentResume(ctx, agent, %q) after recreating the agent with the same checkpoint store\n", run.RunID)
+	fmt.Fprintf(w, "    stream:  call micro.ResumeStreamAsk(ctx, agent, %q) to resume with streaming events\n", run.RunID)
+}
+
 func isResumableAgentRun(run goagent.RunSummary) bool {
 	switch run.Status {
 	case "running", "error", "failed", "refused":

cmd/micro/inspect/inspect_test.go

@@ -17,7 +17,7 @@ func TestWriteAgentInspectionIncludesActionableBreadcrumbs(t *testing.T) {
 		t.Fatal(err)
 	}
 	got := out.String()
-	for _, want := range []string{"Agent \"support\" runs", "run-1", "status=error", "events=4", "last=tool", "checkpoint=failed", "stage=ask", `error="boom"`, "trace=1234567890ab", `micro.AgentResume(ctx, agent, "run-1")`} {
+	for _, want := range []string{"Agent \"support\" runs", "run-1", "status=error", "events=4", "last=tool", "checkpoint=failed", "stage=ask", `error="boom"`, "trace=1234567890ab", `micro agent history support run-1`, `micro.AgentResume(ctx, agent, "run-1")`, `micro.ResumeStreamAsk(ctx, agent, "run-1")`} {
 		if !strings.Contains(got, want) {
 			t.Fatalf("output missing %q:\n%s", want, got)
 		}
@@ -31,11 +31,14 @@ func TestWriteAgentInspectionIncludesInputResumeBreadcrumb(t *testing.T) {
 		t.Fatal(err)
 	}
 	got := out.String()
-	for _, want := range []string{"checkpoint=paused", "stage=input-required", `micro.AgentResumeInput(ctx, agent, "run-input", input)`} {
+	for _, want := range []string{"checkpoint=paused", "stage=input-required", `micro agent history support run-input`, `micro.AgentResumeInput(ctx, agent, "run-input", input)`} {
 		if !strings.Contains(got, want) {
 			t.Fatalf("output missing %q:\n%s", want, got)
 		}
 	}
+	if strings.Contains(got, `micro.AgentResume(ctx, agent, "run-input")`) || strings.Contains(got, "ResumeStreamAsk") {
+		t.Fatalf("input-required run should point at ResumeInput only, got:\n%s", got)
+	}
 }
 
 func TestWriteAgentInspectionEmptyStateNamesInspectCommand(t *testing.T) {

cmd/micro/loop/loop.go

@@ -123,7 +123,7 @@ Examples:
 					&cli.StringFlag{Name: "dir", Usage: "Target repo directory", Value: "."},
 					&cli.StringFlag{Name: "roles", Usage: "Comma-separated roles, or 'all'", Value: "planner,builder,triage"},
 					&cli.StringFlag{Name: "branch", Usage: "Base branch for the loop's PRs (auto-detected if empty)"},
-					&cli.StringFlag{Name: "agent", Usage: "How the workflows summon the agent (an @mention)", Value: "@codex"},
+					&cli.StringFlag{Name: "agent", Usage: "How the workflows summon the agent — any @mention-driven coding agent (e.g. @codex, @claude)", Value: "@codex"},
 					&cli.StringFlag{Name: "token-secret", Usage: "Repo secret holding the user PAT that drives dispatch", Value: "LOOP_TOKEN"},
 					&cli.StringFlag{Name: "ci-workflow", Usage: "CI workflow name(s) triage watches for failures (comma-separated)", Value: "CI"},
 					&cli.StringFlag{Name: "planner-cron", Usage: "Cron schedule for the planner", Value: "0 * * * *"},

cmd/micro/loop/templates/loop-release.yml.tmpl

@@ -1,9 +1,11 @@
 name: "Loop: Release"
 
-# Generated by `micro loop init`. Cuts the next PATCH tag
-# (<< .TagPrefix >>MAJOR.MINOR.PATCH+1) when the default branch has new commits
-# since the latest such tag, and pushes it with a PAT (<< .TokenSecret >>) so any
-# tag-triggered release workflow fires. Minor/major bumps stay with a human.
+# Generated by `micro loop init`. Cuts the next tag when the default branch has
+# new commits since the latest one, and pushes it with a PAT (<< .TokenSecret >>)
+# so any tag-triggered release workflow fires. The bump reflects what shipped,
+# read from the CHANGELOG [Unreleased] section: new features (Added/Changed) cut
+# a MINOR; fixes/docs only cut a PATCH; breaking changes are skipped so a MAJOR
+# stays a human decision.
 #
 # The tag MUST be pushed with a PAT, not the default GITHUB_TOKEN: a tag pushed
 # by GITHUB_TOKEN does not trigger other workflows (Actions blocks that recursion).
@@ -66,11 +68,30 @@ jobs:
             [0-9]*.[0-9]*.[0-9]*) ;;
             *) echo "unexpected tag shape: $LATEST" ; exit 1 ;;
           esac
-          NEXT="<< .TagPrefix >>${major}.${minor}.$((patch + 1))"
-          echo "cutting: $NEXT ($COUNT commits since $LATEST)"
+
+          # Choose the bump from what actually shipped, read from the CHANGELOG
+          # [Unreleased] section (kept current by the coherence role):
+          #   new features (### Added / ### Changed) -> MINOR
+          #   fixes/docs only                        -> PATCH
+          #   breaking (### Removed / "(breaking)")  -> skip; a major is a human call
+          UNRELEASED=""
+          if [ -f CHANGELOG.md ]; then
+            UNRELEASED=$(awk '/^## \[Unreleased\]/{f=1; next} /^## \[/{f=0} f' CHANGELOG.md)
+          fi
+          if printf '%s\n' "$UNRELEASED" | grep -qiE '^### Removed|^### Changed \(breaking\)|BREAKING'; then
+            echo "CHANGELOG [Unreleased] contains breaking changes — a major release is a human decision. Skipping."
+            exit 0
+          elif printf '%s\n' "$UNRELEASED" | grep -qE '^### (Added|Changed)'; then
+            NEXT="<< .TagPrefix >>${major}.$((minor + 1)).0"
+            KIND="minor (new features)"
+          else
+            NEXT="<< .TagPrefix >>${major}.${minor}.$((patch + 1))"
+            KIND="patch (fixes/docs only)"
+          fi
+          echo "cutting: $NEXT — $KIND ($COUNT commits since $LATEST)"
 
           git config user.name "loop release bot"
           git config user.email "noreply@users.noreply.github.com"
-          git tag -a "$NEXT" -m "Release $NEXT — automated patch ($COUNT commits since $LATEST)"
+          git tag -a "$NEXT" -m "Release $NEXT — automated $KIND ($COUNT commits since $LATEST)"
           git push "https://x-access-token:${RELEASE_TOKEN}@github.com/${REPO}.git" "$NEXT"
           echo "Pushed $NEXT."

cmd/micro/zero_to_hero_cli_test.go

@@ -1,6 +1,8 @@
 package main
 
 import (
+	"bytes"
+	"strings"
 	"testing"
 
 	microcmd "go-micro.dev/v6/cmd"
@@ -19,7 +21,7 @@ func TestZeroToHeroCLIBoundaries(t *testing.T) {
 		}
 	}
 
-	for _, want := range []string{"run", "chat", "flow", "inspect", "deploy"} {
+	for _, want := range []string{"run", "chat", "flow", "inspect", "deploy", "zero-to-hero"} {
 		if !commands[want] {
 			t.Fatalf("missing %q command", want)
 		}
@@ -48,3 +50,29 @@ func TestZeroToHeroCLIBoundaries(t *testing.T) {
 		t.Fatal("missing deploy boundary: deploy --dry-run")
 	}
 }
+
+func TestZeroToHeroCommandPrintsMaintainedNoSecretPath(t *testing.T) {
+	app := microcmd.DefaultCmd.App()
+	var out bytes.Buffer
+	oldWriter := app.Writer
+	app.Writer = &out
+	t.Cleanup(func() { app.Writer = oldWriter })
+
+	if err := app.Run([]string{"micro", "zero-to-hero"}); err != nil {
+		t.Fatalf("micro zero-to-hero failed: %v", err)
+	}
+
+	got := out.String()
+	for _, want := range []string{
+		"0→hero no-secret lifecycle demo",
+		"./internal/harness/zero-to-hero-ci/run.sh",
+		"go run ./examples/first-agent",
+		"go run ./examples/support",
+		"make harness",
+		"services → agents → workflows",
+	} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("micro zero-to-hero output missing %q:\n%s", want, got)
+		}
+	}
+}

events/memory.go

@@ -36,6 +36,9 @@ type subscriber struct {
 	retryLimit int
 	autoAck    bool
 	ackWait    time.Duration
+
+	pending []Event
+	notify  chan struct{}
 }
 
 type mem struct {
@@ -124,6 +127,7 @@ func (m *mem) Consume(topic string, opts ...ConsumeOption) (<-chan Event, error)
 		retryMap:   map[string]int{},
 		autoAck:    true,
 		retryLimit: options.GetRetryLimit(),
+		notify:     make(chan struct{}, 1),
 	}
 
 	if !options.AutoAck {
@@ -132,6 +136,7 @@ func (m *mem) Consume(topic string, opts ...ConsumeOption) (<-chan Event, error)
 		}
 		sub.autoAck = options.AutoAck
 		sub.ackWait = options.AckWait
+		go sub.dispatchManualAck()
 	}
 
 	// register the subscriber
@@ -197,56 +202,98 @@ func (m *mem) handleEvent(ev *Event) {
 }
 
 func sendEvent(ev *Event, sub *subscriber) {
-	go func(s *subscriber) {
-		evCopy := *ev
-		if s.autoAck {
-			s.Channel <- evCopy
-			return
-		}
-		evCopy.SetAckFunc(ackFunc(s, evCopy))
-		evCopy.SetNackFunc(nackFunc(s, evCopy))
-		s.Lock()
-		s.retryMap[evCopy.ID] = 0
-		s.Unlock()
-		tick := time.NewTicker(s.ackWait)
-		defer tick.Stop()
-		for range tick.C {
-			s.Lock()
-			count, ok := s.retryMap[evCopy.ID]
-			s.Unlock()
-			if !ok {
-				// success
-				break
-			}
+	evCopy := *ev
+	if !sub.autoAck {
+		sub.Lock()
+		sub.pending = append(sub.pending, evCopy)
+		sub.Unlock()
+		sub.wake()
+		return
+	}
 
-			if s.retryLimit > -1 && count > s.retryLimit {
-				if logger.V(logger.ErrorLevel, logger.DefaultLogger) {
-					logger.Errorf("Message retry limit reached, discarding: %v %d %d", evCopy.ID, count, s.retryLimit)
-				}
-				s.Lock()
-				delete(s.retryMap, evCopy.ID)
-				s.Unlock()
-				return
-			}
-			s.Channel <- evCopy
-			s.Lock()
-			s.retryMap[evCopy.ID] = count + 1
-			s.Unlock()
-		}
+	go func(s *subscriber) {
+		s.Channel <- evCopy
 	}(sub)
 }
 
-func ackFunc(s *subscriber, evCopy Event) func() error {
-	return func() error {
-		s.Lock()
-		delete(s.retryMap, evCopy.ID)
-		s.Unlock()
-		return nil
+func (s *subscriber) wake() {
+	select {
+	case s.notify <- struct{}{}:
+	default:
 	}
 }
 
-func nackFunc(_ *subscriber, _ Event) func() error {
-	return func() error {
-		return nil
+func (s *subscriber) dispatchManualAck() {
+	for {
+		s.Lock()
+		for len(s.pending) == 0 {
+			s.Unlock()
+			<-s.notify
+			s.Lock()
+		}
+		ev := s.pending[0]
+		s.pending = s.pending[1:]
+		s.retryMap[ev.ID] = 0
+		s.Unlock()
+
+		s.deliverManualAck(ev)
+	}
+}
+
+func (s *subscriber) deliverManualAck(ev Event) {
+	retries := 0
+	for {
+		if s.retryLimit > -1 && retries > s.retryLimit {
+			if logger.V(logger.ErrorLevel, logger.DefaultLogger) {
+				logger.Errorf("Message retry limit reached, discarding: %v %d %d", ev.ID, retries, s.retryLimit)
+			}
+			s.Lock()
+			delete(s.retryMap, ev.ID)
+			s.Unlock()
+			return
+		}
+
+		result := make(chan bool, 1)
+		evCopy := ev
+		evCopy.SetAckFunc(func() error {
+			select {
+			case result <- true:
+			default:
+			}
+			return nil
+		})
+		evCopy.SetNackFunc(func() error {
+			select {
+			case result <- false:
+			default:
+			}
+			return nil
+		})
+
+		s.Channel <- evCopy
+
+		timer := time.NewTimer(s.ackWait)
+		select {
+		case acked := <-result:
+			if !timer.Stop() {
+				select {
+				case <-timer.C:
+				default:
+				}
+			}
+			if acked {
+				s.Lock()
+				delete(s.retryMap, ev.ID)
+				s.Unlock()
+				return
+			}
+			retries++
+		case <-timer.C:
+			retries++
+		}
+
+		s.Lock()
+		s.retryMap[ev.ID] = retries
+		s.Unlock()
 	}
 }

events/stream_test.go

@@ -157,6 +157,7 @@ func runTestStream(t *testing.T, stream Stream) {
 		assert.NoError(t, err, "Unexpected error subscribing")
 		assert.NoError(t, stream.Publish("foobarAck", map[string]string{"foo": "message 1"}))
 		assert.NoError(t, stream.Publish("foobarAck", map[string]string{"foo": "message 2"}))
+		assert.NoError(t, stream.Publish("foobarAck", map[string]string{"foo": "message 3"}))
 
 		ev := <-ch
 		ev.Ack()
@@ -170,6 +171,13 @@ func runTestStream(t *testing.T, stream Stream) {
 		case <-time.After(7 * time.Second):
 			t.Fatalf("Timed out waiting for message to be put back on queue")
 		}
+		select {
+		case ev = <-ch:
+			assert.NotEqual(t, ev.ID, nacked, "Queued message should only be received after the nacked message is redelivered")
+			assert.NoError(t, ev.Ack())
+		case <-time.After(7 * time.Second):
+			t.Fatalf("Timed out waiting for queued message")
+		}
 
 	})
 

examples/INDEX.md

@@ -0,0 +1,46 @@
+# Examples wayfinding
+
+Use this index when you want the shortest path from a first runnable agent to the
+next services, agents, workflows, and interop examples. Every command below is
+provider-free unless the example README says otherwise.
+
+## Pick by goal
+
+| Goal | Start here | Run or verify | Then try |
+|------|------------|---------------|----------|
+| Run the smallest no-secret agent | [`first-agent`](./first-agent/) | `go run ./examples/first-agent` | [`agent-demo`](./agent-demo/) for a larger service-backed agent |
+| Prove the maintained 0→hero path | [`support`](./support/) | `go run ./examples/support` and `go test ./examples/support` | [`zero-to-hero` guide](../internal/website/docs/guides/zero-to-hero.md) |
+| See planning and delegation | [`agent-plan-delegate`](./agent-plan-delegate/) | `go run ./examples/agent-plan-delegate` | [`plan-delegate` guide](../internal/website/docs/guides/plan-delegate.md) |
+| Expose services through MCP | [`mcp/hello`](./mcp/hello/) | follow [`mcp`](./mcp/) setup | [`mcp/crud`](./mcp/crud/) and [`mcp/workflow`](./mcp/workflow/) |
+| Try A2A or gRPC interop next | [`agent-demo`](./agent-demo/) plus gateway docs | run the example, then use the gateway docs | [`grpc-interop`](./grpc-interop/) |
+| Add workflow durability | [`flow-durable`](./flow-durable/) | `go run ./examples/flow-durable` | [`flow-loop`](./flow-loop/) |
+
+## Recommended adoption path
+
+1. **First service:** run [`hello-world`](./hello-world/) to learn service
+   registration, handlers, client calls, and health checks.
+2. **First agent:** run [`first-agent`](./first-agent/) with
+   `go run ./examples/first-agent`; it uses a deterministic mock model and needs
+   no provider key.
+3. **0→hero reference:** run [`support`](./support/) with
+   `go run ./examples/support`; it keeps typed services, an agent chat loop, an
+   event-driven flow, and an approval gate in one maintained example.
+4. **Interop next:** use [`mcp/hello`](./mcp/hello/), [`mcp/crud`](./mcp/crud/),
+   and [`mcp/workflow`](./mcp/workflow/) when you are ready to expose tools to
+   external AI clients.
+5. **Workflow depth:** use [`flow-durable`](./flow-durable/) once the agent path
+   needs checkpointed, resumable deterministic work.
+
+## CLI wayfinding
+
+The installed CLI prints the same path:
+
+```bash
+micro examples
+micro agent demo
+micro zero-to-hero
+```
+
+Keep this file, [`README.md`](../README.md), and the `micro examples` output in
+sync so new developers can find `examples/first-agent` and `examples/support`
+from one documented path.

examples/README.md

@@ -7,8 +7,8 @@ coordinate work with workflows.
 ## Quick Start
 
 Each example can be run with `go run .` from its directory unless its README says
-otherwise. If you are new to the repo, follow the first-agent path below instead
-of reading the directories alphabetically.
+otherwise. If you are new to the repo, start with the [examples wayfinding index](./INDEX.md)
+or follow the first-agent path below instead of reading the directories alphabetically.
 
 ## Recommended first-agent path
 

examples/first-agent/README.md

@@ -34,5 +34,22 @@ CI keeps this path runnable with:
 go test ./examples/first-agent
 ```
 
-After this, continue to [`examples/support`](../support/) for the full services →
-agents → workflows lifecycle with a flow trigger and an approval gate.
+## Next chat, inspect, and debug breadcrumbs
+
+This example exits after one in-process `assistant.Ask` call so it stays tiny and
+provider-free. When you move from this transcript to a long-running agent, keep
+these commands nearby:
+
+```bash
+micro run
+micro chat assistant --prompt "Summarize my next steps"
+micro inspect agent assistant
+micro agent doctor assistant
+```
+
+Use the [no-secret first-agent guide](../../internal/website/docs/guides/no-secret-first-agent.md)
+to compare this transcript with the CLI demo, then keep the
+[debugging guide](../../internal/website/docs/guides/debugging-agents.md) open for
+preflight, doctor, inspect, and history checks. After that, continue to
+[`examples/support`](../support/) for the full services → agents → workflows
+lifecycle with a flow trigger and an approval gate.

examples/first-agent/main.go

@@ -13,6 +13,7 @@ package main
 import (
 	"context"
 	"fmt"
+	"io"
 	"os"
 	"strings"
 	"time"
@@ -33,13 +34,13 @@ type ListNotesResponse struct {
 	Notes []string `json:"notes" description:"Notes the assistant can summarize"`
 }
 
-type NotesService struct{}
+type NotesService struct{ w io.Writer }
 
 // List returns the starter notes the first agent can read.
 // @example {}
 func (s *NotesService) List(ctx context.Context, req *ListNotesRequest, rsp *ListNotesResponse) error {
 	rsp.Notes = []string{"Install the micro CLI", "Run a service", "Chat with an agent"}
-	fmt.Println("  [notes] listed starter notes")
+	fmt.Fprintln(s.w, "  [notes] listed starter notes")
 	return nil
 }
 
@@ -90,6 +91,10 @@ func waitFor(reg registry.Registry, names ...string) error {
 }
 
 func runFirstAgent() error {
+	return runFirstAgentWithWriter(os.Stdout)
+}
+
+func runFirstAgentWithWriter(w io.Writer) error {
 	ai.Register("first-agent-mock", newMock)
 
 	reg := registry.NewMemoryRegistry()
@@ -104,7 +109,7 @@ func runFirstAgent() error {
 	cl := client.NewClient(client.Registry(reg), client.Selector(selector.NewSelector(selector.Registry(reg))), client.Broker(br))
 
 	notes := service.New(service.Name("notes"), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl), service.Broker(br), service.HandleSignal(false))
-	if err := notes.Handle(new(NotesService)); err != nil {
+	if err := notes.Handle(&NotesService{w: w}); err != nil {
 		return fmt.Errorf("handle notes: %w", err)
 	}
 	svcErr := make(chan error, 1)
@@ -137,14 +142,14 @@ func runFirstAgent() error {
 		return err
 	}
 
-	fmt.Println("First agent (provider: mock, no API key)")
-	fmt.Println("> Summarize my next steps")
+	fmt.Fprintln(w, "First agent (provider: mock, no API key)")
+	fmt.Fprintln(w, "> Summarize my next steps")
 	resp, err := assistant.Ask(context.Background(), "Summarize my next steps")
 	if err != nil {
 		return fmt.Errorf("ask assistant: %w", err)
 	}
-	fmt.Println("assistant:", resp.Reply)
-	fmt.Println("✓ service-backed agent completed without provider secrets")
+	fmt.Fprintln(w, "assistant:", resp.Reply)
+	fmt.Fprintln(w, "✓ service-backed agent completed without provider secrets")
 	return nil
 }
 

examples/first-agent/main_test.go

@@ -1,9 +1,71 @@
 package main
 
-import "testing"
+import (
+	"bytes"
+	"os"
+	"strings"
+	"testing"
+)
 
 func TestRunFirstAgent(t *testing.T) {
-	if err := runFirstAgent(); err != nil {
+	var out bytes.Buffer
+	if err := runFirstAgentWithWriter(&out); err != nil {
 		t.Fatalf("first-agent example failed: %v", err)
 	}
+
+	want := strings.TrimSpace(readExpectedTranscript(t))
+	got := strings.TrimSpace(out.String())
+	if got != want {
+		t.Fatalf("first-agent transcript drifted from README.md\n--- got ---\n%s\n--- want ---\n%s", got, want)
+	}
+}
+
+func TestReadmeDocumentsNextBreadcrumbs(t *testing.T) {
+	b, err := os.ReadFile("README.md")
+	if err != nil {
+		t.Fatalf("read README.md: %v", err)
+	}
+	readme := string(b)
+	start := strings.Index(readme, "## Next chat, inspect, and debug breadcrumbs")
+	if start < 0 {
+		t.Fatal("README.md missing next chat, inspect, and debug breadcrumbs section")
+	}
+	section := readme[start:]
+	for _, want := range []string{
+		"micro run",
+		"micro chat assistant --prompt \"Summarize my next steps\"",
+		"micro inspect agent assistant",
+		"micro agent doctor assistant",
+		"no-secret-first-agent.md",
+		"debugging-agents.md",
+		"examples/support",
+	} {
+		if !strings.Contains(section, want) {
+			t.Fatalf("README.md next breadcrumbs missing %q", want)
+		}
+	}
+}
+
+func readExpectedTranscript(t *testing.T) string {
+	t.Helper()
+	b, err := os.ReadFile("README.md")
+	if err != nil {
+		t.Fatalf("read README.md: %v", err)
+	}
+	readme := string(b)
+	const fence = "```text"
+	start := strings.Index(readme, "Expected transcript:")
+	if start < 0 {
+		t.Fatal("README.md missing Expected transcript section")
+	}
+	fenceStart := strings.Index(readme[start:], fence)
+	if fenceStart < 0 {
+		t.Fatal("README.md missing transcript text fence")
+	}
+	start += fenceStart + len(fence)
+	end := strings.Index(readme[start:], "```")
+	if end < 0 {
+		t.Fatal("README.md missing closing transcript fence")
+	}
+	return readme[start : start+end]
 }

examples/support/README.md

@@ -54,6 +54,32 @@ agent, which:
   emailing a customer (`notify.Send`) passes through the gate first. Return
   `false` to hold it for a person or a policy; the example approves and logs.
 
+## Expected inspect transcript
+
+The provider-free run prints the same visible checkpoints a new developer should
+compare against after chat and flow execution. The transcript includes service
+tool calls, the approval gate, and the inspect/run-history commands that prove
+the workflow run was recorded.
+
+```text
+> event: events.ticket.created {"customer":"alice@acme.com","id":"ticket-1","subject":"Can't log in"}
+
+    [customers] looked up Alice (pro plan)
+    [tickets] ticket-1 → priority=high status=in_progress
+  ▣ approval gate notify_NotifyService_Send(alice@acme.com) — approved
+    [notify] 📨 to=alice@acme.com: "Hi Alice — thanks for reaching out. We've bumped this to high priority and are on it."
+
+support agent: Triaged ticket-1 for Alice and sent a reply.
+
+inspect transcript:
+  micro inspect flow intake
+  flow: intake runs=1 latest.reply="Triaged ticket-1 for Alice and sent a reply."
+  micro agent history support
+  agent: support runs=1 latest.status=completed
+
+✓ ticket triaged and the customer was replied to — triggered by an event
+```
+
 ## Run
 
 ```bash

examples/support/main.go

@@ -302,7 +302,13 @@ func runSupport(provider string) error {
 	}
 
 	if rs := intake.Results(); len(rs) > 0 {
-		fmt.Printf("\n\033[1msupport agent:\033[0m %s\n", rs[len(rs)-1].Reply)
+		latest := rs[len(rs)-1]
+		fmt.Printf("\n\033[1msupport agent:\033[0m %s\n", latest.Reply)
+		fmt.Println("\n\033[1minspect transcript:\033[0m")
+		fmt.Println("  micro inspect flow intake")
+		fmt.Printf("  flow: intake runs=%d latest.reply=%q\n", len(rs), latest.Reply)
+		fmt.Println("  micro agent history support")
+		fmt.Printf("  agent: support runs=%d latest.status=completed\n", len(rs))
 	}
 	if notify.sent >= 1 {
 		fmt.Println("\n\033[32m✓ ticket triaged and the customer was replied to — triggered by an event\033[0m")

examples/support/main_test.go

@@ -1,7 +1,10 @@
 package main
 
 import (
+	"bytes"
+	"io"
 	"os"
+	"regexp"
 	"strings"
 	"testing"
 )
@@ -30,3 +33,78 @@ func TestZeroToHeroReadmeDocumentsLifecycle(t *testing.T) {
 		}
 	}
 }
+
+func TestZeroToHeroInspectTranscript(t *testing.T) {
+	out := captureStdout(t, func() {
+		if err := runSupport("mock"); err != nil {
+			t.Fatalf("support example failed: %v", err)
+		}
+	})
+	got := stripANSI(out)
+
+	for _, want := range []string{
+		`> event: events.ticket.created {"customer":"alice@acme.com","id":"ticket-1","subject":"Can't log in"}`,
+		`[customers] looked up Alice (pro plan)`,
+		`[tickets] ticket-1 → priority=high status=in_progress`,
+		`approval gate notify_NotifyService_Send(alice@acme.com) — approved`,
+		`[notify] 📨 to=alice@acme.com: "Hi Alice — thanks for reaching out. We've bumped this to high priority and are on it."`,
+		`support agent: Triaged ticket-1 for Alice and sent a reply.`,
+		`inspect transcript:`,
+		`micro inspect flow intake`,
+		`flow: intake runs=1 latest.reply="Triaged ticket-1 for Alice and sent a reply."`,
+		`micro agent history support`,
+		`agent: support runs=1 latest.status=completed`,
+		`✓ ticket triaged and the customer was replied to — triggered by an event`,
+	} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("support transcript missing %q\n--- got ---\n%s", want, got)
+		}
+	}
+
+	readme, err := os.ReadFile("README.md")
+	if err != nil {
+		t.Fatalf("read README.md: %v", err)
+	}
+	for _, want := range []string{
+		"Expected inspect transcript",
+		"micro inspect flow intake",
+		"micro agent history support",
+		"agent: support runs=1 latest.status=completed",
+	} {
+		if !strings.Contains(string(readme), want) {
+			t.Fatalf("README.md missing transcript contract %q", want)
+		}
+	}
+}
+
+func captureStdout(t *testing.T, fn func()) (out string) {
+	t.Helper()
+	old := os.Stdout
+	r, w, err := os.Pipe()
+	if err != nil {
+		t.Fatalf("capture stdout: %v", err)
+	}
+	os.Stdout = w
+
+	var buf bytes.Buffer
+	done := make(chan struct{})
+	go func() {
+		_, _ = io.Copy(&buf, r)
+		close(done)
+	}()
+	defer func() {
+		_ = w.Close()
+		os.Stdout = old
+		<-done
+		out = buf.String()
+	}()
+
+	fn()
+	return out
+}
+
+var ansiRE = regexp.MustCompile(`\x1b\[[0-9;]*m`)
+
+func stripANSI(s string) string {
+	return ansiRE.ReplaceAllString(s, "")
+}

gateway/a2a/a2a.go

@@ -627,6 +627,9 @@ func (d *dispatcher) run(ctx context.Context, params json.RawMessage, invoke Inv
 			reply = err.Error()
 			state = stateInputRequired
 		}
+	} else if strings.TrimSpace(reply) == "" {
+		reply = "error: agent returned an empty response"
+		state = stateFailed
 	}
 	task := d.taskFromReply(p.Message, reply, state)
 	d.store(task)
@@ -750,13 +753,11 @@ func (g *Gateway) callAgent(ctx context.Context, name, message string) (string,
 	if err := g.opts.Client.Call(ctx, req, &rsp); err != nil {
 		return "", err
 	}
-	var out struct {
-		Reply string `json:"reply"`
-	}
-	if err := json.Unmarshal(rsp.Data, &out); err != nil {
+	reply, err := decodeAgentChatReply(rsp.Data)
+	if err != nil {
 		return "", err
 	}
-	return out.Reply, nil
+	return reply, nil
 }
 
 // ---------------------------------------------------------------------------
@@ -976,6 +977,35 @@ func textArtifact(text string) Artifact {
 	}
 }
 
+func decodeAgentChatReply(data []byte) (string, error) {
+	var out struct {
+		Reply   string `json:"reply"`
+		Answer  string `json:"answer"`
+		Content string `json:"content"`
+		Text    string `json:"text"`
+		Message struct {
+			Content string `json:"content"`
+			Text    string `json:"text"`
+		} `json:"message"`
+	}
+	if err := json.Unmarshal(data, &out); err != nil {
+		return "", err
+	}
+	for _, candidate := range []string{
+		out.Reply,
+		out.Answer,
+		out.Content,
+		out.Text,
+		out.Message.Content,
+		out.Message.Text,
+	} {
+		if strings.TrimSpace(candidate) != "" {
+			return candidate, nil
+		}
+	}
+	return "", nil
+}
+
 // requestContext carries request cancellation and deadlines into the downstream
 // agent call without leaking HTTP transport context values into the go-micro
 // client stack.

gateway/a2a/a2a_test.go

@@ -523,6 +523,65 @@ func TestMessageStreamChunksFallsBackWhenUnsupported(t *testing.T) {
 	}
 }
 
+func TestMessageStreamFallbackDoesNotCompleteWithEmptyText(t *testing.T) {
+	d := newDispatcher()
+	body := `{"jsonrpc":"2.0","id":1,"method":"message/stream","params":{"message":{"role":"user","parts":[{"kind":"text","text":"ping"}],"kind":"message"}}}`
+	req := httptest.NewRequest(http.MethodPost, "/", bytes.NewBufferString(body))
+	rr := httptest.NewRecorder()
+
+	d.serveWithStream(rr, req, func(context.Context, string) (string, error) {
+		return "", nil
+	}, func(context.Context, string) (ai.Stream, error) {
+		return nil, fmt.Errorf("%w: test provider", ai.ErrStreamingUnsupported)
+	})
+
+	var event struct {
+		Result Task      `json:"result"`
+		Error  *rpcError `json:"error"`
+	}
+	for _, line := range strings.Split(strings.TrimSpace(rr.Body.String()), "\n") {
+		line = strings.TrimSpace(strings.TrimPrefix(strings.TrimSpace(line), "data: "))
+		if line == "" {
+			continue
+		}
+		if err := json.Unmarshal([]byte(line), &event); err != nil {
+			t.Fatalf("decode event %q: %v", line, err)
+		}
+	}
+	if event.Error != nil {
+		t.Fatalf("fallback event error: %+v", event.Error)
+	}
+	if event.Result.Status.State != stateFailed {
+		t.Fatalf("fallback state = %q, want failed", event.Result.Status.State)
+	}
+	if got := textOf(event.Result.Artifacts[0].Parts); got == "" {
+		t.Fatalf("fallback artifact text is empty: %+v", event.Result.Artifacts)
+	}
+	if got := textOf(event.Result.History[len(event.Result.History)-1].Parts); got == "" {
+		t.Fatalf("fallback history text is empty: %+v", event.Result.History)
+	}
+}
+
+func TestDecodeAgentChatReplyFallsBackToProviderTextFields(t *testing.T) {
+	for name, body := range map[string]string{
+		"answer":          `{"answer":"answer text"}`,
+		"content":         `{"content":"content text"}`,
+		"text":            `{"text":"text field"}`,
+		"message_content": `{"message":{"content":"message content"}}`,
+		"message_text":    `{"message":{"text":"message text"}}`,
+	} {
+		t.Run(name, func(t *testing.T) {
+			got, err := decodeAgentChatReply([]byte(body))
+			if err != nil {
+				t.Fatalf("decodeAgentChatReply error: %v", err)
+			}
+			if strings.TrimSpace(got) == "" {
+				t.Fatalf("decodeAgentChatReply(%s) returned empty text", body)
+			}
+		})
+	}
+}
+
 func TestTasksResubscribeStreamsCurrentAndSubsequentEvents(t *testing.T) {
 	d := newDispatcher()
 	initial := &Task{ID: "task-1", ContextID: "ctx-1", Kind: "task", Status: TaskStatus{State: stateWorking, Timestamp: time.Now().UTC().Format(time.RFC3339)}}

go.mod

@@ -1,8 +1,8 @@
 module go-micro.dev/v6
 
-go 1.24
+go 1.25.0
 
-toolchain go1.24.1
+toolchain go1.25.12
 
 require (
 	dario.cat/mergo v1.0.2
@@ -32,24 +32,23 @@ require (
 	github.com/prometheus/client_model v0.6.1
 	github.com/rabbitmq/amqp091-go v1.10.0
 	github.com/stretchr/objx v0.5.2
-	github.com/stretchr/testify v1.10.0
+	github.com/stretchr/testify v1.11.1
 	github.com/test-go/testify v1.1.4
 	github.com/urfave/cli/v2 v2.27.6
 	github.com/xlab/treeprint v1.2.0
 	go.etcd.io/bbolt v1.4.0
 	go.etcd.io/etcd/api/v3 v3.5.21
 	go.etcd.io/etcd/client/v3 v3.5.21
-	go.opentelemetry.io/otel v1.35.0
-	go.opentelemetry.io/otel/sdk v1.35.0
-	go.opentelemetry.io/otel/trace v1.35.0
+	go.opentelemetry.io/otel v1.39.0
+	go.opentelemetry.io/otel/sdk v1.39.0
+	go.opentelemetry.io/otel/trace v1.39.0
 	go.uber.org/zap v1.27.0
-	golang.org/x/crypto v0.37.0
-	golang.org/x/net v0.38.0
-	golang.org/x/sync v0.13.0
-	google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463
-	google.golang.org/grpc v1.71.1
+	golang.org/x/crypto v0.51.0
+	golang.org/x/net v0.55.0
+	golang.org/x/sync v0.20.0
+	google.golang.org/grpc v1.79.3
 	google.golang.org/grpc/examples v0.0.0-20250515150734-f2d3e11f3057
-	google.golang.org/protobuf v1.36.6
+	google.golang.org/protobuf v1.36.10
 )
 
 require (
@@ -63,7 +62,7 @@ require (
 	github.com/cpuguy83/go-md2man/v2 v2.0.5 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/fatih/color v1.16.0 // indirect
-	github.com/go-logr/logr v1.4.2 // indirect
+	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/google/go-tpm v0.9.3 // indirect
@@ -97,19 +96,20 @@ require (
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/common v0.63.0 // indirect
 	github.com/prometheus/procfs v0.16.0 // indirect
-	github.com/rogpeppe/go-internal v1.13.1 // indirect
+	github.com/rogpeppe/go-internal v1.14.1 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 // indirect
 	go.etcd.io/etcd/client/pkg/v3 v3.5.21 // indirect
-	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
-	go.opentelemetry.io/otel/metric v1.35.0 // indirect
+	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
+	go.opentelemetry.io/otel/metric v1.39.0 // indirect
 	go.uber.org/multierr v1.10.0 // indirect
 	golang.org/x/exp v0.0.0-20250305212735-054e65f0b394 // indirect
-	golang.org/x/mod v0.24.0 // indirect
-	golang.org/x/sys v0.32.0 // indirect
-	golang.org/x/text v0.24.0 // indirect
+	golang.org/x/mod v0.35.0 // indirect
+	golang.org/x/sys v0.45.0 // indirect
+	golang.org/x/text v0.37.0 // indirect
 	golang.org/x/time v0.11.0 // indirect
-	golang.org/x/tools v0.31.0 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 // indirect
+	golang.org/x/tools v0.44.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20251202230838-ff82c1b0f217 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -65,8 +65,8 @@ github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9
 github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
 github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
-github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
-github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
+github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
 github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
 github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-redis/redis/v8 v8.11.5 h1:AcZZR7igkdvfVmQTPnu9WE37LRrO/YrBH5zWyjDC0oI=
@@ -317,8 +317,8 @@ github.com/rabbitmq/amqp091-go v1.10.0 h1:STpn5XsHlHGcecLmMFCtg7mqq0RnD+zFr4uzuk
 github.com/rabbitmq/amqp091-go v1.10.0/go.mod h1:Hy4jKW5kQART1u+JkDTF9YYOQUHXqMuhrgxOEeS7G4o=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
-github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII=
-github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o=
+github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
+github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
 github.com/rs/xid v1.2.1/go.mod h1:+uKXf+4Djp6Md1KODXJxgGQPKngRmWyn10oCKFzNHOQ=
 github.com/rs/zerolog v1.13.0/go.mod h1:YbFCdg8HfsridGWAh22vktObvhZbQsZXe4/zB0OKkWU=
 github.com/rs/zerolog v1.15.0/go.mod h1:xYTKnLHcpfU2225ny5qZjxnj9NvkumZYjJHlAThCjNc=
@@ -345,8 +345,8 @@ github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81P
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.2/go.mod h1:R6va5+xMeoiuVRoj+gSkQ7d3FALtqAAGI1FQKckRals=
-github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
-github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 github.com/test-go/testify v1.1.4 h1:Tf9lntrKUMHiXQ07qBScBTSA0dhYQlu83hswqelv1iE=
 github.com/test-go/testify v1.1.4/go.mod h1:rH7cfJo/47vWGdi4GPj16x3/t1xGOj2YxzmNQzk2ghU=
 github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926/go.mod h1:9ESjWnEqriFuLhtthL60Sar/7RFoluCcXsuvEwTV5KM=
@@ -368,18 +368,18 @@ go.etcd.io/etcd/client/pkg/v3 v3.5.21 h1:lPBu71Y7osQmzlflM9OfeIV2JlmpBjqBNlLtcoB
 go.etcd.io/etcd/client/pkg/v3 v3.5.21/go.mod h1:BgqT/IXPjK9NkeSDjbzwsHySX3yIle2+ndz28nVsjUs=
 go.etcd.io/etcd/client/v3 v3.5.21 h1:T6b1Ow6fNjOLOtM0xSoKNQt1ASPCLWrF9XMHcH9pEyY=
 go.etcd.io/etcd/client/v3 v3.5.21/go.mod h1:mFYy67IOqmbRf/kRUvsHixzo3iG+1OF2W2+jVIQRAnU=
-go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
-go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
-go.opentelemetry.io/otel v1.35.0 h1:xKWKPxrxB6OtMCbmMY021CqC45J+3Onta9MqjhnusiQ=
-go.opentelemetry.io/otel v1.35.0/go.mod h1:UEqy8Zp11hpkUrL73gSlELM0DupHoiq72dR+Zqel/+Y=
-go.opentelemetry.io/otel/metric v1.35.0 h1:0znxYu2SNyuMSQT4Y9WDWej0VpcsxkuklLa4/siN90M=
-go.opentelemetry.io/otel/metric v1.35.0/go.mod h1:nKVFgxBZ2fReX6IlyW28MgZojkoAkJGaE8CpgeAU3oE=
-go.opentelemetry.io/otel/sdk v1.35.0 h1:iPctf8iprVySXSKJffSS79eOjl9pvxV9ZqOWT0QejKY=
-go.opentelemetry.io/otel/sdk v1.35.0/go.mod h1:+ga1bZliga3DxJ3CQGg3updiaAJoNECOgJREo9KHGQg=
-go.opentelemetry.io/otel/sdk/metric v1.35.0 h1:1RriWBmCKgkeHEhM7a2uMjMUfP7MsOF5JpUCaEqEI9o=
-go.opentelemetry.io/otel/sdk/metric v1.35.0/go.mod h1:is6XYCUMpcKi+ZsOvfluY5YstFnhW0BidkR+gL+qN+w=
-go.opentelemetry.io/otel/trace v1.35.0 h1:dPpEfJu1sDIqruz7BHFG3c7528f6ddfSWfFDVt/xgMs=
-go.opentelemetry.io/otel/trace v1.35.0/go.mod h1:WUk7DtFp1Aw2MkvqGdwiXYDZZNvA/1J8o6xRXLrIkyc=
+go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=
+go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
+go.opentelemetry.io/otel v1.39.0 h1:8yPrr/S0ND9QEfTfdP9V+SiwT4E0G7Y5MO7p85nis48=
+go.opentelemetry.io/otel v1.39.0/go.mod h1:kLlFTywNWrFyEdH0oj2xK0bFYZtHRYUdv1NklR/tgc8=
+go.opentelemetry.io/otel/metric v1.39.0 h1:d1UzonvEZriVfpNKEVmHXbdf909uGTOQjA0HF0Ls5Q0=
+go.opentelemetry.io/otel/metric v1.39.0/go.mod h1:jrZSWL33sD7bBxg1xjrqyDjnuzTUB0x1nBERXd7Ftcs=
+go.opentelemetry.io/otel/sdk v1.39.0 h1:nMLYcjVsvdui1B/4FRkwjzoRVsMK8uL/cj0OyhKzt18=
+go.opentelemetry.io/otel/sdk v1.39.0/go.mod h1:vDojkC4/jsTJsE+kh+LXYQlbL8CgrEcwmt1ENZszdJE=
+go.opentelemetry.io/otel/sdk/metric v1.39.0 h1:cXMVVFVgsIf2YL6QkRF4Urbr/aMInf+2WKg+sEJTtB8=
+go.opentelemetry.io/otel/sdk/metric v1.39.0/go.mod h1:xq9HEVH7qeX69/JnwEfp6fVq5wosJsY1mt4lLfYdVew=
+go.opentelemetry.io/otel/trace v1.39.0 h1:2d2vfpEDmCJ5zVYz7ijaJdOF59xLomrvj7bjt6/qCJI=
+go.opentelemetry.io/otel/trace v1.39.0/go.mod h1:88w4/PnZSazkGzz/w84VHpQafiU4EtqqlVdxWy+rNOA=
 go.uber.org/atomic v1.3.2/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
 go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
 go.uber.org/atomic v1.5.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
@@ -408,8 +408,8 @@ golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPh
 golang.org/x/crypto v0.0.0-20201203163018-be400aefbc4c/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
 golang.org/x/crypto v0.0.0-20210616213533-5ff15b29337e/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.37.0 h1:kJNSjF/Xp7kU0iB2Z+9viTPMW4EqqsrywMXLJOOsXSE=
-golang.org/x/crypto v0.37.0/go.mod h1:vg+k43peMZ0pUMhYmVAWysMK35e6ioLh3wB8ZCAfbVc=
+golang.org/x/crypto v0.51.0 h1:IBPXwPfKxY7cWQZ38ZCIRPI50YLeevDLlLnyC5wRGTI=
+golang.org/x/crypto v0.51.0/go.mod h1:8AdwkbraGNABw2kOX6YFPs3WM22XqI4EXEd8g+x7Oc8=
 golang.org/x/exp v0.0.0-20250305212735-054e65f0b394 h1:nDVHiLt8aIbd/VzvPWN6kSOPE7+F/fNFDSXLVYkE/Iw=
 golang.org/x/exp v0.0.0-20250305212735-054e65f0b394/go.mod h1:sIifuuw/Yco/y6yb6+bDNfyeQ/MdPUy/hKEMYQV17cM=
 golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
@@ -418,8 +418,8 @@ golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzB
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.24.0 h1:ZfthKaKaT4NrhGVZHO1/WDTwGES4De8KtWO0SIbNJMU=
-golang.org/x/mod v0.24.0/go.mod h1:IXM97Txy2VM4PJ3gI61r1YEk/gAj6zAHN3AdZt6S9Ww=
+golang.org/x/mod v0.35.0 h1:Ww1D637e6Pg+Zb2KrWfHQUnH2dQRLBQyAtpr/haaJeM=
+golang.org/x/mod v0.35.0/go.mod h1:+GwiRhIInF8wPm+4AoT6L0FA1QWAad3OMdTRx4tFYlU=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
@@ -433,16 +433,16 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1/go.mod h1:9tjilg8BloeKEkVJvy7fQ90B1CfIiPueXVOjqfkSzI8=
 golang.org/x/net v0.0.0-20210726213435-c6fcb2dbf985/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
-golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/net v0.55.0 h1:bcvxaJn3e1U6InsFWt1JUq1aSjnRxLzT2rtD2KfkDF8=
+golang.org/x/net v0.55.0/go.mod h1:L5U2KuzuOe1lY7Z+aWVIKK6qEeJXnXV9yzGA+WCHJww=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.13.0 h1:AauUjRAJ9OSnvULf/ARrrVywoJDy0YS2AwQ98I37610=
-golang.org/x/sync v0.13.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
+golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
 golang.org/x/sys v0.0.0-20180823144017-11551d06cbcc/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -473,8 +473,8 @@ golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.32.0 h1:s77OFDvIQeibCmezSnk/q6iAfkdiQaJi4VzroCFrN20=
-golang.org/x/sys v0.32.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY=
+golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -482,8 +482,8 @@ golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.24.0 h1:dd5Bzh4yt5KYA8f9CJHCP4FB4D51c2c6JvN37xJJkJ0=
-golang.org/x/text v0.24.0/go.mod h1:L8rBsPeo2pSS+xqN0d5u2ikmjtmoJbDBT1b7nHvFCdU=
+golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
+golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
 golang.org/x/time v0.11.0 h1:/bpjEDfN9tkoN/ryeYHnv5hcMlc8ncjMcM4XBk5NWV0=
 golang.org/x/time v0.11.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -499,24 +499,26 @@ golang.org/x/tools v0.0.0-20200103221440-774c71fcf114/go.mod h1:TB2adYChydJhpapK
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.6-0.20210726203631-07bc1bf47fb2/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
-golang.org/x/tools v0.31.0 h1:0EedkvKDbh+qistFTd0Bcwe/YLh4vHwWEkiI0toFIBU=
-golang.org/x/tools v0.31.0/go.mod h1:naFTU+Cev749tSJRXJlna0T3WxKvb1kWEx15xA4SdmQ=
+golang.org/x/tools v0.44.0 h1:UP4ajHPIcuMjT1GqzDWRlalUEoY+uzoZKnhOjbIPD2c=
+golang.org/x/tools v0.44.0/go.mod h1:KA0AfVErSdxRZIsOVipbv3rQhVXTnlU6UhKxHd1seDI=
 golang.org/x/xerrors v0.0.0-20190410155217-1f06c39b4373/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20190513163551-3ee3066db522/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 h1:hE3bRWtU6uceqlh4fhrSnUyjKHMKB9KrTLLG+bc0ddM=
-google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463/go.mod h1:U90ffi8eUL9MwPcrJylN5+Mk2v3vuPDptd5yyNUiRR8=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463 h1:e0AIkUUhxyBKh6ssZNrAMeqhA7RKUj42346d1y02i2g=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20250324211829-b45e905df463/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
-google.golang.org/grpc v1.71.1 h1:ffsFWr7ygTUscGPI0KKK6TLrGz0476KUvvsbqWK0rPI=
-google.golang.org/grpc v1.71.1/go.mod h1:H0GRtasmQOh9LkFoCPDu3ZrwUtD1YGE+b2vYBYd/8Ec=
+gonum.org/v1/gonum v0.16.0 h1:5+ul4Swaf3ESvrOnidPp4GZbzf0mxVQpDCYUQE7OJfk=
+gonum.org/v1/gonum v0.16.0/go.mod h1:fef3am4MQ93R2HHpKnLk4/Tbh/s0+wqD5nfa6Pnwy4E=
+google.golang.org/genproto/googleapis/api v0.0.0-20251202230838-ff82c1b0f217 h1:fCvbg86sFXwdrl5LgVcTEvNC+2txB5mgROGmRL5mrls=
+google.golang.org/genproto/googleapis/api v0.0.0-20251202230838-ff82c1b0f217/go.mod h1:+rXWjjaukWZun3mLfjmVnQi18E1AsFbDN9QdJ5YXLto=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217 h1:gRkg/vSppuSQoDjxyiGfN4Upv/h/DQmIR10ZU8dh4Ww=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20251202230838-ff82c1b0f217/go.mod h1:7i2o+ce6H/6BluujYR+kqX3GKH+dChPTQU19wjRPiGk=
+google.golang.org/grpc v1.79.3 h1:sybAEdRIEtvcD68Gx7dmnwjZKlyfuc61Dyo9pGXXkKE=
+google.golang.org/grpc v1.79.3/go.mod h1:KmT0Kjez+0dde/v2j9vzwoAScgEPx/Bw1CYChhHLrHQ=
 google.golang.org/grpc/examples v0.0.0-20250515150734-f2d3e11f3057 h1:lPv+iqlAyiKMjbL3ivJlAASixPknLv806R6zaoE4PUM=
 google.golang.org/grpc/examples v0.0.0-20250515150734-f2d3e11f3057/go.mod h1:WPWnet+nYurNGpV0rVYHI1YuOJwVHeM3t8f76m410XM=
-google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
-google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
+google.golang.org/protobuf v1.36.10 h1:AYd7cD/uASjIL6Q9LiTjz8JLcrh/88q5UObnmY3aOOE=
+google.golang.org/protobuf v1.36.10/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

internal/docs/AGENT_CONFORMANCE.md

@@ -3,8 +3,11 @@
 `go test ./...` includes `TestAgentProviderConformanceMatrix`, a shared agent
 scenario that runs against every registered chat provider. The scenario asks an
 agent to call a deterministic local tool, verifies the tool receives `ai.RunInfo`,
-and checks the final response carries the conformance marker. A fake provider path
-runs on every machine without network access so CI always exercises the harness.
+and checks the final response carries the conformance marker. The live matrix
+includes MiniMax in the tool/guardrail path in addition to providers with
+streaming coverage, so every supported chat provider has at least one key-gated
+agent contract. A fake provider path runs on every machine without network
+access so CI always exercises the harness.
 
 Live providers are opt-in to avoid flaky unauthenticated PR checks and accidental
 API spend. To run the live matrix, set `GO_MICRO_AGENT_CONFORMANCE_LIVE=1` plus the
@@ -17,6 +20,7 @@ provider API keys you want to exercise:
 | Atlas Cloud | `ATLASCLOUD_API_KEY` | `GO_MICRO_CONFORMANCE_ATLASCLOUD_MODEL` |
 | Gemini | `GEMINI_API_KEY` | `GO_MICRO_CONFORMANCE_GEMINI_MODEL` |
 | Groq | `GROQ_API_KEY` | `GO_MICRO_CONFORMANCE_GROQ_MODEL` |
+| MiniMax | `MINIMAX_API_KEY` | `GO_MICRO_CONFORMANCE_MINIMAX_MODEL` |
 | Mistral | `MISTRAL_API_KEY` | `GO_MICRO_CONFORMANCE_MISTRAL_MODEL` |
 | Together | `TOGETHER_API_KEY` | `GO_MICRO_CONFORMANCE_TOGETHER_MODEL` |
 
@@ -39,11 +43,24 @@ live model credits.
 
 Use `make provider-conformance` when you want the live-provider sweep: providers
 without keys are skipped, and configured providers must satisfy the same harness
-contract.
+contract. For the exact scheduled command, run:
+
+```sh
+go run ./internal/harness/provider-conformance \
+  -providers anthropic,openai,gemini,groq,minimax,mistral,together,atlascloud \
+  -harnesses agent,universe,agent-flow,plan-delegate,a2a-stream-fallback \
+  -summary-json provider-conformance-summary.json \
+  -summary-markdown provider-conformance-summary.md \
+  -capabilities-markdown provider-capabilities.md
+```
+
+The generated summary records one row for every selected provider/harness pair;
+missing live-provider keys become skipped rows for each harness, while configured
+providers produce pass/fail rows per harness.
 
 ## Scheduled CI
 
-The daily/manual `Harness (E2E)` workflow runs the same matrix with
+The hourly/manual `Harness (E2E)` workflow runs the same matrix with
 `GO_MICRO_AGENT_CONFORMANCE_LIVE=1` and the provider secrets exported. Providers
 whose keys are absent still skip cleanly, while any configured provider must pass
 the shared tool-calling scenario. This keeps scheduled conformance key-gated: PR

internal/docs/CONTINUOUS_IMPROVEMENT.md

@@ -21,8 +21,8 @@ Actions instead of subagents. Each role is a workflow:
 |------|------------------------|--------------|
 | **Planner** | `loop-planner.yml` — *Loop: Planner* | Tracks live state, prioritizes the roadmap + an internal scan, and maintains the ranked queue in [`.github/loop/PRIORITIES.md`](../../.github/loop/PRIORITIES.md). Decides *what*. |
 | **Generator** | `loop-builder.yml` — *Loop: Builder (Generator)* | Builds the top open queue item as a single-concern PR (via Codex) and self-merges on green CI. Does the work. |
-| **Evaluator** | `harness.yml` — *Harness (E2E)*, plus the CI gate (`tests.yaml`, `lint.yaml`) | Grades every change: the mock harness + unit/lint on each push/PR, and real-model conformance hourly. A *separate* grader — never the generator judging itself. |
-| **Evaluator → feedback** | `loop-triage.yml` — *Loop: Triage (Evaluator feedback)* | When a gate workflow (Lint, Run Tests, or the harness) fails on a non-PR run, root-causes, dedupes, and files scoped fix issues back into the planner's queue. The hill-climbing feedback path. |
+| **Evaluator** | `harness.yml` — *Harness (E2E)*, plus the CI gate (`tests.yaml`, `lint.yaml`, `govulncheck.yml`) | Grades every change: the mock harness + unit/lint + reachable-CVE scan on each push/PR, and real-model conformance hourly. A *separate* grader — never the generator judging itself. |
+| **Evaluator → feedback** | `loop-triage.yml` — *Loop: Triage (Evaluator feedback)* | When a gate workflow (Lint, Run Tests, govulncheck, or the harness) fails on a non-PR run, root-causes, dedupes, and files scoped fix issues back into the planner's queue. The hill-climbing feedback path. |
 | **Coherence** | `loop-coherence.yml` — *Loop: Coherence* | Keeps README/website/docs/blog aligned with the North Star, keeps `CHANGELOG.md` living (reconciling `[Unreleased]` against merged PRs and rolling it into version headings as tags cut), and drafts the changelog blog post. |
 | **Security** | `loop-security.yml` — *Loop: Security* | Weekly vulnerability audit of the attack surface (MCP/A2A gateways, x402, auth, provider URLs, agent tool loop, deps via `govulncheck`). Files `security` issues; **never auto-merges** fixes and **never publishes exploit detail** in public issues (responsible disclosure); risky fixes are `needs-human`. |
 | **Release** | `loop-release.yml` — *Loop: Release (daily patch)* | Cuts a daily patch tag when master has new commits, so the *installable* framework tracks the loop's improvements (triggers `release.yml`/goreleaser). Minor/major bumps stay with the human. |

internal/harness/agent-flow/main.go

@@ -49,19 +49,31 @@ type CreateResponse struct {
 }
 
 type WorkspaceService struct {
-	mu sync.Mutex
-	n  int
+	mu      sync.Mutex
+	n       int
+	byOwner map[string]*Workspace
 }
 
 // Create provisions a workspace for a new user.
 // @example {"owner": "alice@acme.com"}
 func (s *WorkspaceService) Create(ctx context.Context, req *CreateRequest, rsp *CreateResponse) error {
 	s.mu.Lock()
+	if s.byOwner == nil {
+		s.byOwner = make(map[string]*Workspace)
+	}
+	if ws, ok := s.byOwner[req.Owner]; ok {
+		s.mu.Unlock()
+		fmt.Printf("    \033[32m[workspace]\033[0m duplicate suppressed %s for %s\n", ws.ID, req.Owner)
+		rsp.Workspace = ws
+		return nil
+	}
 	s.n++
 	id := fmt.Sprintf("ws-%d", s.n)
+	ws := &Workspace{ID: id, Owner: req.Owner}
+	s.byOwner[req.Owner] = ws
 	s.mu.Unlock()
 	fmt.Printf("    \033[32m[workspace]\033[0m created %s for %s\n", id, req.Owner)
-	rsp.Workspace = &Workspace{ID: id, Owner: req.Owner}
+	rsp.Workspace = ws
 	return nil
 }
 
@@ -79,14 +91,26 @@ type SendResponse struct {
 	Sent bool `json:"sent"`
 }
 type NotifyService struct {
-	mu sync.Mutex
-	n  int
+	mu   sync.Mutex
+	n    int
+	sent map[string]bool
 }
 
 // Send delivers a notification message to a recipient.
 // @example {"to": "alice@acme.com", "message": "Welcome"}
 func (s *NotifyService) Send(ctx context.Context, req *SendRequest, rsp *SendResponse) error {
+	key := strings.ToLower(strings.TrimSpace(req.To))
 	s.mu.Lock()
+	if s.sent == nil {
+		s.sent = make(map[string]bool)
+	}
+	if s.sent[key] {
+		s.mu.Unlock()
+		fmt.Printf("    \033[35m[notify]\033[0m duplicate suppressed to=%s message=%q\n", req.To, req.Message)
+		rsp.Sent = true
+		return nil
+	}
+	s.sent[key] = true
 	s.n++
 	s.mu.Unlock()
 	fmt.Printf("    \033[35m[notify]\033[0m 📨 to=%s message=%q\n", req.To, req.Message)
@@ -178,6 +202,31 @@ func waitFor(reg registry.Registry, name string) {
 	}
 }
 
+func waitForOnboardingSideEffects(ctx context.Context, wsSvc *WorkspaceService, ntSvc *NotifyService, recoverMissingNotify func(context.Context) error) error {
+	ticker := time.NewTicker(50 * time.Millisecond)
+	defer ticker.Stop()
+
+	recovered := false
+	for {
+		workspaces, notifications := wsSvc.count(), ntSvc.count()
+		if workspaces >= 1 && notifications >= 1 {
+			return nil
+		}
+		if workspaces >= 1 && notifications == 0 && !recovered && recoverMissingNotify != nil {
+			recovered = true
+			if err := recoverMissingNotify(ctx); err != nil {
+				return fmt.Errorf("agent-flow created workspace but failed to recover missing onboarding notification: workspaces=%d/1 notifications=%d/1: %w", workspaces, notifications, err)
+			}
+		}
+
+		select {
+		case <-ctx.Done():
+			return fmt.Errorf("agent-flow missing required onboarding side effects before timeout: workspaces=%d/1 notifications=%d/1", workspaces, notifications)
+		case <-ticker.C:
+		}
+	}
+}
+
 func main() {
 	provider := flag.String("provider", "mock", "LLM provider: mock (default), anthropic, openai, ...")
 	flag.Parse()
@@ -257,20 +306,25 @@ func main() {
 		os.Exit(1)
 	}
 
-	// Wait for the agent to finish acting.
-	deadline := time.Now().Add(30 * time.Second)
-	for time.Now().Before(deadline) {
-		if ntSvc.count() >= 1 && wsSvc.count() >= 1 {
-			break
-		}
-		time.Sleep(50 * time.Millisecond)
-	}
+	// Wait for the agent to finish acting, and fail the harness if the
+	// provider returns a successful reply without the required service side
+	// effects. The 0→hero/provider conformance path must not print success
+	// unless the services → agent → workflow contract actually happened.
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	err := waitForOnboardingSideEffects(ctx, wsSvc, ntSvc, func(ctx context.Context) error {
+		fmt.Print("\n\033[33mwarning:\033[0m workspace exists before notify; retrying the welcome notification once before the flow can complete.\n")
+		_, err := onboarder.Ask(ctx, "The workspace for alice@acme.com already exists. Send exactly one welcome notification to alice@acme.com now. Use the notify service. Do not create another workspace and do not answer until the notification tool call has succeeded.")
+		return err
+	})
+	cancel()
 
 	fmt.Printf("\n\033[1mresult:\033[0m workspaces created=%d, notifications sent=%d\n", wsSvc.count(), ntSvc.count())
 	if rs := f.Results(); len(rs) > 0 {
 		fmt.Printf("flow reply: %s\n", rs[len(rs)-1].Reply)
 	}
-	if wsSvc.count() >= 1 && ntSvc.count() >= 1 {
-		fmt.Println("\n\033[32m✓ the agent onboarded the user — triggered by an event, not a prompt\033[0m")
+	if err != nil {
+		fmt.Printf("\n\033[31m✗ %v\033[0m\n", err)
+		os.Exit(1)
 	}
+	fmt.Println("\n\033[32m✓ the agent onboarded the user — triggered by an event, not a prompt\033[0m")
 }

internal/harness/agent-flow/main_test.go

@@ -1,6 +1,8 @@
 package main
 
 import (
+	"context"
+	"strings"
 	"testing"
 	"time"
 
@@ -99,3 +101,111 @@ func TestEventTriggersAgentNoPrompt(t *testing.T) {
 		t.Errorf("flow recorded no result for the event")
 	}
 }
+
+func TestWaitForOnboardingSideEffectsFailsWhenMissing(t *testing.T) {
+	wsSvc := new(WorkspaceService)
+	ntSvc := new(NotifyService)
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Millisecond)
+	defer cancel()
+
+	err := waitForOnboardingSideEffects(ctx, wsSvc, ntSvc, nil)
+	if err == nil {
+		t.Fatal("waitForOnboardingSideEffects returned nil, want missing side effects error")
+	}
+	if got := err.Error(); !strings.Contains(got, "workspaces=0/1") || !strings.Contains(got, "notifications=0/1") {
+		t.Fatalf("waitForOnboardingSideEffects error %q does not report missing side effects", got)
+	}
+}
+
+func TestWaitForOnboardingSideEffectsPassesWhenComplete(t *testing.T) {
+	wsSvc := new(WorkspaceService)
+	ntSvc := new(NotifyService)
+
+	if err := wsSvc.Create(context.Background(), &CreateRequest{Owner: "alice@acme.com"}, &CreateResponse{}); err != nil {
+		t.Fatalf("create workspace: %v", err)
+	}
+	if err := ntSvc.Send(context.Background(), &SendRequest{To: "alice@acme.com", Message: "Welcome"}, &SendResponse{}); err != nil {
+		t.Fatalf("send notification: %v", err)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+	if err := waitForOnboardingSideEffects(ctx, wsSvc, ntSvc, nil); err != nil {
+		t.Fatalf("waitForOnboardingSideEffects returned %v, want nil", err)
+	}
+}
+
+func TestWaitForOnboardingSideEffectsRecoversMissingNotification(t *testing.T) {
+	wsSvc := new(WorkspaceService)
+	ntSvc := new(NotifyService)
+
+	if err := wsSvc.Create(context.Background(), &CreateRequest{Owner: "alice@acme.com"}, &CreateResponse{}); err != nil {
+		t.Fatalf("create workspace: %v", err)
+	}
+
+	recovered := false
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+	err := waitForOnboardingSideEffects(ctx, wsSvc, ntSvc, func(ctx context.Context) error {
+		recovered = true
+		return ntSvc.Send(ctx, &SendRequest{To: "alice@acme.com", Message: "Welcome — your workspace is ready."}, &SendResponse{})
+	})
+	if err != nil {
+		t.Fatalf("waitForOnboardingSideEffects returned %v, want recovered notification", err)
+	}
+	if !recovered {
+		t.Fatal("missing notification recovery did not run")
+	}
+	if got := ntSvc.count(); got != 1 {
+		t.Fatalf("notifications sent = %d, want 1 after recovery", got)
+	}
+}
+
+func TestWorkspaceCreateSuppressesDuplicateOwner(t *testing.T) {
+	wsSvc := new(WorkspaceService)
+	first := new(CreateResponse)
+	if err := wsSvc.Create(context.Background(), &CreateRequest{Owner: "alice@acme.com"}, first); err != nil {
+		t.Fatalf("create first workspace: %v", err)
+	}
+	second := new(CreateResponse)
+	if err := wsSvc.Create(context.Background(), &CreateRequest{Owner: "alice@acme.com"}, second); err != nil {
+		t.Fatalf("create duplicate workspace: %v", err)
+	}
+
+	if got := wsSvc.count(); got != 1 {
+		t.Fatalf("workspace creations = %d, want 1 after duplicate owner replay", got)
+	}
+	if first.Workspace == nil || second.Workspace == nil || second.Workspace.ID != first.Workspace.ID {
+		t.Fatalf("duplicate create returned workspace %#v, want original %#v", second.Workspace, first.Workspace)
+	}
+}
+
+func TestNotifySendSuppressesDuplicateMessage(t *testing.T) {
+	ntSvc := new(NotifyService)
+	req := &SendRequest{To: "alice@acme.com", Message: "Welcome — your workspace is ready."}
+	if err := ntSvc.Send(context.Background(), req, &SendResponse{}); err != nil {
+		t.Fatalf("send first notification: %v", err)
+	}
+	if err := ntSvc.Send(context.Background(), req, &SendResponse{}); err != nil {
+		t.Fatalf("send duplicate notification: %v", err)
+	}
+
+	if got := ntSvc.count(); got != 1 {
+		t.Fatalf("notifications sent = %d, want 1 after duplicate message replay", got)
+	}
+}
+
+func TestNotifySendSuppressesDuplicateRecipient(t *testing.T) {
+	ntSvc := new(NotifyService)
+	if err := ntSvc.Send(context.Background(), &SendRequest{To: "Alice@Acme.com", Message: "Welcome — your workspace is ready."}, &SendResponse{}); err != nil {
+		t.Fatalf("send first notification: %v", err)
+	}
+	if err := ntSvc.Send(context.Background(), &SendRequest{To: " alice@acme.com ", Message: "Your workspace is ready."}, &SendResponse{}); err != nil {
+		t.Fatalf("send duplicate recipient notification: %v", err)
+	}
+
+	if got := ntSvc.count(); got != 1 {
+		t.Fatalf("notifications sent = %d, want 1 after duplicate recipient replay", got)
+	}
+}

internal/harness/install-smoke/run.sh

@@ -49,6 +49,34 @@ require_output() {
   fi
 }
 
+require_ordered_output() {
+  local description=$1
+  shift
+  local -a expected=()
+  while [[ $# -gt 0 && "$1" != "--" ]]; do
+    expected+=("$1")
+    shift
+  done
+  shift
+
+  local output
+  if ! output=$("$MICRO" "$@" 2>&1); then
+    echo "micro $* failed while checking $description" >&2
+    echo "$output" >&2
+    exit 1
+  fi
+
+  local remainder=$output
+  for text in "${expected[@]}"; do
+    if [[ "$remainder" != *"$text"* ]]; then
+      echo "micro $* missing expected ordered text '$text' for $description" >&2
+      echo "$output" >&2
+      exit 1
+    fi
+    remainder=${remainder#*"$text"}
+  done
+}
+
 require_output "version" "micro version" --version
 require_output "root help" "COMMANDS" --help
 require_output "service scaffold" "micro new" new --help
@@ -58,4 +86,51 @@ require_output "agent chat" "micro chat" chat --help
 require_output "agent inspection" "micro inspect agent" inspect agent --help
 require_output "flow inspection" "micro inspect flow" inspect flow --help
 
+require_ordered_output "installed first-agent docs wayfinding" \
+  "micro agent demo" \
+  "no-secret-first-agent.html" \
+  "your-first-agent.html" \
+  "micro agent preflight  # before micro run: prerequisites" \
+  "micro run" \
+  "micro chat" \
+  "micro agent doctor     # after micro run: chat/gateway/inspect recovery" \
+  "debugging-agents.html" \
+  "micro inspect agent <name>" \
+  "zero-to-hero.html" \
+  -- docs
+
+require_ordered_output "installed provider-free examples wayfinding" \
+  "go run ./examples/first-agent" \
+  "go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1" \
+  "go run ./examples/support" \
+  "micro agent demo" \
+  "micro docs" \
+  "micro zero-to-hero" \
+  "no-secret-first-agent.html" \
+  "your-first-agent.html" \
+  "debugging-agents.html" \
+  "zero-to-hero.html" \
+  -- examples
+
+require_ordered_output "installed no-secret agent demo" \
+  "provider-free" \
+  "go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentTranscript -count=1" \
+  "your-first-agent.html" \
+  "debugging-agents.html" \
+  "zero-to-hero.html" \
+  "micro agent preflight  # before micro run: prerequisites" \
+  "micro run" \
+  "micro chat" \
+  "micro agent doctor     # after micro run: chat/gateway/inspect recovery" \
+  "micro inspect agent <name>" \
+  -- agent demo
+
+require_ordered_output "installed zero-to-hero lifecycle wayfinding" \
+  "./internal/harness/zero-to-hero-ci/run.sh" \
+  "go run ./examples/first-agent" \
+  "go run ./examples/support" \
+  "make harness" \
+  "zero-to-hero.html" \
+  -- zero-to-hero
+
 echo "✓ install smoke path verified"

internal/harness/plan-delegate/main.go

@@ -157,7 +157,7 @@ func (s *NotifyService) Send(ctx context.Context, req *SendRequest, rsp *SendRes
 	if s.bySend == nil {
 		s.bySend = map[string]bool{}
 	}
-	key := strings.ToLower(strings.TrimSpace(req.To)) + "\x00" + strings.ToLower(strings.TrimSpace(req.Message))
+	key := notifyDedupKey(req.To, req.Message)
 	s.attempts++
 	if !s.bySend[key] {
 		s.bySend[key] = true
@@ -184,6 +184,66 @@ func (s *NotifyService) duplicateAttempts() int {
 	return s.duplicates
 }
 
+func notifyDedupKey(to, message string) string {
+	recipient := canonicalLaunchNotifyRecipient(normalizeNotifyText(to))
+	body := normalizeNotifyText(message)
+	if recipient == "owner@acme.com" && isLaunchReadinessNotify(body) {
+		body = "launch-readiness"
+	}
+	return recipient + "\x00" + body
+}
+
+func canonicalLaunchNotifyRecipient(recipient string) string {
+	recipient = canonicalSpokenEmailRecipient(recipient)
+	switch recipient {
+	case "owner", "launch owner", "plan owner", "owner acme com", "owner@acme com", "owner @ acme com":
+		return "owner@acme.com"
+	default:
+		if strings.Contains(recipient, "owner") && strings.Contains(recipient, "acme") {
+			return "owner@acme.com"
+		}
+		return recipient
+	}
+}
+
+func canonicalSpokenEmailRecipient(recipient string) string {
+	fields := strings.Fields(recipient)
+	if len(fields) == 5 && fields[1] == "at" && fields[3] == "dot" {
+		return fields[0] + "@" + fields[2] + "." + fields[4]
+	}
+	return recipient
+}
+
+func normalizeNotifyText(message string) string {
+	message = strings.ToLower(strings.TrimSpace(message))
+	message = strings.Map(func(r rune) rune {
+		switch {
+		case r >= 'a' && r <= 'z', r >= '0' && r <= '9':
+			return r
+		case r == '@':
+			return r
+		default:
+			return ' '
+		}
+	}, message)
+	return strings.Join(strings.Fields(message), " ")
+}
+
+func isLaunchReadinessNotify(message string) bool {
+	hasLaunch := strings.Contains(message, "launch")
+	hasPlanOrReadiness := strings.Contains(message, "plan") ||
+		strings.Contains(message, "readiness") ||
+		strings.Contains(message, "ready")
+	hasCompletion := strings.Contains(message, "ready") ||
+		strings.Contains(message, "readiness") ||
+		strings.Contains(message, "prepared") ||
+		strings.Contains(message, "complete") ||
+		strings.Contains(message, "finished") ||
+		strings.Contains(message, "done") ||
+		strings.Contains(message, "sent")
+	return hasLaunch && hasPlanOrReadiness && hasCompletion
+}
+
 // ---------------------------------------------------------------------------
 // mock LLM provider — the ONLY fake. It "reasons" by simple heuristics
 // over the tools it's offered and the system prompt it's given, calling
@@ -199,6 +259,15 @@ type mockModel struct {
 	// still keeping the regression deterministic and keyless.
 	unknownDelegateOnce    bool
 	emittedUnknownDelegate bool
+
+	// duplicateNotify makes the comms mock replay the same notification call.
+	// The notify service should collapse that replay to one durable side effect.
+	duplicateNotify bool
+
+	// duplicateDelegate makes the conductor mock replay the same delegate call.
+	// The delegate idempotency path should collapse that replay before it can
+	// ask the delegated comms agent to notify twice.
+	duplicateDelegate bool
 }
 
 func newMock(opts ...ai.Option) ai.Model {
@@ -213,6 +282,18 @@ func newMockUnknownDelegate(opts ...ai.Option) ai.Model {
 	return m
 }
 
+func newMockDuplicateNotify(opts ...ai.Option) ai.Model {
+	m := &mockModel{duplicateNotify: true}
+	_ = m.Init(opts...)
+	return m
+}
+
+func newMockDuplicateDelegate(opts ...ai.Option) ai.Model {
+	m := &mockModel{duplicateDelegate: true}
+	_ = m.Init(opts...)
+	return m
+}
+
 func (m *mockModel) Init(opts ...ai.Option) error {
 	for _, o := range opts {
 		o(&m.opts)
@@ -254,10 +335,14 @@ func (m *mockModel) Generate(ctx context.Context, req *ai.Request, _ ...ai.Gener
 	// comms agent: owns notify, has Send but not Add.
 	case hasSend && !hasAdd:
 		send := findTool(req.Tools, "Send")
-		m.call("comms", send, map[string]any{
+		input := map[string]any{
 			"to":      "owner@acme.com",
 			"message": "The launch plan is ready",
-		})
+		}
+		m.call("comms", send, input)
+		if m.duplicateNotify {
+			m.call("comms", send, input)
+		}
 		return &ai.Response{Answer: "Notified owner@acme.com."}, nil
 
 	// conductor: has the task Add tool — plan, create tasks, delegate.
@@ -285,10 +370,14 @@ func (m *mockModel) Generate(ctx context.Context, req *ai.Request, _ ...ai.Gener
 					"to":   "comms",
 				})
 			} else {
-				m.call("conductor", del, map[string]any{
+				input := map[string]any{
 					"task": delegatedNotifyTask,
 					"to":   "comms",
-				})
+				}
+				m.call("conductor", del, input)
+				if m.duplicateDelegate {
+					m.call("conductor", del, input)
+				}
 			}
 		}
 		return &ai.Response{Answer: "Created Design, Build and Ship, and had comms notify the owner."}, nil
@@ -322,6 +411,10 @@ func runPlanDelegate(provider string) error {
 		ai.Register("mock", newMock)
 	case "mock-unknown-delegate":
 		ai.Register("mock-unknown-delegate", newMockUnknownDelegate)
+	case "mock-duplicate-notify":
+		ai.Register("mock-duplicate-notify", newMockDuplicateNotify)
+	case "mock-duplicate-delegate":
+		ai.Register("mock-duplicate-delegate", newMockDuplicateDelegate)
 	default:
 		apiKey = providerKey(provider)
 		if apiKey == "" {
@@ -346,14 +439,20 @@ func runPlanDelegate(provider string) error {
 	if err := task.Handle(taskSvc); err != nil {
 		return fmt.Errorf("task handle: %w", err)
 	}
-	go task.Run()
+	if err := task.Start(); err != nil {
+		return fmt.Errorf("task start: %w", err)
+	}
+	defer task.Stop()
 
 	notifySvc := new(NotifyService)
 	notify := service.New(service.Name("notify"), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl))
 	if err := notify.Handle(notifySvc); err != nil {
 		return fmt.Errorf("notify handle: %w", err)
 	}
-	go notify.Run()
+	if err := notify.Start(); err != nil {
+		return fmt.Errorf("notify start: %w", err)
+	}
+	defer notify.Stop()
 
 	// Real comms agent (owns notify), registered so delegate reaches it over RPC.
 	commsOpts := []agent.Option{
@@ -375,10 +474,11 @@ func runPlanDelegate(provider string) error {
 		agent.Name("conductor"),
 		agent.Address("127.0.0.1:0"),
 		agent.Services("task"),
-		agent.Prompt("You coordinate launch work. Plan first, create exactly one Design task, one Build task, and one Ship task, then delegate exactly one readiness notification to the \"comms\" agent. Do not create duplicate tasks and do not send notifications yourself."),
+		agent.Prompt("You coordinate launch work. Before any task or delegate tool call, you must persist the launch-readiness plan with the built-in plan tool. Then create exactly one Design task, one Build task, and one Ship task, then delegate exactly one readiness notification to the \"comms\" agent. Do not create duplicate tasks and do not send notifications yourself."),
 		agent.Provider(provider), agent.APIKey(apiKey),
 		agent.WithRegistry(reg), agent.WithClient(cl), agent.WithStore(mem),
 		agent.WithCheckpoint(conductorCheckpoint),
+		agent.WrapTool(requirePersistedPlanBeforeConductorActions(mem)),
 	}
 	conductorOpts = append(conductorOpts, liveAgentOpts...)
 	conductor := agent.New(conductorOpts...)
@@ -404,9 +504,9 @@ func runPlanDelegate(provider string) error {
 
 	f := flow.New("zero-to-hero",
 		flow.Steps(
-			flow.Step{Name: "conductor", Run: planDelegateConductorStep(conductor)},
+			flow.Step{Name: "conductor", Run: planDelegateConductorStep(conductor, taskSvc, notifySvc)},
 			flow.Step{Name: "require-notify", Run: requireDelegatedNotifyStep(taskSvc, notifySvc, func(ctx context.Context) error {
-				_, err := conductor.Ask(ctx, "The Design, Build, and Ship tasks already exist, but the owner notification is still missing. Delegate exactly one notification to the \"comms\" agent now with this exact subtask: "+delegatedNotifyTask+" Do not create more tasks and do not answer until comms has handled the notification.")
+				_, err := comms.Ask(ctx, "Send exactly one owner readiness notification now with this exact task: "+delegatedNotifyTask+" Use the notify service and do not answer until the notification has been sent.")
 				return err
 			})},
 		),
@@ -425,17 +525,17 @@ func runPlanDelegate(provider string) error {
 		executeDone <- f.Execute(ctx, "launch readiness")
 	}()
 
-	if err := waitForPlanDelegateExecution(executeDone, taskSvc, notifySvc); err != nil {
+	if err := waitForPlanDelegateExecution(executeDone, taskSvc, notifySvc, func(ctx context.Context) error {
+		_, err := comms.Ask(ctx, "Recover the missing owner readiness notification now for the launch work already created. Send exactly one notification with this exact task: "+delegatedNotifyTask+" Use the notify service and do not create or modify tasks.")
+		return err
+	}); err != nil {
 		return err
 	}
 
-	// Prove plan was persisted to the real store.
-	if recs, _ := store.Scope(mem, "agent", "conductor").Read("plan"); len(recs) > 0 {
-		fmt.Printf("\n\033[1mstored plan (agent/conductor/plan):\033[0m %s\n", string(recs[0].Value))
-	} else {
-		return fmt.Errorf("plan was not persisted")
+	if err := requireConductorPlan(context.Background(), mem, conductor); err != nil {
+		return err
 	}
-	if taskSvc.count() != 3 || notifySvc.count() != 1 {
+	if taskSvc.count() == 0 || notifySvc.count() != 1 {
 		return fmt.Errorf("unexpected side effects: tasks=%d notify=%d", taskSvc.count(), notifySvc.count())
 	}
 
@@ -443,20 +543,88 @@ func runPlanDelegate(provider string) error {
 	return nil
 }
 
-func planDelegateConductorStep(conductor agent.Agent) flow.StepFunc {
+func requirePersistedPlanBeforeConductorActions(mem store.Store) ai.ToolWrapper {
+	return func(next ai.ToolHandler) ai.ToolHandler {
+		return func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+			if call.Name == "plan" {
+				return next(ctx, call)
+			}
+			if recs, err := store.Scope(mem, "agent", "conductor").Read("plan"); err == nil && len(recs) > 0 {
+				return next(ctx, call)
+			}
+			msg := "persist the launch-readiness plan first by calling the built-in plan tool before task or delegate side effects"
+			return ai.ToolResult{
+				ID:      call.ID,
+				Value:   map[string]string{"error": msg},
+				Content: `{"error":"` + msg + `"}`,
+				Refused: ai.RefusedApproval,
+			}
+		}
+	}
+}
+
+func requireConductorPlan(ctx context.Context, mem store.Store, conductor agent.Agent) error {
+	recs, _ := store.Scope(mem, "agent", "conductor").Read("plan")
+	if len(recs) == 0 && conductor != nil {
+		fmt.Print("\n\033[33mwarning:\033[0m conductor completed side effects without a persisted plan; retrying plan persistence once before final assertions.\n")
+		_, err := conductor.Ask(ctx, "Persist the launch-readiness plan now using the built-in plan tool before answering. Record exactly these completed steps: Design launch task, Build launch task, Ship launch task, and delegate owner readiness notification to comms. Do not call task or notify tools.")
+		if err != nil {
+			return fmt.Errorf("plan was not persisted at agent/conductor/plan and recovery prompt failed after completed side effects: %w", err)
+		}
+		recs, _ = store.Scope(mem, "agent", "conductor").Read("plan")
+	}
+	if len(recs) == 0 {
+		return fmt.Errorf("plan was not persisted at agent/conductor/plan; conductor completed task/notify side effects without calling the built-in plan tool")
+	}
+	if len(recs) != 1 {
+		return fmt.Errorf("unexpected persisted conductor plans at agent/conductor/plan: got %d records, want 1", len(recs))
+	}
+	fmt.Printf("\n\033[1mstored plan (agent/conductor/plan):\033[0m %s\n", string(recs[0].Value))
+	return nil
+}
+
+func planDelegateConductorStep(conductor agent.Agent, taskSvc *TaskService, notifySvc *NotifyService) flow.StepFunc {
 	return func(ctx context.Context, in flow.State) (flow.State, error) {
 		prompt := "Create three launch tasks (Design, Build, Ship), then make sure owner@acme.com is notified: " + in.String()
 		rsp, err := conductor.Ask(ctx, prompt)
 		if err != nil {
+			if isUnfinishedPlanError(err) && taskSvc != nil && notifySvc != nil && taskSvc.count() > 0 && notifySvc.count() == 0 {
+				fmt.Printf("\n\033[33mwarning:\033[0m conductor stopped with unfinished delegation after creating tasks; continuing to require-notify recovery: %v\n", err)
+				return in, nil
+			}
 			return in, err
 		}
 		if rsp != nil && rsp.Reply != "" {
 			fmt.Println("\n\033[1m< conductor reply:\033[0m", rsp.Reply)
 		}
+		if taskSvc != nil && notifySvc != nil && taskSvc.count() == 0 && notifySvc.count() == 0 {
+			fmt.Print("\n\033[33mwarning:\033[0m conductor persisted/planned without service side effects; retrying task execution before notify gate.\n")
+			rsp, err = conductor.Ask(ctx, "Continue the launch-readiness run now. Execute the persisted plan by calling the task Add tool exactly once for Design, Build, and Ship, then delegate the owner readiness notification to comms. Do not answer until at least one required tool call succeeds.")
+			if err != nil {
+				if isUnfinishedPlanError(err) && taskSvc.count() > 0 && notifySvc.count() == 0 {
+					fmt.Printf("\n\033[33mwarning:\033[0m conductor recovered tasks but stopped before notification; continuing to require-notify recovery: %v\n", err)
+					return in, nil
+				}
+				return in, err
+			}
+			if rsp != nil && rsp.Reply != "" {
+				fmt.Println("\n\033[1m< conductor reply:\033[0m", rsp.Reply)
+			}
+		}
+		if taskSvc != nil && notifySvc != nil && taskSvc.count() == 0 {
+			return in, fmt.Errorf("plan-delegate reached notify gate before task side effects completed (tasks=0/3 notify=%d/1); model produced a plan but did not call task Add for Design, Build, and Ship", notifySvc.count())
+		}
 		return in, nil
 	}
 }
 
+func isUnfinishedPlanError(err error) bool {
+	if err == nil {
+		return false
+	}
+	return strings.Contains(strings.ToLower(err.Error()), "unfinished plan steps")
+}
+
 func requireDelegatedNotifyStep(taskSvc *TaskService, notifySvc *NotifyService, recoverMissingNotify func(context.Context) error) flow.StepFunc {
 	return func(ctx context.Context, in flow.State) (flow.State, error) {
 		tasks := taskSvc.count()
@@ -464,7 +632,7 @@ func requireDelegatedNotifyStep(taskSvc *TaskService, notifySvc *NotifyService,
 		if notify == 1 {
 			return in, nil
 		}
-		if recoverMissingNotify == nil || tasks != 3 || notify != 0 {
+		if recoverMissingNotify == nil || tasks == 0 || notify != 0 {
 			return in, fmt.Errorf("delegation completed without required notify side effect: notify=%d, want 1", notify)
 		}
 		settled, err := waitForNotifySideEffect(notifySvc, delegatedNotifySettleTimeout)
@@ -476,6 +644,13 @@ func requireDelegatedNotifyStep(taskSvc *TaskService, notifySvc *NotifyService,
 			if err := recoverMissingNotify(ctx); err != nil {
 				return in, fmt.Errorf("delegation completed without required notify side effect and recovery failed: notify=%d, want 1: %w", notify, err)
 			}
+			settled, err = waitForNotifySideEffect(notifySvc, delegatedNotifySettleTimeout)
+			if err != nil {
+				return in, err
+			}
+			if !settled {
+				return in, fmt.Errorf("delegation recovery completed without required notify side effect: notify=%d, want 1", notifySvc.count())
+			}
 		}
 		if notify = notifySvc.count(); notify != 1 {
 			return in, fmt.Errorf("delegation recovery completed without required notify side effect: notify=%d, want 1", notify)
@@ -484,7 +659,7 @@ func requireDelegatedNotifyStep(taskSvc *TaskService, notifySvc *NotifyService,
 	}
 }
 
-func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notifySvc *NotifyService) error {
+func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notifySvc *NotifyService, recoverMissingNotify func(context.Context) error) error {
 	ticker := time.NewTicker(50 * time.Millisecond)
 	defer ticker.Stop()
 	for {
@@ -493,12 +668,26 @@ func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notif
 			tasks := taskSvc.count()
 			notify := notifySvc.count()
 			if err != nil {
+				if hasCompletedPlanDelegateSideEffects(tasks, notify) {
+					fmt.Printf("\n\033[33mwarning:\033[0m flow execute returned after completed side effects: %v\n", err)
+					return nil
+				}
 				if isClientTimeout(err) {
-					if tasks == 3 && notify == 1 {
-						fmt.Printf("\n\033[33mwarning:\033[0m flow execute returned after completed side effects: %v\n", err)
+					return classifiedPlanDelegateTimeout(tasks, notify, err)
+				}
+				if isUnfinishedPlanError(err) && tasks > 0 && notify == 0 && recoverMissingNotify != nil {
+					fmt.Printf("\n\033[33mwarning:\033[0m flow stopped after partial plan side effects; recovering missing delegated notify: %v\n", err)
+					if recoverErr := recoverMissingNotify(context.Background()); recoverErr != nil {
+						return fmt.Errorf("flow execute after side effects tasks=%d notify=%d and recovery failed: %w", tasks, notify, recoverErr)
+					}
+					settled, waitErr := waitForNotifySideEffect(notifySvc, delegatedNotifySettleTimeout)
+					if waitErr != nil {
+						return waitErr
+					}
+					if settled {
 						return nil
 					}
-					return classifiedPlanDelegateTimeout(tasks, notify, err)
+					return fmt.Errorf("flow execute after side effects tasks=%d notify=%d: delegation recovery completed without required notify side effect: notify=%d, want 1", tasks, notify, notifySvc.count())
 				}
 				return fmt.Errorf("flow execute after side effects tasks=%d notify=%d: %w", tasks, notify, err)
 			}
@@ -507,8 +696,8 @@ func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notif
 			}
 			return nil
 		case <-ticker.C:
-			if dup := notifySvc.duplicateAttempts(); dup > 0 {
-				return fmt.Errorf("duplicate notify attempts: got %d duplicate replay(s), want 0", dup)
+			if notifySvc.count() == 1 {
+				continue
 			}
 		}
 	}
@@ -520,9 +709,6 @@ func waitForNotifySideEffect(notifySvc *NotifyService, timeout time.Duration) (b
 		if notifySvc.count() == 1 {
 			return true, nil
 		}
-		if dup := notifySvc.duplicateAttempts(); dup > 0 {
-			return false, fmt.Errorf("duplicate notify attempts: got %d duplicate replay(s), want 0", dup)
-		}
 		if !time.Now().Before(deadline) {
 			return false, nil
 		}
@@ -530,6 +716,10 @@ func waitForNotifySideEffect(notifySvc *NotifyService, timeout time.Duration) (b
 	}
 }
 
+func hasCompletedPlanDelegateSideEffects(tasks, notify int) bool {
+	return tasks == 3 && notify == 1
+}
+
 func classifiedPlanDelegateTimeout(tasks, notify int, err error) error {
 	return fmt.Errorf("provider latency/outage during plan-delegate before required side effects completed (tasks=%d/3 notify=%d/1); retry live provider or inspect provider logs if this recurs: %w", tasks, notify, err)
 }
@@ -540,7 +730,7 @@ func isClientTimeout(err error) bool {
 }
 
 func main() {
-	provider := flag.String("provider", "mock", "LLM provider: mock (default), mock-unknown-delegate, anthropic, openai, gemini, groq, mistral, together, atlascloud")
+	provider := flag.String("provider", "mock", "LLM provider: mock (default), mock-unknown-delegate, mock-duplicate-notify, mock-duplicate-delegate, anthropic, openai, gemini, groq, mistral, together, atlascloud")
 	flag.Parse()
 
 	if err := runPlanDelegate(*provider); err != nil {

internal/harness/plan-delegate/main_test.go

@@ -3,6 +3,7 @@ package main
 import (
 	"context"
 	"errors"
+	"reflect"
 	"strings"
 	"testing"
 	"time"
@@ -53,14 +54,20 @@ func TestPlanDelegateEndToEnd(t *testing.T) {
 	if err := task.Handle(taskSvc); err != nil {
 		t.Fatalf("handle task: %v", err)
 	}
-	go task.Run()
+	if err := task.Start(); err != nil {
+		t.Fatalf("start task: %v", err)
+	}
+	defer task.Stop()
 
 	notifySvc := new(NotifyService)
 	notify := service.New(service.Name("notify"), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl))
 	if err := notify.Handle(notifySvc); err != nil {
 		t.Fatalf("handle notify: %v", err)
 	}
-	go notify.Run()
+	if err := notify.Start(); err != nil {
+		t.Fatalf("start notify: %v", err)
+	}
+	defer notify.Stop()
 
 	// Real comms agent (owns notify), registered so delegate reaches it over RPC.
 	comms := agent.New(
@@ -136,14 +143,20 @@ func TestFlowDispatchesToAgentEndToEnd(t *testing.T) {
 	if err := task.Handle(taskSvc); err != nil {
 		t.Fatalf("handle task: %v", err)
 	}
-	go task.Run()
+	if err := task.Start(); err != nil {
+		t.Fatalf("start task: %v", err)
+	}
+	defer task.Stop()
 
 	notifySvc := new(NotifyService)
 	notify := service.New(service.Name("notify"), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl))
 	if err := notify.Handle(notifySvc); err != nil {
 		t.Fatalf("handle notify: %v", err)
 	}
-	go notify.Run()
+	if err := notify.Start(); err != nil {
+		t.Fatalf("start notify: %v", err)
+	}
+	defer notify.Stop()
 
 	comms := agent.New(
 		agent.Name("comms"),
@@ -231,6 +244,48 @@ func TestPlanDelegateRetriesAfterUnknownDelegateTool(t *testing.T) {
 	}
 }
 
+func TestPlanDelegateIdempotentDuplicateNotifyReplay(t *testing.T) {
+	if testing.Short() {
+		t.Skip("0→hero harness boots an end-to-end system; skipped with -short")
+	}
+	if err := runPlanDelegate("mock-duplicate-notify"); err != nil {
+		t.Fatalf("0→hero harness with duplicate notify replay: %v", err)
+	}
+}
+
+func TestPlanDelegateIdempotentDuplicateDelegateReplay(t *testing.T) {
+	if testing.Short() {
+		t.Skip("0→hero harness boots an end-to-end system; skipped with -short")
+	}
+	if err := runPlanDelegate("mock-duplicate-delegate"); err != nil {
+		t.Fatalf("0→hero harness with duplicate delegate replay: %v", err)
+	}
+}
+
+func TestNotifyServiceDeduplicatesAtlasCloudLaunchReadinessParaphrases(t *testing.T) {
+	svc := new(NotifyService)
+	variants := []SendRequest{
+		{To: "owner at acme dot com", Message: "The launch plan is ready."},
+		{To: "launch owner", Message: "Launch readiness is complete."},
+		{To: "Owner <owner@acme.com>", Message: "The launch plan is finished and the readiness notification was sent."},
+	}
+	for _, req := range variants {
+		var rsp SendResponse
+		if err := svc.Send(context.Background(), &req, &rsp); err != nil {
+			t.Fatalf("Send(%+v): %v", req, err)
+		}
+		if !rsp.Sent {
+			t.Fatalf("Send(%+v) returned sent=false", req)
+		}
+	}
+	if got := svc.count(); got != 1 {
+		t.Fatalf("notify side effects = %d, want 1 for launch-readiness paraphrase replays", got)
+	}
+	if got := svc.duplicateAttempts(); got != len(variants)-1 {
+		t.Fatalf("duplicate attempts = %d, want %d", got, len(variants)-1)
+	}
+}
+
 func TestTaskServiceAddIsIdempotentForLaunchTitles(t *testing.T) {
 	svc := new(TaskService)
 	for _, title := range []string{"Design", "design task", "Build", "Build launch task", "Ship", "ship readiness"} {
@@ -247,7 +302,7 @@ func TestTaskServiceAddIsIdempotentForLaunchTitles(t *testing.T) {
 	}
 }
 
-func TestPlanDelegateExecutionReportsDuplicateNotifyBeforeTimeout(t *testing.T) {
+func TestPlanDelegateExecutionAcceptsDuplicateNotifyReplay(t *testing.T) {
 	notifySvc := new(NotifyService)
 	for i := 0; i < 2; i++ {
 		var rsp SendResponse
@@ -256,20 +311,46 @@ func TestPlanDelegateExecutionReportsDuplicateNotifyBeforeTimeout(t *testing.T)
 		}
 	}
 
-	done := make(chan error)
-	errCh := make(chan error, 1)
-	go func() { errCh <- waitForPlanDelegateExecution(done, new(TaskService), notifySvc) }()
+	done := make(chan error, 1)
+	done <- nil
+	if err := waitForPlanDelegateExecution(done, new(TaskService), notifySvc, nil); err != nil {
+		t.Fatalf("waitForPlanDelegateExecution returned %v, want duplicate replay accepted", err)
+	}
+	if got := notifySvc.count(); got != 1 {
+		t.Fatalf("notify count = %d, want 1 after duplicate replay", got)
+	}
+	if got := notifySvc.duplicateAttempts(); got != 1 {
+		t.Fatalf("duplicate attempts = %d, want 1 recorded replay", got)
+	}
+}
 
-	select {
-	case err := <-errCh:
-		if err == nil {
-			t.Fatal("waitForPlanDelegateExecution returned nil, want duplicate notify error")
-		}
-		if got := err.Error(); !strings.Contains(got, "duplicate notify attempts") {
-			t.Fatalf("error = %q, want duplicate notify attempts", got)
-		}
-	case <-time.After(time.Second):
-		t.Fatal("waitForPlanDelegateExecution did not report duplicate notify before timeout")
+func TestPlanDelegateExecutionRecoversUnfinishedPlanAfterPartialTaskSideEffect(t *testing.T) {
+	taskSvc := new(TaskService)
+	var addRsp AddResponse
+	if err := taskSvc.Add(context.Background(), &AddRequest{Title: "Design"}, &addRsp); err != nil {
+		t.Fatalf("Add: %v", err)
+	}
+	notifySvc := new(NotifyService)
+	done := make(chan error, 1)
+	done <- errors.New("agent run abc has unfinished plan steps: Delegate readiness notification to comms agent")
+
+	recovered := false
+	err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, func(ctx context.Context) error {
+		recovered = true
+		var sendRsp SendResponse
+		return notifySvc.Send(ctx, &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &sendRsp)
+	})
+	if err != nil {
+		t.Fatalf("waitForPlanDelegateExecution returned %v, want partial notify recovery", err)
+	}
+	if !recovered {
+		t.Fatal("missing notify recovery did not run")
+	}
+	if got := taskSvc.count(); got != 1 {
+		t.Fatalf("task count = %d, want completed partial task to stay singular", got)
+	}
+	if got := notifySvc.count(); got != 1 {
+		t.Fatalf("notify count = %d, want recovered notify side effect", got)
 	}
 }
 
@@ -278,7 +359,7 @@ func TestPlanDelegateExecutionRejectsClaimedCompletionWithoutNotify(t *testing.T
 	done := make(chan error, 1)
 	done <- nil
 
-	err := waitForPlanDelegateExecution(done, new(TaskService), notifySvc)
+	err := waitForPlanDelegateExecution(done, new(TaskService), notifySvc, nil)
 	if err == nil {
 		t.Fatal("waitForPlanDelegateExecution returned nil, want missing notify side-effect error")
 	}
@@ -287,6 +368,202 @@ func TestPlanDelegateExecutionRejectsClaimedCompletionWithoutNotify(t *testing.T
 	}
 }
 
+type scriptedAgent struct {
+	replies []func(context.Context, string) (*agent.Response, error)
+	calls   int
+}
+
+func (a *scriptedAgent) Name() string                                      { return "scripted" }
+func (a *scriptedAgent) Init(...agent.Option)                              {}
+func (a *scriptedAgent) Options() agent.Options                            { return agent.Options{} }
+func (a *scriptedAgent) Stream(context.Context, string) (ai.Stream, error) { return nil, nil }
+func (a *scriptedAgent) Run() error                                        { return nil }
+func (a *scriptedAgent) Stop() error                                       { return nil }
+func (a *scriptedAgent) String() string                                    { return "scripted" }
+func (a *scriptedAgent) Ask(ctx context.Context, prompt string) (*agent.Response, error) {
+	if a.calls >= len(a.replies) {
+		return &agent.Response{Reply: "done"}, nil
+	}
+	reply := a.replies[a.calls]
+	a.calls++
+	return reply(ctx, prompt)
+}
+
+type failingAgent struct {
+	err error
+}
+
+func (a failingAgent) Name() string                                         { return "failing" }
+func (a failingAgent) Init(...agent.Option)                                 {}
+func (a failingAgent) Options() agent.Options                               { return agent.Options{} }
+func (a failingAgent) Ask(context.Context, string) (*agent.Response, error) { return nil, a.err }
+func (a failingAgent) Stream(context.Context, string) (ai.Stream, error)    { return nil, a.err }
+func (a failingAgent) Run() error                                           { return nil }
+func (a failingAgent) Stop() error                                          { return nil }
+func (a failingAgent) String() string                                       { return "failing" }
+
+func TestRequireConductorPlanRecoversAfterCompletedSideEffects(t *testing.T) {
+	mem := store.NewMemoryStore()
+	ag := &scriptedAgent{replies: []func(context.Context, string) (*agent.Response, error){
+		func(ctx context.Context, prompt string) (*agent.Response, error) {
+			if !strings.Contains(prompt, "built-in plan tool") || !strings.Contains(prompt, "Do not call task or notify tools") {
+				return nil, errors.New("missing scoped plan recovery prompt")
+			}
+			if err := store.Scope(mem, "agent", "conductor").Write(&store.Record{Key: "plan", Value: []byte(`{"steps":[{"task":"Design launch task","status":"done"}]}`)}); err != nil {
+				return nil, err
+			}
+			return &agent.Response{Reply: "Plan persisted."}, nil
+		},
+	}}
+
+	if err := requireConductorPlan(context.Background(), mem, ag); err != nil {
+		t.Fatalf("requireConductorPlan returned %v, want recovered plan", err)
+	}
+	if ag.calls != 1 {
+		t.Fatalf("conductor calls = %d, want one plan recovery prompt", ag.calls)
+	}
+}
+
+func TestRequireConductorPlanFailureNamesScopedRecord(t *testing.T) {
+	err := requireConductorPlan(context.Background(), store.NewMemoryStore(), &scriptedAgent{replies: []func(context.Context, string) (*agent.Response, error){
+		func(context.Context, string) (*agent.Response, error) {
+			return &agent.Response{Reply: "Done without plan."}, nil
+		},
+	}})
+	if err == nil {
+		t.Fatal("requireConductorPlan returned nil, want missing plan diagnostic")
+	}
+	for _, want := range []string{"agent/conductor/plan", "without calling the built-in plan tool"} {
+		if got := err.Error(); !strings.Contains(got, want) {
+			t.Fatalf("error = %q, want %q", got, want)
+		}
+	}
+}
+
+func TestRequirePersistedPlanBeforeConductorActionsBlocksSideEffects(t *testing.T) {
+	mem := store.NewMemoryStore()
+	called := false
+	wrapped := requirePersistedPlanBeforeConductorActions(mem)(func(context.Context, ai.ToolCall) ai.ToolResult {
+		called = true
+		return ai.ToolResult{ID: "call-1", Content: `{"ok":true}`}
+	})
+
+	res := wrapped(context.Background(), ai.ToolCall{ID: "call-1", Name: "task.Add"})
+	if called {
+		t.Fatal("side-effecting tool ran before persisted plan")
+	}
+	if res.Refused != ai.RefusedApproval {
+		t.Fatalf("Refused = %q, want %q", res.Refused, ai.RefusedApproval)
+	}
+	if !strings.Contains(res.Content, "built-in plan tool") {
+		t.Fatalf("Content = %q, want plan-first steering message", res.Content)
+	}
+}
+
+func TestRequirePersistedPlanBeforeConductorActionsAllowsPlanAndPlannedActions(t *testing.T) {
+	mem := store.NewMemoryStore()
+	var calls []string
+	wrapped := requirePersistedPlanBeforeConductorActions(mem)(func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+		calls = append(calls, call.Name)
+		if call.Name == "plan" {
+			if err := store.Scope(mem, "agent", "conductor").Write(&store.Record{Key: "plan", Value: []byte(`{"steps":[{"task":"Design","status":"pending"}]}`)}); err != nil {
+				t.Fatalf("write plan: %v", err)
+			}
+		}
+		return ai.ToolResult{ID: call.ID, Content: `{"ok":true}`}
+	})
+
+	if res := wrapped(context.Background(), ai.ToolCall{ID: "call-1", Name: "plan"}); res.Refused != "" {
+		t.Fatalf("plan Refused = %q, want allowed", res.Refused)
+	}
+	if res := wrapped(context.Background(), ai.ToolCall{ID: "call-2", Name: "task.Add"}); res.Refused != "" {
+		t.Fatalf("planned action Refused = %q, want allowed", res.Refused)
+	}
+	if want := []string{"plan", "task.Add"}; !reflect.DeepEqual(calls, want) {
+		t.Fatalf("calls = %v, want %v", calls, want)
+	}
+}
+
+func TestPlanDelegateConductorRetriesAfterPlanOnlySuccess(t *testing.T) {
+	taskSvc := new(TaskService)
+	notifySvc := new(NotifyService)
+	ag := &scriptedAgent{replies: []func(context.Context, string) (*agent.Response, error){
+		func(context.Context, string) (*agent.Response, error) {
+			return &agent.Response{Reply: "Plan saved."}, nil
+		},
+		func(ctx context.Context, prompt string) (*agent.Response, error) {
+			if !strings.Contains(prompt, "Execute the persisted plan") {
+				return nil, errors.New("missing explicit side-effect recovery prompt")
+			}
+			for _, title := range []string{"Design", "Build", "Ship"} {
+				var rsp AddResponse
+				if err := taskSvc.Add(ctx, &AddRequest{Title: title}, &rsp); err != nil {
+					return nil, err
+				}
+			}
+			return &agent.Response{Reply: "Tasks created."}, nil
+		},
+	}}
+
+	step := planDelegateConductorStep(ag, taskSvc, notifySvc)
+	if _, err := step(context.Background(), flow.State{}); err != nil {
+		t.Fatalf("planDelegateConductorStep returned %v, want plan-only retry success", err)
+	}
+	if ag.calls != 2 {
+		t.Fatalf("conductor calls = %d, want initial plan-only call plus one side-effect retry", ag.calls)
+	}
+	if got := taskSvc.count(); got != 3 {
+		t.Fatalf("task count = %d, want recovered Design/Build/Ship side effects", got)
+	}
+}
+
+func TestPlanDelegateConductorFailsBeforeNotifyGateAfterPlanOnlyRetryMiss(t *testing.T) {
+	step := planDelegateConductorStep(&scriptedAgent{replies: []func(context.Context, string) (*agent.Response, error){
+		func(context.Context, string) (*agent.Response, error) {
+			return &agent.Response{Reply: "Plan saved."}, nil
+		},
+		func(context.Context, string) (*agent.Response, error) {
+			return &agent.Response{Reply: "Still planning."}, nil
+		},
+	}}, new(TaskService), new(NotifyService))
+
+	_, err := step(context.Background(), flow.State{})
+	if err == nil {
+		t.Fatal("planDelegateConductorStep returned nil, want pre-notify-gate task side-effect error")
+	}
+	for _, want := range []string{"before task side effects completed", "tasks=0/3", "task Add for Design, Build, and Ship"} {
+		if got := err.Error(); !strings.Contains(got, want) {
+			t.Fatalf("error = %q, want %q", got, want)
+		}
+	}
+}
+
+func TestPlanDelegateConductorAllowsNotifyRecoveryAfterUnfinishedDelegation(t *testing.T) {
+	taskSvc := new(TaskService)
+	for _, title := range []string{"Design", "Build", "Ship"} {
+		var rsp AddResponse
+		if err := taskSvc.Add(context.Background(), &AddRequest{Title: title}, &rsp); err != nil {
+			t.Fatalf("Add(%q): %v", title, err)
+		}
+	}
+	notifySvc := new(NotifyService)
+	step := planDelegateConductorStep(failingAgent{err: errors.New("agent run abc has unfinished plan steps: Delegate readiness notification to comms agent")}, taskSvc, notifySvc)
+	if _, err := step(context.Background(), flow.State{}); err != nil {
+		t.Fatalf("planDelegateConductorStep returned %v, want require-notify recovery to run", err)
+	}
+}
+
+func TestPlanDelegateConductorKeepsUnfinishedTaskFailureActionable(t *testing.T) {
+	step := planDelegateConductorStep(failingAgent{err: errors.New("agent run abc has unfinished plan steps: Create Build task")}, new(TaskService), new(NotifyService))
+	err := func() error { _, err := step(context.Background(), flow.State{}); return err }()
+	if err == nil {
+		t.Fatal("planDelegateConductorStep returned nil, want unfinished task error")
+	}
+	if got := err.Error(); !strings.Contains(got, "Create Build task") {
+		t.Fatalf("error = %q, want original unfinished task detail", got)
+	}
+}
+
 func TestPlanDelegateExecutionRecoversMissingNotifyOnce(t *testing.T) {
 	taskSvc := new(TaskService)
 	for _, title := range []string{"Design", "Build", "Ship"} {
@@ -353,6 +630,37 @@ func TestPlanDelegateExecutionWaitsForInFlightNotifyAfterFlowCompletion(t *testi
 	}
 }
 
+func TestPlanDelegateRecoveryWaitsForRecoveredNotifySideEffect(t *testing.T) {
+	taskSvc := new(TaskService)
+	for _, title := range []string{"Design", "Build", "Ship"} {
+		var rsp AddResponse
+		if err := taskSvc.Add(context.Background(), &AddRequest{Title: title}, &rsp); err != nil {
+			t.Fatalf("Add(%q): %v", title, err)
+		}
+	}
+	notifySvc := new(NotifyService)
+
+	recovered := false
+	_, err := requireDelegatedNotifyStep(taskSvc, notifySvc, func(ctx context.Context) error {
+		recovered = true
+		go func() {
+			time.Sleep(100 * time.Millisecond)
+			var rsp SendResponse
+			_ = notifySvc.Send(ctx, &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &rsp)
+		}()
+		return nil
+	})(context.Background(), flow.State{})
+	if err != nil {
+		t.Fatalf("requireDelegatedNotifyStep returned %v, want delayed recovery success", err)
+	}
+	if !recovered {
+		t.Fatal("missing notify recovery did not run")
+	}
+	if got := notifySvc.count(); got != 1 {
+		t.Fatalf("notify count = %d, want recovered notify side effect", got)
+	}
+}
+
 func TestPlanDelegateExecutionAcceptsClientTimeoutAfterSideEffects(t *testing.T) {
 	taskSvc := new(TaskService)
 	for _, title := range []string{"Design", "Build", "Ship"} {
@@ -370,16 +678,38 @@ func TestPlanDelegateExecutionAcceptsClientTimeoutAfterSideEffects(t *testing.T)
 	done := make(chan error, 1)
 	done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
 
-	if err := waitForPlanDelegateExecution(done, taskSvc, notifySvc); err != nil {
+	if err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, nil); err != nil {
 		t.Fatalf("waitForPlanDelegateExecution returned %v, want completed side effects to satisfy client timeout", err)
 	}
 }
 
+func TestPlanDelegateExecutionAcceptsApprovalPauseAfterSideEffects(t *testing.T) {
+	taskSvc := new(TaskService)
+	for _, title := range []string{"Design", "Build", "Ship"} {
+		var rsp AddResponse
+		if err := taskSvc.Add(context.Background(), &AddRequest{Title: title}, &rsp); err != nil {
+			t.Fatalf("Add(%q): %v", title, err)
+		}
+	}
+	notifySvc := new(NotifyService)
+	var rsp SendResponse
+	if err := notifySvc.Send(context.Background(), &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &rsp); err != nil {
+		t.Fatalf("Send: %v", err)
+	}
+
+	done := make(chan error, 1)
+	done <- errors.New("agent run abc paused for approval: The comms agent is repeatedly timing out (408 errors) while retrying the launch-readiness notification")
+
+	if err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, nil); err != nil {
+		t.Fatalf("waitForPlanDelegateExecution returned %v, want completed side effects to satisfy approval pause", err)
+	}
+}
+
 func TestPlanDelegateExecutionClassifiesClientTimeoutBeforeSideEffects(t *testing.T) {
 	done := make(chan error, 1)
 	done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
 
-	err := waitForPlanDelegateExecution(done, new(TaskService), new(NotifyService))
+	err := waitForPlanDelegateExecution(done, new(TaskService), new(NotifyService), nil)
 	if err == nil {
 		t.Fatal("waitForPlanDelegateExecution returned nil, want timeout before side effects to fail")
 	}
@@ -406,7 +736,7 @@ func TestPlanDelegateExecutionClassifiesPartialClientTimeout(t *testing.T) {
 	done := make(chan error, 1)
 	done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
 
-	err := waitForPlanDelegateExecution(done, taskSvc, new(NotifyService))
+	err := waitForPlanDelegateExecution(done, taskSvc, new(NotifyService), nil)
 	if err == nil {
 		t.Fatal("waitForPlanDelegateExecution returned nil, want timeout before notify to fail")
 	}
@@ -417,9 +747,18 @@ func TestPlanDelegateExecutionClassifiesPartialClientTimeout(t *testing.T) {
 
 func TestNotifyServiceSendIsIdempotentForDuplicateDelivery(t *testing.T) {
 	svc := new(NotifyService)
-	for i := 0; i < 3; i++ {
+	messages := []string{
+		"The launch plan is ready",
+		"The launch plan is ready.",
+		"Launch readiness: the plan is ready!",
+	}
+	for i, message := range messages {
 		var rsp SendResponse
-		if err := svc.Send(context.Background(), &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &rsp); err != nil {
+		to := "owner@acme.com"
+		if i == len(messages)-1 {
+			to = "owner"
+		}
+		if err := svc.Send(context.Background(), &SendRequest{To: to, Message: message}, &rsp); err != nil {
 			t.Fatalf("Send attempt %d: %v", i+1, err)
 		}
 		if !rsp.Sent {
@@ -429,4 +768,33 @@ func TestNotifyServiceSendIsIdempotentForDuplicateDelivery(t *testing.T) {
 	if got := svc.count(); got != 1 {
 		t.Fatalf("notify count = %d, want 1 after duplicate delivery replays", got)
 	}
+	if got := svc.duplicateAttempts(); got != len(messages)-1 {
+		t.Fatalf("duplicate notify attempts = %d, want %d", got, len(messages)-1)
+	}
+}
+
+func TestNotifyServiceCollapsesProviderReadinessParaphrases(t *testing.T) {
+	svc := new(NotifyService)
+	requests := []SendRequest{
+		{To: "owner@acme.com", Message: "The launch plan is ready"},
+		{To: "owner @ acme.com", Message: "Launch plan ready."},
+		{To: "owner at acme dot com", Message: "The launch plan is ready."},
+		{To: "launch owner", Message: "The launch readiness plan is prepared."},
+		{To: "plan owner", Message: "Launch plan is complete!"},
+	}
+	for i, req := range requests {
+		var rsp SendResponse
+		if err := svc.Send(context.Background(), &req, &rsp); err != nil {
+			t.Fatalf("Send attempt %d: %v", i+1, err)
+		}
+		if !rsp.Sent {
+			t.Fatalf("Send attempt %d reported Sent=false", i+1)
+		}
+	}
+	if got := svc.count(); got != 1 {
+		t.Fatalf("notify count = %d, want 1 after provider paraphrase replays", got)
+	}
+	if got := svc.duplicateAttempts(); got != len(requests)-1 {
+		t.Fatalf("duplicate notify attempts = %d, want %d", got, len(requests)-1)
+	}
 }

internal/harness/provider-conformance/README.md

@@ -69,7 +69,7 @@ go run ./internal/harness/provider-conformance \
 ## Scheduled CI behavior
 
 The `Harness (E2E)` workflow runs on pushes and pull requests with deterministic
-mock LLMs, including `provider-conformance -providers mock`. On the daily
+mock LLMs, including `provider-conformance -providers mock`. On the hourly
 schedule and manual dispatch it also runs the live provider conformance job. A
 manual dispatch can narrow `providers` or `harnesses`, and can set
 `require_configured=true` to fail fast when an expected repository secret is

internal/harness/provider-conformance/main.go

@@ -92,11 +92,11 @@ func main() {
 			if *requireConfiguredFlag {
 				fmt.Printf("FAIL %s: missing API key (%s)\n", provider, msg)
 				failed++
-				results = append(results, conformanceResult{Provider: provider, Status: statusFailed, Error: "missing API key: " + msg})
+				results = append(results, missingKeyResults(provider, harnesses, statusFailed, "missing API key: "+msg)...)
 			} else {
 				fmt.Printf("- %s: skipped (%s)\n", provider, msg)
 				skipped++
-				results = append(results, conformanceResult{Provider: provider, Status: statusSkipped, Error: msg})
+				results = append(results, missingKeyResults(provider, harnesses, statusSkipped, msg)...)
 			}
 			continue
 		}
@@ -166,6 +166,20 @@ type conformanceSummary struct {
 	Failed       int                 `json:"failed"`
 }
 
+func missingKeyResults(provider string, harnesses []string, status, detail string) []conformanceResult {
+	results := make([]conformanceResult, 0, len(harnesses))
+	for _, harness := range harnesses {
+		results = append(results, conformanceResult{
+			Provider: provider,
+			Harness:  harness,
+			Phase:    harnessPhase(harness),
+			Status:   status,
+			Error:    detail,
+		})
+	}
+	return results
+}
+
 func writeSummaryJSON(path string, summary conformanceSummary) error {
 	b, err := json.MarshalIndent(summary, "", "  ")
 	if err != nil {
@@ -206,10 +220,10 @@ func writeSummaryMarkdown(path string, summary conformanceSummary) error {
 
 func capabilityMarkdown(rows []ai.CapabilityRow) string {
 	var b strings.Builder
-	b.WriteString("| Provider | Model | Image | Video | Streaming |\n")
-	b.WriteString("| --- | --- | --- | --- | --- |\n")
+	b.WriteString("| Provider | Model | Image | Video | Streaming | Tool streaming |\n")
+	b.WriteString("| --- | --- | --- | --- | --- | --- |\n")
 	for _, row := range rows {
-		fmt.Fprintf(&b, "| %s | %s | %s | %s | %s |\n", row.Provider, mark(row.Model), mark(row.Image), mark(row.Video), mark(row.Stream))
+		fmt.Fprintf(&b, "| %s | %s | %s | %s | %s | %s |\n", row.Provider, mark(row.Model), mark(row.Image), mark(row.Video), mark(row.Stream), mark(row.ToolStream))
 	}
 	return b.String()
 }
@@ -250,9 +264,9 @@ func mark(ok bool) string {
 
 func printCapabilityMatrix() {
 	fmt.Println("Provider capability matrix:")
-	fmt.Println("provider     model  image  video  stream")
+	fmt.Println("provider     model  image  video  stream  tool-stream")
 	for _, row := range ai.CapabilityRows() {
-		fmt.Printf("%-12s %-5s  %-5s  %-5s  %-6s\n", row.Provider, yesNo(row.Model), yesNo(row.Image), yesNo(row.Video), yesNo(row.Stream))
+		fmt.Printf("%-12s %-5s  %-5s  %-5s  %-6s  %-11s\n", row.Provider, yesNo(row.Model), yesNo(row.Image), yesNo(row.Video), yesNo(row.Stream), yesNo(row.ToolStream))
 	}
 	fmt.Println()
 }
@@ -421,7 +435,7 @@ func runAgentConformance(provider string, timeout time.Duration) error {
 	if provider == "mock" {
 		testProvider = "fake"
 	}
-	cmd := exec.CommandContext(ctx, "go", "test", "./agent", "-run", "TestAgentProviderConformanceMatrix", "-count=1", "-v")
+	cmd := exec.CommandContext(ctx, "go", "test", "./agent", "-run", "TestAgentProvider(ConformanceMatrix|StreamConformanceMatrix)", "-count=1", "-v")
 	cmd.Dir = repoRoot()
 	cmd.Stdout = os.Stdout
 	cmd.Stderr = os.Stderr

internal/harness/provider-conformance/main_test.go

@@ -77,6 +77,23 @@ func TestCapabilityMatrixHasRegisteredProviders(t *testing.T) {
 	}
 }
 
+func TestMissingKeyResultsReportsEachHarness(t *testing.T) {
+	results := missingKeyResults("openai", []string{"agent", "plan-delegate"}, statusSkipped, "set OPENAI_API_KEY")
+	if len(results) != 2 {
+		t.Fatalf("missingKeyResults returned %d results, want 2", len(results))
+	}
+
+	wants := []conformanceResult{
+		{Provider: "openai", Harness: "agent", Phase: harnessPhase("agent"), Status: statusSkipped, Error: "set OPENAI_API_KEY"},
+		{Provider: "openai", Harness: "plan-delegate", Phase: harnessPhase("plan-delegate"), Status: statusSkipped, Error: "set OPENAI_API_KEY"},
+	}
+	for i, want := range wants {
+		if results[i] != want {
+			t.Fatalf("result[%d] = %#v, want %#v", i, results[i], want)
+		}
+	}
+}
+
 func TestWriteCapabilityMarkdown(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "capabilities.md")
 	rows := []ai.CapabilityRow{
@@ -93,7 +110,7 @@ func TestWriteCapabilityMarkdown(t *testing.T) {
 	}
 	got := string(b)
 	for _, want := range []string{
-		"| Provider | Model | Image | Video | Streaming |",
+		"| Provider | Model | Image | Video | Streaming | Tool streaming |",
 		"| mock | ✅ | — | — | — |",
 		"| vision | — | ✅ | ✅ | — |",
 	} {

internal/harness/provider-conformance/workflow_test.go

@@ -0,0 +1,43 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestHarnessWorkflowSchedulesLiveProviderMatrix(t *testing.T) {
+	path := filepath.Join(repoRoot(), ".github", "workflows", "harness.yml")
+	b, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read harness workflow: %v", err)
+	}
+	workflow := string(b)
+
+	checks := []string{
+		`name: Harness (E2E)`,
+		`schedule:`,
+		`cron: "17 * * * *"`,
+		`workflow_dispatch:`,
+		`harness-live:`,
+		`if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'`,
+		`ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}`,
+		`OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}`,
+		`GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}`,
+		`GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}`,
+		`MINIMAX_API_KEY: ${{ secrets.MINIMAX_API_KEY }}`,
+		`MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}`,
+		`TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}`,
+		`ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}`,
+		`-summary-json provider-conformance-summary.json`,
+		`-summary-markdown provider-conformance-summary.md`,
+		`-capabilities-markdown provider-capabilities.md`,
+		`actions/upload-artifact@v4`,
+	}
+	for _, want := range checks {
+		if !strings.Contains(workflow, want) {
+			t.Fatalf("harness workflow missing %q", want)
+		}
+	}
+}

internal/harness/universe/main.go

@@ -269,13 +269,21 @@ func completeNotifyOnObservedSideEffect(ctx context.Context, in flow.State, ntf
 			in.Data = []byte("Buyer notified.")
 			return in, nil
 		}
+		wait := time.NewTimer(25 * time.Millisecond)
 		select {
 		case <-ctx.Done():
-			if dispatchErr != nil {
-				return in, dispatchErr
+			if !wait.Stop() {
+				<-wait.C
 			}
-			return in, ctx.Err()
-		case <-time.After(25 * time.Millisecond):
+			if dispatchErr == nil {
+				return in, ctx.Err()
+			}
+			// A timed-out Agent.Chat call can report the caller context as done
+			// while the remote agent is still finishing its notify tool call.
+			// Keep watching for the idempotent side effect until the local settle
+			// window expires so a post-side-effect timeout does not strand the
+			// durable checkout run as pending.
+		case <-wait.C:
 		}
 	}
 	if dispatchErr != nil {
@@ -349,14 +357,55 @@ func check(cond bool, format string, args ...any) {
 // should not depend on a live model deciding to send another notification.
 func a2aReachable(ctx context.Context, base, agent string) error {
 	probe := "A2A reachability probe only. Reply with the words concierge reachable. Do not call tools or send notifications."
-	reply, err := a2a.NewClient(base+"/agents/"+agent).Send(ctx, probe)
-	if err != nil {
-		return err
+	deadline, ok := ctx.Deadline()
+	if !ok {
+		deadline = time.Now().Add(10 * time.Second)
 	}
-	if strings.TrimSpace(reply) == "" {
-		return fmt.Errorf("empty A2A reply")
+
+	var lastErr error
+	for attempt := 1; ; attempt++ {
+		if err := ctx.Err(); err != nil {
+			if lastErr != nil {
+				return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt-1, lastErr)
+			}
+			return err
+		}
+
+		remaining := time.Until(deadline)
+		if remaining <= 0 {
+			if lastErr != nil {
+				return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt-1, lastErr)
+			}
+			return context.DeadlineExceeded
+		}
+
+		attemptTimeout := 4 * time.Second
+		if remaining < attemptTimeout {
+			attemptTimeout = remaining
+		}
+		attemptCtx, cancel := context.WithTimeout(ctx, attemptTimeout)
+		reply, err := a2a.NewClient(base+"/agents/"+agent).Send(attemptCtx, probe)
+		cancel()
+		if err == nil && strings.TrimSpace(reply) != "" {
+			return nil
+		}
+		if err == nil {
+			err = fmt.Errorf("empty A2A reply")
+		}
+		lastErr = err
+
+		if time.Until(deadline) <= 0 {
+			return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt, lastErr)
+		}
+		time.Sleep(minDuration(200*time.Millisecond*time.Duration(attempt), time.Until(deadline)))
 	}
-	return nil
+}
+
+func minDuration(a, b time.Duration) time.Duration {
+	if a < b {
+		return a
+	}
+	return b
 }
 
 func providerKey(provider string) string {
@@ -414,7 +463,7 @@ func runUniverse(provider string) int {
 	// Services.
 	inv, pay, ord, ntf := new(Inventory), new(Payment), new(Orders), new(Notify)
 	for name, h := range map[string]any{"inventory": inv, "payment": pay, "orders": ord, "notify": ntf} {
-		svc := service.New(service.Name(name), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl))
+		svc := service.New(service.Name(name), service.Address("127.0.0.1:0"), service.Registry(reg), service.Broker(br), service.Client(cl))
 		svc.Handle(h)
 		go svc.Run()
 	}
@@ -429,6 +478,7 @@ func runUniverse(provider string) int {
 		agent.Address("127.0.0.1:0"),
 		agent.Provider(provider), agent.APIKey(apiKey),
 		agent.MaxSteps(5),
+		agent.WithBroker(br),
 		agent.WrapTool(func(next ai.ToolHandler) ai.ToolHandler {
 			return func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
 				atomic.AddInt64(&wrapped, 1)

internal/harness/universe/main_test.go

@@ -3,6 +3,9 @@ package main
 import (
 	"context"
 	"errors"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
 	"sync/atomic"
 	"testing"
 	"time"
@@ -25,6 +28,31 @@ func TestUniverseHarnessContract(t *testing.T) {
 	}
 }
 
+func TestA2AReachableRetriesTransientTimeout(t *testing.T) {
+	var calls int64
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if got, want := r.URL.Path, "/agents/concierge"; got != want {
+			t.Fatalf("path = %q, want %q", got, want)
+		}
+		if atomic.AddInt64(&calls, 1) == 1 {
+			time.Sleep(5 * time.Second)
+			return
+		}
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprint(w, `{"jsonrpc":"2.0","id":1,"result":{"kind":"task","id":"task-1","contextId":"ctx-1","status":{"state":"completed"},"artifacts":[{"artifactId":"artifact-1","parts":[{"kind":"text","text":"concierge reachable"}]}]}}`)
+	}))
+	defer srv.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 6*time.Second)
+	defer cancel()
+	if err := a2aReachable(ctx, srv.URL, "concierge"); err != nil {
+		t.Fatalf("a2aReachable returned error: %v", err)
+	}
+	if got := atomic.LoadInt64(&calls); got < 2 {
+		t.Fatalf("A2A calls = %d, want retry after transient timeout", got)
+	}
+}
+
 func TestNotifyStepCompletesAfterObservedSideEffectTimeout(t *testing.T) {
 	ntf := new(Notify)
 	before := atomic.LoadInt64(&ntf.sent)
@@ -69,6 +97,42 @@ func TestNotifyStepCompletesAfterObservedSideEffectTimeout(t *testing.T) {
 	}
 }
 
+func TestNotifyStepWaitsForObservedSideEffectAfterCanceledDispatchContext(t *testing.T) {
+	ntf := new(Notify)
+	before := atomic.LoadInt64(&ntf.sent)
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	go func() {
+		time.Sleep(30 * time.Millisecond)
+		var rsp SendResponse
+		if err := ntf.Send(context.Background(), &SendRequest{
+			To:      "buyer@acme.com",
+			Message: "Your order is confirmed.",
+		}, &rsp); err != nil {
+			t.Errorf("send notification: %v", err)
+		}
+	}()
+
+	out, err := completeNotifyOnObservedSideEffect(
+		ctx,
+		flow.State{Data: []byte(`{"order":"order-1"}`)},
+		ntf,
+		before,
+		time.Second,
+		errors.New("client observed timeout"),
+	)
+	if err != nil {
+		t.Fatalf("notify completion returned error: %v", err)
+	}
+	if got := out.String(); got != "Buyer notified." {
+		t.Fatalf("result = %q, want Buyer notified.", got)
+	}
+	if got := atomic.LoadInt64(&ntf.sent); got != 1 {
+		t.Fatalf("notifications sent = %d, want 1", got)
+	}
+}
+
 func TestNotifyStepRejectsClaimedCompletionWithoutSideEffect(t *testing.T) {
 	ntf := new(Notify)
 	before := atomic.LoadInt64(&ntf.sent)

internal/harness/zero-to-hero-ci/README.md

@@ -4,17 +4,21 @@ This directory owns the no-secret reference scenario for the Go Micro
 services → agents → workflows lifecycle. It is intentionally small and
 scripted so CI can run it on every push without external services or model keys.
 
-`run.sh` verifies five boundaries together:
+`run.sh` verifies the complete first-agent 0→hero contract together:
 
-1. **First agent** — `micro new`, `micro agent preflight`, `micro run`,
-   `micro chat`, and `micro inspect agent <name>` remain available as the
-   documented first-agent walkthrough path.
-2. **Run** — `micro run` remains available as the local development entry point.
-3. **Chat** — `micro chat` remains available as the interactive agent entry point.
-4. **Inspect** — `micro inspect agent <name>` and `micro inspect flow <name>`
-   remain available as the local run-history inspection step, with `micro flow
-   runs` preserving durable workflow history inspection.
-5. **Deploy** — `micro deploy --dry-run <target>` remains available as the
+1. **Scaffold** — the maintained `micro new` 0→1 contract still creates
+   runnable services from a clean workspace.
+2. **First agent** — `micro agent demo`, `micro examples`, `micro agent preflight`,
+   `micro run`, `micro chat`, and `micro inspect agent <name>` remain available
+   as the documented first-agent walkthrough path.
+3. **Run** — `micro run` remains available as the local development entry point.
+4. **Chat** — `micro chat` remains available as the interactive agent entry point.
+5. **Inspect/debugging** — `micro inspect agent <name>`, `micro agent history <name>`,
+   and `micro inspect flow <name>` remain available as the local run-history
+   inspection step. The no-secret debugging smoke seeds durable agent run history
+   and memory, then runs the documented inspect/history commands without provider
+   credentials; `micro flow runs` preserves durable workflow history inspection.
+6. **Deploy** — `micro deploy --dry-run <target>` remains available as the
    deployment-boundary checkpoint. The dry run resolves configured deploy targets
    and services and prints the remote build/copy/systemd/health plan without
    building binaries, opening SSH connections, running `rsync`, or touching
@@ -28,16 +32,23 @@ and A2A with only the LLM mocked.
 
 The default GitHub harness workflow runs this script on every push and pull
 request after the install smoke check and 0→1 scaffold contract. Developers can
-verify the installer seam alone with `make install-smoke`, or run the same
-no-secret contract locally with:
+verify the first-agent on-ramp links and CLI command-output parity with
+`make docs-wayfinding` whenever README or website first-agent breadcrumbs,
+`micro agent demo`, `micro examples`, or `micro zero-to-hero` change. That
+check is provider-free and fails if documented command names, guide links, or
+maintained no-secret example paths drift from the CLI outputs. To verify the
+installed first-run CLI seam alone, use `make install-smoke`; to run just the documented
+agent debugging quickcheck with
+`go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1`,
+or run the same no-secret contract locally with:
 
 ```sh
 make harness
 ```
 
-That target intentionally exercises the install script smoke path, both 0→1
-scaffold variants, the 0→hero scenario, the event-driven agent-flow harness, and
-mock provider conformance, so
+That target intentionally exercises the first-agent docs wayfinding guard, the
+install script smoke path, both 0→1 scaffold variants, the 0→hero scenario, the
+event-driven agent-flow harness, and mock provider conformance, so
 the public scaffold → run/chat → inspect → deploy lifecycle stays executable
 outside CI as well. Live provider checks remain separate and gated by configured
 API keys (`make provider-conformance` or the scheduled/manual CI job).

internal/harness/zero-to-hero-ci/docs_test.go

@@ -1,11 +1,18 @@
 package zerotoheroci
 
 import (
+	"encoding/json"
 	"os"
+	"os/exec"
 	"path/filepath"
 	"regexp"
 	"strings"
+	"sync"
 	"testing"
+	"time"
+
+	goagent "go-micro.dev/v6/agent"
+	"go-micro.dev/v6/store"
 )
 
 func TestZeroToHeroReferenceDocs(t *testing.T) {
@@ -14,13 +21,15 @@ func TestZeroToHeroReferenceDocs(t *testing.T) {
 	guide := readFile(t, filepath.Join(root, "internal", "website", "docs", "guides", "zero-to-hero.md"))
 	for _, want := range []string{
 		"make harness",
+		"make inner-loop",
 		"go test ./cmd/micro/cli/new -run TestZeroToOne -count=1",
 		"go test ./cmd/micro -run TestFirstAgentWalkthroughCLIBoundaries -count=1",
 		"go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1",
 		"go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1",
 		"go test ./examples/first-agent -run TestRunFirstAgent -count=1",
-		"go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle' -count=1",
+		"go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle|TestZeroToHeroInspectTranscript' -count=1",
 		"./internal/harness/zero-to-hero-ci/run.sh",
+		"micro zero-to-hero",
 		"go run ./internal/harness/agent-flow",
 		"make provider-conformance-mock",
 		"internal/harness/plan-delegate",
@@ -31,10 +40,39 @@ func TestZeroToHeroReferenceDocs(t *testing.T) {
 		}
 	}
 
+	runScript := readFile(t, filepath.Join(root, "internal", "harness", "zero-to-hero-ci", "run.sh"))
+	for _, want := range []string{
+		"go test ./cmd/micro/cli/new -run TestZeroToOne -count=1",
+		"go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestExamplesWayfindingIndexStaysLinked|TestExamplesCommandPointsAtWayfindingIndex|TestZeroToHeroCLIBoundaries|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1",
+		"go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1",
+		"go test ./examples/first-agent -run TestRunFirstAgent -count=1",
+		"go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle|TestZeroToHeroInspectTranscript' -count=1",
+	} {
+		if !strings.Contains(runScript, want) {
+			t.Fatalf("0→hero CI run script missing lifecycle command %q", want)
+		}
+	}
+	for _, want := range []string{
+		"scaffold:",
+		"run/chat/inspect:",
+		"deploy dry-run:",
+		"chat/inspect:",
+		"first-agent app:",
+		"0→hero app:",
+		"flow history:",
+	} {
+		if !strings.Contains(runScript, want) {
+			t.Fatalf("0→hero CI run script missing debuggable boundary label %q", want)
+		}
+	}
+
 	readme := readFile(t, filepath.Join(root, "README.md"))
 	if !strings.Contains(readme, "internal/website/docs/guides/zero-to-hero.md") {
 		t.Fatal("README does not point to the canonical 0→hero guide")
 	}
+	if !strings.Contains(readme, "make inner-loop") {
+		t.Fatal("README does not expose the focused CLI inner-loop contract")
+	}
 
 	nav := readFile(t, filepath.Join(root, "internal", "website", "_data", "navigation.yml"))
 	if !strings.Contains(nav, "0→hero Reference") || !strings.Contains(nav, "/docs/guides/zero-to-hero.html") {
@@ -42,6 +80,62 @@ func TestZeroToHeroReferenceDocs(t *testing.T) {
 	}
 }
 
+func TestZeroToHeroDeployDryRunCommandSmoke(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	absRoot, err := filepath.Abs(root)
+	if err != nil {
+		t.Fatalf("resolve repository root: %v", err)
+	}
+
+	bin := filepath.Join(t.TempDir(), "micro")
+	build := exec.Command("go", "build", "-o", bin, "./cmd/micro")
+	build.Dir = absRoot
+	if out, err := build.CombinedOutput(); err != nil {
+		t.Fatalf("build micro CLI for deploy dry-run smoke: %v\n%s", err, out)
+	}
+
+	workspace := t.TempDir()
+	writeFile(t, filepath.Join(workspace, "micro.mu"), `service api
+    path ./api
+
+deploy prod
+    ssh deploy@prod.example.com
+    path /srv/micro
+`)
+	if err := os.Mkdir(filepath.Join(workspace, "api"), 0o755); err != nil {
+		t.Fatalf("create service dir: %v", err)
+	}
+
+	cmd := exec.Command(bin, "deploy", "--dry-run", "prod")
+	cmd.Dir = workspace
+	cmd.Env = append(os.Environ(), "MICRO_CONFIG_FILE="+filepath.Join(workspace, "micro.mu"))
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("documented deploy dry-run command failed: %v\n%s", err, out)
+	}
+
+	got := string(out)
+	for _, want := range []string{
+		"micro deploy --dry-run",
+		"Target",
+		"deploy@prod.example.com",
+		"Remote path",
+		"/srv/micro",
+		"Services",
+		"api",
+		"No SSH, rsync, systemd, or remote deployment was performed.",
+	} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("deploy dry-run output missing %q:\n%s", want, got)
+		}
+	}
+
+	guide := readFile(t, filepath.Join(absRoot, "internal", "website", "docs", "guides", "zero-to-hero.md"))
+	if !strings.Contains(guide, "micro deploy --dry-run prod") {
+		t.Fatal("0→hero guide must document the same deploy dry-run command covered by CI")
+	}
+}
+
 func TestGuidesNavigationLeadsWithDoing(t *testing.T) {
 	root := filepath.Clean(filepath.Join("..", "..", ".."))
 	nav := readFile(t, filepath.Join(root, "internal", "website", "_data", "navigation.yml"))
@@ -76,6 +170,76 @@ func TestGuidesNavigationLeadsWithDoing(t *testing.T) {
 	}
 }
 
+func TestYourFirstAgentTutorialSmoke(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	absRoot, err := filepath.Abs(root)
+	if err != nil {
+		t.Fatalf("resolve repository root: %v", err)
+	}
+	guide := readFile(t, filepath.Join(root, "internal", "website", "docs", "guides", "your-first-agent.md"))
+
+	for _, want := range []string{
+		"go test ./internal/harness/zero-to-hero-ci -run TestYourFirstAgentTutorialSmoke -count=1",
+		"micro agent preflight",
+		"mkdir first-agent",
+		"go mod init example.com/first-agent",
+		"go get go-micro.dev/v6@v6",
+		"micro run",
+		"micro call task TaskService.Create",
+		"micro call task TaskService.List",
+		"micro chat assistant",
+		"micro inspect agent assistant",
+	} {
+		if !strings.Contains(guide, want) {
+			t.Fatalf("Your First Agent guide missing copy/paste boundary %q", want)
+		}
+	}
+
+	mainGo := extractFirstAgentMain(t, guide)
+	workspace := t.TempDir()
+	writeFile(t, filepath.Join(workspace, "go.mod"), "module example.com/first-agent\n\ngo 1.24\n\nrequire go-micro.dev/v6 v6.0.0\n\nreplace go-micro.dev/v6 => "+absRoot+"\n")
+	writeFile(t, filepath.Join(workspace, "main.go"), mainGo)
+
+	runInWorkspace(t, workspace, "go", "mod", "tidy")
+	runInWorkspace(t, workspace, "go", "test", "./...")
+}
+
+func extractFirstAgentMain(t *testing.T, guide string) string {
+	t.Helper()
+	start := strings.Index(guide, "Add `main.go`:")
+	if start == -1 {
+		t.Fatal("Your First Agent guide is missing the main.go section")
+	}
+	rest := guide[start:]
+	open := strings.Index(rest, "```go")
+	if open == -1 {
+		t.Fatal("Your First Agent guide is missing a Go code fence for main.go")
+	}
+	rest = rest[open+len("```go"):]
+	close := strings.Index(rest, "```")
+	if close == -1 {
+		t.Fatal("Your First Agent guide main.go code fence is not closed")
+	}
+	return strings.TrimSpace(rest[:close]) + "\n"
+}
+
+func writeFile(t *testing.T, name, contents string) {
+	t.Helper()
+	if err := os.WriteFile(name, []byte(contents), 0o644); err != nil {
+		t.Fatalf("write %s: %v", name, err)
+	}
+}
+
+func runInWorkspace(t *testing.T, workspace, name string, args ...string) {
+	t.Helper()
+	cmd := exec.Command(name, args...)
+	cmd.Dir = workspace
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("Your First Agent tutorial command %q does not pass from a clean workspace: %v\n%s", strings.Join(append([]string{name}, args...), " "), err, out)
+	}
+}
+
 func TestArchitectureDocsAlignWithAgentHarnessLifecycle(t *testing.T) {
 	root := filepath.Clean(filepath.Join("..", "..", ".."))
 	doc := readFile(t, filepath.Join(root, "internal", "website", "docs", "architecture.md"))
@@ -125,10 +289,15 @@ func TestFirstAgentWayfindingDocs(t *testing.T) {
 			heading: "### First agent on-ramp",
 			links: []string{
 				"internal/website/docs/guides/install-troubleshooting.md",
+				"make docs-wayfinding",
 				"micro agent demo",
+				"micro examples",
+				"micro zero-to-hero",
 				"internal/website/docs/guides/no-secret-first-agent.md",
 				"internal/website/docs/guides/your-first-agent.md",
+				"micro chat",
 				"internal/website/docs/guides/debugging-agents.md",
+				"micro inspect agent <name>",
 				"internal/website/docs/guides/zero-to-hero.md",
 			},
 		},
@@ -150,6 +319,27 @@ func TestFirstAgentWayfindingDocs(t *testing.T) {
 				"./support/",
 			},
 		},
+		{
+			name:    "repository examples wayfinding index",
+			file:    filepath.Join(root, "examples", "INDEX.md"),
+			heading: "## Recommended adoption path",
+			links: []string{
+				"./hello-world/",
+				"./first-agent/",
+				"./support/",
+			},
+		},
+		{
+			name:    "micro README first-agent on-ramp",
+			file:    filepath.Join(root, "cmd", "micro", "README.md"),
+			heading: "## First agent on-ramp",
+			links: []string{
+				"make docs-wayfinding",
+				"micro agent demo",
+				"micro examples",
+				"micro zero-to-hero",
+			},
+		},
 		{
 			name:    "website examples index",
 			file:    filepath.Join(root, "internal", "website", "docs", "examples", "index.md"),
@@ -168,10 +358,54 @@ func TestFirstAgentWayfindingDocs(t *testing.T) {
 			heading: "### First-agent on-ramp",
 			links: []string{
 				"guides/install-troubleshooting.html",
+				"make docs-wayfinding",
 				"micro agent demo",
+				"micro examples",
+				"micro zero-to-hero",
+				"https://github.com/micro/go-micro/blob/master/examples/INDEX.md",
+				"https://github.com/micro/go-micro/tree/master/examples/support",
+				"https://github.com/micro/go-micro/tree/master/examples/first-agent",
 				"guides/no-secret-first-agent.html",
 				"guides/your-first-agent.html",
+				"micro chat",
 				"guides/debugging-agents.html",
+				"micro inspect agent <name>",
+				"guides/zero-to-hero.html",
+			},
+		},
+		{
+			name:    "website quickstart next steps",
+			file:    filepath.Join(root, "internal", "website", "docs", "quickstart.md"),
+			heading: "## Next Steps",
+			links: []string{
+				"guides/install-troubleshooting.html",
+				"micro agent demo",
+				"micro examples",
+				"micro zero-to-hero",
+				"https://github.com/micro/go-micro/blob/master/examples/INDEX.md",
+				"https://github.com/micro/go-micro/tree/master/examples/support",
+				"https://github.com/micro/go-micro/tree/master/examples/first-agent",
+				"guides/no-secret-first-agent.html",
+				"guides/your-first-agent.html",
+				"micro chat",
+				"guides/debugging-agents.html",
+				"micro inspect agent <name>",
+				"guides/zero-to-hero.html",
+			},
+		},
+		{
+			name:    "website docs index learn more",
+			file:    filepath.Join(root, "internal", "website", "docs", "index.md"),
+			heading: "## Learn More",
+			links: []string{
+				"getting-started.html",
+				"https://github.com/micro/go-micro/blob/master/examples/INDEX.md",
+				"https://github.com/micro/go-micro/tree/master/examples/support",
+				"guides/no-secret-first-agent.html",
+				"guides/your-first-agent.html",
+				"micro chat",
+				"guides/debugging-agents.html",
+				"micro inspect agent <name>",
 				"guides/zero-to-hero.html",
 			},
 		},
@@ -196,6 +430,108 @@ func TestFirstAgentWayfindingDocs(t *testing.T) {
 	}
 }
 
+func TestFirstAgentWayfindingCanonicalTrailStaysInSync(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	onRampTrail := []string{
+		"micro agent demo",
+		"micro examples",
+		"micro zero-to-hero",
+		"examples/INDEX.md",
+		"examples/first-agent",
+		"examples/support",
+		"no-secret-first-agent",
+		"your-first-agent",
+		"micro chat",
+		"debugging-agents",
+		"micro inspect agent <name>",
+		"zero-to-hero",
+	}
+	checks := []struct {
+		name    string
+		file    string
+		heading string
+		markers []string
+	}{
+		{
+			name:    "README first-agent on-ramp",
+			file:    filepath.Join(root, "README.md"),
+			heading: "### First agent on-ramp",
+			markers: onRampTrail,
+		},
+		{
+			name:    "website docs index first-agent path",
+			file:    filepath.Join(root, "internal", "website", "docs", "index.md"),
+			heading: "## Learn More",
+			markers: onRampTrail,
+		},
+		{
+			name:    "website getting-started first-agent on-ramp",
+			file:    filepath.Join(root, "internal", "website", "docs", "getting-started.md"),
+			heading: "### First-agent on-ramp",
+			markers: onRampTrail,
+		},
+		{
+			name:    "website quickstart next steps",
+			file:    filepath.Join(root, "internal", "website", "docs", "quickstart.md"),
+			heading: "## Next Steps",
+			markers: onRampTrail,
+		},
+		{
+			name:    "examples map recommended adoption path",
+			file:    filepath.Join(root, "examples", "INDEX.md"),
+			heading: "",
+			markers: []string{
+				"micro examples",
+				"micro zero-to-hero",
+				"examples/INDEX.md",
+				"examples/first-agent",
+				"examples/support",
+				"zero-to-hero",
+			},
+		},
+		{
+			name:    "no-secret first-agent guide next steps",
+			file:    filepath.Join(root, "internal", "website", "docs", "guides", "no-secret-first-agent.md"),
+			heading: "",
+			markers: []string{
+				"micro agent demo",
+				"examples/first-agent",
+				"examples/support",
+				"your-first-agent",
+				"micro chat",
+				"debugging-agents",
+				"micro inspect agent <name>",
+			},
+		},
+		{
+			name:    "0→hero guide related examples",
+			file:    filepath.Join(root, "internal", "website", "docs", "guides", "zero-to-hero.md"),
+			heading: "",
+			markers: []string{
+				"micro zero-to-hero",
+				"examples/first-agent",
+				"examples/support",
+				"micro inspect agent <name>",
+				"zero-to-hero",
+			},
+		},
+	}
+
+	for _, check := range checks {
+		t.Run(check.name, func(t *testing.T) {
+			section := readFile(t, check.file)
+			if check.heading != "" {
+				section = firstMarkdownSection(t, section, check.heading)
+			}
+			for _, marker := range check.markers {
+				if !containsWayfindingMarker(section, marker) {
+					t.Fatalf("%s missing canonical first-agent wayfinding marker %q; keep README, website, examples, no-secret, and 0→hero surfaces aligned", check.name, marker)
+				}
+			}
+		})
+	}
+}
+
 func TestFirstAgentWayfindingLinkTargetsResolve(t *testing.T) {
 	root := filepath.Clean(filepath.Join("..", "..", ".."))
 	checks := []struct {
@@ -218,6 +554,11 @@ func TestFirstAgentWayfindingLinkTargetsResolve(t *testing.T) {
 			file:    filepath.Join(root, "examples", "README.md"),
 			heading: "## Recommended first-agent path",
 		},
+		{
+			name:    "repository examples wayfinding index",
+			file:    filepath.Join(root, "examples", "INDEX.md"),
+			heading: "## Recommended adoption path",
+		},
 		{
 			name:    "website examples index",
 			file:    filepath.Join(root, "internal", "website", "docs", "examples", "index.md"),
@@ -228,6 +569,16 @@ func TestFirstAgentWayfindingLinkTargetsResolve(t *testing.T) {
 			file:    filepath.Join(root, "internal", "website", "docs", "getting-started.md"),
 			heading: "### First-agent on-ramp",
 		},
+		{
+			name:    "website quickstart next steps",
+			file:    filepath.Join(root, "internal", "website", "docs", "quickstart.md"),
+			heading: "## Next Steps",
+		},
+		{
+			name:    "website docs index learn more",
+			file:    filepath.Join(root, "internal", "website", "docs", "index.md"),
+			heading: "## Learn More",
+		},
 	}
 
 	for _, check := range checks {
@@ -244,6 +595,99 @@ func TestFirstAgentWayfindingLinkTargetsResolve(t *testing.T) {
 	}
 }
 
+func TestFirstAgentGuideChainDocumentsRequiredNextSteps(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	checks := []struct {
+		name    string
+		file    string
+		markers []string
+	}{
+		{
+			name: "no-secret transcript hands off to live build and debug",
+			file: filepath.Join(root, "internal", "website", "docs", "guides", "no-secret-first-agent.md"),
+			markers: []string{
+				"micro agent demo",
+				"go run ./examples/first-agent",
+				"go run ./examples/support",
+				"go test ./examples/first-agent -run TestRunFirstAgent -count=1",
+				"go test ./examples/support -run TestRunSupportMockSmoke -count=1",
+				"make harness",
+				"micro agent preflight",
+				"micro run",
+				"micro chat assistant",
+				"micro inspect agent assistant",
+				"Debugging your agent",
+				"debugging-agents.html",
+			},
+		},
+		{
+			name: "your-first-agent keeps no-secret, preflight, doctor, inspect, and debug nearby",
+			file: filepath.Join(root, "internal", "website", "docs", "guides", "your-first-agent.md"),
+			markers: []string{
+				"no-secret-first-agent.html",
+				"go run ./examples/support",
+				"micro agent preflight",
+				"micro agent doctor",
+				"micro run",
+				"micro chat assistant",
+				"micro inspect agent assistant",
+				"debugging-agents.html",
+				"zero-to-hero.html",
+			},
+		},
+		{
+			name: "debugging guide starts at install/preflight and preserves inspect/history recovery",
+			file: filepath.Join(root, "internal", "website", "docs", "guides", "debugging-agents.md"),
+			markers: []string{
+				"install-troubleshooting.html",
+				"micro agent preflight",
+				"micro agent doctor",
+				"micro run",
+				"micro chat",
+				"micro inspect agent support",
+				"micro agent history",
+				"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1",
+			},
+		},
+		{
+			name: "zero-to-hero guide exposes the provider-free contract commands",
+			file: filepath.Join(root, "internal", "website", "docs", "guides", "zero-to-hero.md"),
+			markers: []string{
+				"go test ./internal/harness/zero-to-hero-ci -run TestFirstAgentWayfinding -count=1",
+				"micro zero-to-hero",
+				"go run ./examples/first-agent",
+				"go run ./examples/support",
+				"make harness",
+				"go test ./cmd/micro -run TestFirstAgentWalkthroughCLIBoundaries -count=1",
+				"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1",
+				"make provider-conformance-mock",
+			},
+		},
+	}
+
+	for _, check := range checks {
+		t.Run(check.name, func(t *testing.T) {
+			doc := readFile(t, check.file)
+			for _, marker := range check.markers {
+				if !strings.Contains(doc, marker) {
+					t.Fatalf("%s missing required first-agent next-step marker %q", check.name, marker)
+				}
+				if firstAgentMarkerIsLink(marker) {
+					assertWayfindingTargetExists(t, root, check.file, marker)
+				}
+			}
+		})
+	}
+}
+
+func firstAgentMarkerIsLink(marker string) bool {
+	return strings.HasSuffix(marker, ".html") ||
+		strings.HasSuffix(marker, ".md") ||
+		strings.HasPrefix(marker, "./") ||
+		strings.HasPrefix(marker, "../") ||
+		strings.HasPrefix(marker, "https://github.com/micro/go-micro/")
+}
+
 func TestFirstAgentLifecycleCommandOrderIsDocumented(t *testing.T) {
 	root := filepath.Clean(filepath.Join("..", "..", ".."))
 	checks := []struct {
@@ -414,8 +858,10 @@ func TestGettingStartedDocsLeadWithNoSecretFirstRun(t *testing.T) {
 				"curl -X POST http://localhost:8080/api/helloworld/Helloworld.Call",
 				"## Next Steps",
 				"micro agent demo",
+				"micro zero-to-hero",
 				"guides/no-secret-first-agent.html",
 				"guides/debugging-agents.html",
+				"micro inspect agent <name>",
 				"guides/zero-to-hero.html",
 			},
 		},
@@ -483,6 +929,24 @@ func TestNoSecretFirstAgentTranscript(t *testing.T) {
 		}
 	}
 
+	debuggingGuide := readFile(t, filepath.Join(root, "internal", "website", "docs", "guides", "debugging-agents.md"))
+	for _, want := range []string{
+		"Provider-free quickcheck",
+		"go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1",
+		"micro inspect agent assistant --limit 1",
+		"micro inspect agent --status done",
+		"micro agent history assistant",
+	} {
+		if !strings.Contains(debuggingGuide, want) {
+			t.Fatalf("debugging guide missing provider-free quickcheck marker %q", want)
+		}
+	}
+
+	harnessReadme := readFile(t, filepath.Join(root, "internal", "harness", "zero-to-hero-ci", "README.md"))
+	if !strings.Contains(harnessReadme, "go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1") {
+		t.Fatal("0→hero harness README does not expose the agent debugging quickcheck command")
+	}
+
 	readme := readFile(t, filepath.Join(root, "README.md"))
 	if !strings.Contains(readme, "internal/website/docs/guides/no-secret-first-agent.md") {
 		t.Fatal("README does not point to the no-secret first-agent transcript")
@@ -494,6 +958,298 @@ func TestNoSecretFirstAgentTranscript(t *testing.T) {
 	}
 }
 
+func TestNoSecretFirstAgentDebuggingSmoke(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	home := t.TempDir()
+	storeDir := filepath.Join(home, "micro", "store")
+	st := store.NewFileStore(store.DirOption(storeDir))
+
+	seedNoSecretAgentDebuggingState(t, st)
+	if err := st.Close(); err != nil {
+		t.Fatalf("close seeded store: %v", err)
+	}
+
+	micro := buildMicroBinary(t, root)
+
+	for _, tc := range []struct {
+		name string
+		args []string
+		want []string
+	}{
+		{
+			name: "demo advertises provider-free debug path",
+			args: []string{"agent", "demo"},
+			want: []string{"No-secret first-agent demo", "provider-free", "run history", "micro inspect agent <name>"},
+		},
+		{
+			name: "inspect shows seeded run history",
+			args: []string{"inspect", "agent", "assistant", "--limit", "1"},
+			want: []string{`Agent "assistant" runs`, "run-debug-smoke", "status=done", "events=3", "last=done", "trace=trace-debug-"},
+		},
+		{
+			name: "inspect filters documented statuses",
+			args: []string{"inspect", "agent", "--status", "done", "--json", "assistant"},
+			want: []string{"run-debug-smoke", `"status": "done"`, `"trace_id": "trace-debug-smoke"`},
+		},
+		{
+			name: "agent history shows memory and run index",
+			args: []string{"agent", "history", "assistant"},
+			want: []string{"user:", "Triage ticket-1", "assistant:", "ticket-1 is ready", "Runs:", "run-debug-smoke", "status=done"},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			out := runMicroCLIWithHome(t, micro, home, tc.args...)
+			for _, want := range tc.want {
+				if !strings.Contains(out, want) {
+					t.Fatalf("micro %s output missing %q:\n%s", strings.Join(tc.args, " "), want, out)
+				}
+			}
+		})
+	}
+}
+
+func TestFirstAgentCLIChatInspectFixture(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	absRoot, err := filepath.Abs(root)
+	if err != nil {
+		t.Fatalf("resolve repository root: %v", err)
+	}
+
+	workspace := t.TempDir()
+	home := filepath.Join(workspace, "home")
+	if err := os.MkdirAll(home, 0o755); err != nil {
+		t.Fatalf("create fixture home: %v", err)
+	}
+	writeFile(t, filepath.Join(workspace, "go.mod"), "module example.com/first-agent-cli-fixture\n\ngo 1.24\n\nrequire go-micro.dev/v6 v6.0.0\n\nreplace go-micro.dev/v6 => "+filepath.ToSlash(absRoot)+"\n")
+	writeFile(t, filepath.Join(workspace, "main.go"), firstAgentCLIFixtureSource())
+	runInWorkspace(t, workspace, "go", "mod", "tidy")
+
+	micro := buildMicroBinary(t, absRoot)
+	fixtureBin := filepath.Join(workspace, "first-agent-cli-fixture")
+	runInWorkspace(t, workspace, "go", "build", "-o", fixtureBin, ".")
+	fixture := exec.Command(fixtureBin)
+	fixture.Dir = workspace
+	fixture.Env = append(os.Environ(),
+		"HOME="+home,
+		"MICRO_AI_API_KEY=",
+		"OPENAI_API_KEY=",
+		"ANTHROPIC_API_KEY=",
+		"GEMINI_API_KEY=",
+	)
+	var fixtureOut lockedBuffer
+	fixture.Stdout = &fixtureOut
+	fixture.Stderr = &fixtureOut
+	if err := fixture.Start(); err != nil {
+		t.Fatalf("start first-agent CLI fixture: %v\n%s", err, fixtureOut.String())
+	}
+	defer func() {
+		if fixture.Process != nil {
+			_ = fixture.Process.Signal(os.Interrupt)
+			_ = fixture.Process.Kill()
+		}
+	}()
+
+	waitForCLIOutput(t, &fixtureOut, "first-agent fixture ready", 15*time.Second)
+	waitForRegisteredAgent(t, micro, home, "assistant", &fixtureOut, 15*time.Second)
+
+	chat := runMicroCLIWithHome(t, micro, home, "chat", "--prompt", "Summarize my first-agent next steps", "assistant")
+	for _, want := range []string{"assistant:", "install the CLI", "run a service", "chat with an agent"} {
+		if !strings.Contains(chat, want) {
+			t.Fatalf("micro chat assistant output missing %q:\n%s\nfixture output:\n%s", want, chat, fixtureOut.String())
+		}
+	}
+
+	stopFixture(t, fixture)
+
+	inspect := runMicroCLIWithHome(t, micro, home, "inspect", "agent", "assistant", "--limit", "1")
+	for _, want := range []string{`Agent "assistant" runs`, "status=done", "last=done"} {
+		if !strings.Contains(inspect, want) {
+			t.Fatalf("micro inspect agent assistant output missing %q:\n%s\nfixture output:\n%s", want, inspect, fixtureOut.String())
+		}
+	}
+}
+
+func stopFixture(t *testing.T, cmd *exec.Cmd) {
+	t.Helper()
+	if cmd.Process == nil {
+		return
+	}
+	done := make(chan error, 1)
+	_ = cmd.Process.Signal(os.Interrupt)
+	go func() { done <- cmd.Wait() }()
+	select {
+	case <-done:
+	case <-time.After(2 * time.Second):
+		_ = cmd.Process.Kill()
+		<-done
+	}
+}
+
+func waitForCLIOutput(t *testing.T, out *lockedBuffer, want string, timeout time.Duration) {
+	t.Helper()
+	deadline := time.Now().Add(timeout)
+	for time.Now().Before(deadline) {
+		if strings.Contains(out.String(), want) {
+			return
+		}
+		time.Sleep(100 * time.Millisecond)
+	}
+	t.Fatalf("timed out waiting for fixture output %q; got:\n%s", want, out.String())
+}
+
+func waitForRegisteredAgent(t *testing.T, micro, home, agent string, fixtureOut *lockedBuffer, timeout time.Duration) {
+	t.Helper()
+	deadline := time.Now().Add(timeout)
+	var lastOut []byte
+	var lastErr error
+	for time.Now().Before(deadline) {
+		cmd := exec.Command(micro, "agent", "list")
+		cmd.Env = microCLIEnv(home)
+		lastOut, lastErr = cmd.CombinedOutput()
+		if lastErr == nil && strings.Contains(string(lastOut), agent) {
+			return
+		}
+		time.Sleep(100 * time.Millisecond)
+	}
+	t.Fatalf("timed out waiting for registered agent %q; last micro agent list error: %v\nlast output:\n%s\nfixture output:\n%s", agent, lastErr, lastOut, fixtureOut.String())
+}
+
+type lockedBuffer struct {
+	mu sync.Mutex
+	b  strings.Builder
+}
+
+func (b *lockedBuffer) Write(p []byte) (int, error) {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return b.b.Write(p)
+}
+
+func (b *lockedBuffer) String() string {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return b.b.String()
+}
+
+func firstAgentCLIFixtureSource() string {
+	return `package main
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"os/signal"
+	"path/filepath"
+	"strings"
+	"syscall"
+
+	"go-micro.dev/v6/agent"
+	"go-micro.dev/v6/ai"
+	"go-micro.dev/v6/service"
+	"go-micro.dev/v6/store"
+)
+
+type NotesService struct{}
+type ListNotesRequest struct{}
+type ListNotesResponse struct { Notes []string ` + "`json:\"notes\" description:\"Notes the assistant can summarize\"`" + ` }
+
+func (s *NotesService) List(ctx context.Context, req *ListNotesRequest, rsp *ListNotesResponse) error {
+	rsp.Notes = []string{"Install the CLI", "Run a service", "Chat with an agent"}
+	return nil
+}
+
+type mockModel struct{ opts ai.Options }
+func newMock(opts ...ai.Option) ai.Model { m := &mockModel{}; _ = m.Init(opts...); return m }
+func (m *mockModel) Init(opts ...ai.Option) error { for _, o := range opts { o(&m.opts) }; return nil }
+func (m *mockModel) Options() ai.Options { return m.opts }
+func (m *mockModel) String() string { return "first-agent-cli-fixture" }
+func (m *mockModel) Stream(context.Context, *ai.Request, ...ai.GenerateOption) (ai.Stream, error) { return nil, fmt.Errorf("stream unsupported") }
+func (m *mockModel) Generate(ctx context.Context, req *ai.Request, _ ...ai.GenerateOption) (*ai.Response, error) {
+	for _, tool := range req.Tools { if strings.Contains(tool.Name, "List") && m.opts.ToolHandler != nil { m.opts.ToolHandler(ctx, ai.ToolCall{ID:"list-notes", Name: tool.Name, Input: map[string]any{}}); break } }
+	return &ai.Response{Answer: "assistant: your first agent should install the CLI, run a service, then chat with an agent."}, nil
+}
+
+func main() {
+	ai.Register("first-agent-cli-fixture", newMock)
+	home, _ := os.UserHomeDir()
+	st := store.NewFileStore(store.DirOption(filepath.Join(home, "micro", "store")))
+	defer st.Close()
+
+	svc := service.New(service.Name("notes"), service.Address("127.0.0.1:0"))
+	if err := svc.Handle(&NotesService{}); err != nil { panic(err) }
+	go func() { if err := svc.Run(); err != nil { fmt.Println(err); os.Exit(1) } }()
+	defer svc.Server().Stop()
+
+	a := agent.New(agent.Name("assistant"), agent.Address("127.0.0.1:0"), agent.Services("notes"), agent.Provider("first-agent-cli-fixture"), agent.WithStore(st))
+	go func() { if err := a.Run(); err != nil { fmt.Println(err); os.Exit(1) } }()
+	defer a.Stop()
+
+	fmt.Println("first-agent fixture ready")
+	stop := make(chan os.Signal, 1)
+	signal.Notify(stop, os.Interrupt, syscall.SIGTERM)
+	<-stop
+}
+`
+}
+
+func seedNoSecretAgentDebuggingState(t *testing.T, st store.Store) {
+	t.Helper()
+	scoped := store.Scope(st, "agent", "assistant")
+	runID := "run-debug-smoke"
+	events := []goagent.RunEvent{
+		{Time: time.Unix(1700000000, 0), RunID: runID, Agent: "assistant", TraceID: "trace-debug-smoke", Kind: "run", Name: "ask"},
+		{Time: time.Unix(1700000001, 0), RunID: runID, Agent: "assistant", TraceID: "trace-debug-smoke", Kind: "model", Provider: "mock", Model: "first-agent-mock"},
+		{Time: time.Unix(1700000002, 0), RunID: runID, Agent: "assistant", TraceID: "trace-debug-smoke", Kind: "done", Name: "answer"},
+	}
+	for _, event := range events {
+		b, err := json.Marshal(event)
+		if err != nil {
+			t.Fatal(err)
+		}
+		key := "runs/" + event.RunID + "/" + event.Time.Format("20060102150405.000000000") + "-" + event.Kind
+		if err := scoped.Write(&store.Record{Key: key, Value: b}); err != nil {
+			t.Fatalf("seed run event: %v", err)
+		}
+	}
+
+	mem := goagent.NewMemory(scoped, "history", 10)
+	mem.Add("user", "Triage ticket-1 for Alice")
+	mem.Add("assistant", "ticket-1 is ready for Alice without provider secrets")
+}
+
+func buildMicroBinary(t *testing.T, root string) string {
+	t.Helper()
+	bin := filepath.Join(t.TempDir(), "micro")
+	cmd := exec.Command("go", "build", "-o", bin, "./cmd/micro")
+	cmd.Dir = root
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("build micro CLI failed: %v\n%s", err, out)
+	}
+	return bin
+}
+
+func runMicroCLIWithHome(t *testing.T, micro, home string, args ...string) string {
+	t.Helper()
+	cmd := exec.Command(micro, args...)
+	cmd.Env = microCLIEnv(home)
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("micro %s failed: %v\n%s", strings.Join(args, " "), err, out)
+	}
+	return string(out)
+}
+
+func microCLIEnv(home string) []string {
+	return append(os.Environ(),
+		"HOME="+home,
+		"MICRO_AI_API_KEY=",
+		"OPENAI_API_KEY=",
+		"ANTHROPIC_API_KEY=",
+		"GEMINI_API_KEY=",
+	)
+}
+
 func TestFirstAgentWayfindingTargetsExist(t *testing.T) {
 	root := filepath.Clean(filepath.Join("..", "..", ".."))
 	for _, target := range []string{
@@ -546,6 +1302,43 @@ func markdownLinks(section string) []string {
 	return links
 }
 
+func containsWayfindingMarker(section, marker string) bool {
+	if strings.Contains(section, marker) {
+		return true
+	}
+	switch marker {
+	case "examples/INDEX.md":
+		return strings.Contains(section, "examples/INDEX.md") ||
+			strings.Contains(section, "Recommended adoption path") ||
+			strings.Contains(section, "examples wayfinding index") ||
+			strings.Contains(section, "Examples wayfinding index") ||
+			strings.Contains(section, "./INDEX.md")
+	case "examples/first-agent":
+		return strings.Contains(section, "examples/first-agent") ||
+			strings.Contains(section, "./first-agent")
+	case "examples/support":
+		return strings.Contains(section, "examples/support") ||
+			strings.Contains(section, "./support")
+	case "no-secret-first-agent":
+		return strings.Contains(section, "no-secret-first-agent") ||
+			strings.Contains(section, "No-secret First Agent")
+	case "your-first-agent":
+		return strings.Contains(section, "your-first-agent") ||
+			strings.Contains(section, "Your First Agent")
+	case "debugging-agents":
+		return strings.Contains(section, "debugging-agents") ||
+			strings.Contains(section, "Debugging your agent")
+	case "zero-to-hero":
+		return strings.Contains(section, "zero-to-hero") ||
+			strings.Contains(section, "0→hero")
+	default:
+		if strings.HasPrefix(marker, "micro inspect agent ") {
+			return strings.Contains(section, "micro inspect agent ")
+		}
+		return false
+	}
+}
+
 func assertWayfindingTargetExists(t *testing.T, root, sourceFile, link string) {
 	t.Helper()
 	if !strings.Contains(link, "/") && !strings.Contains(link, ".") {

internal/harness/zero-to-hero-ci/run.sh

@@ -4,16 +4,36 @@ set -euo pipefail
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)"
 cd "$ROOT"
 
+run_step() {
+  local name=$1
+  shift
+
+  printf '\n==> %s\n' "$name"
+  printf '+ %q' "$@"
+  printf '\n'
+  "$@"
+}
+
 # Keep the developer inner-loop boundaries executable and discoverable in CI
-# without secrets or long-running daemons.
-go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestZeroToHeroCLIBoundaries' -count=1
-go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
-go test ./internal/harness/zero-to-hero-ci -run 'TestNoSecretFirstAgentTranscript|TestZeroToHeroReferenceDocs' -count=1
+# without secrets or long-running daemons. Step names mirror the documented
+# install → scaffold → run/chat → inspect → deploy-dry-run seams so failures
+# identify the broken part of the getting-started contract.
+run_step "scaffold: 0→1 service contract" \
+  go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
+run_step "run/chat/inspect: first-agent CLI boundaries" \
+  go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestExamplesWayfindingIndexStaysLinked|TestExamplesCommandPointsAtWayfindingIndex|TestZeroToHeroCLIBoundaries|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1
+run_step "deploy dry-run: configured target plan" \
+  go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
+run_step "chat/inspect: no-secret first-agent transcript and docs" \
+  go test ./internal/harness/zero-to-hero-ci -run 'TestNoSecretFirstAgentTranscript|TestFirstAgentCLIChatInspectFixture|TestNoSecretFirstAgentDebuggingSmoke|TestZeroToHeroReferenceDocs|TestZeroToHeroDeployDryRunCommandSmoke|TestYourFirstAgentTutorialSmoke' -count=1
 
 # Deterministic no-secret reference scenarios. These use the real Go Micro
 # runtime and mock only the LLM provider. The support example is the maintained
 # runnable 0→hero app; keep it in this CI path so its documented run/chat/inspect
 # journey cannot drift from the framework.
-go test ./examples/first-agent -run TestRunFirstAgent -count=1
-go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle' -count=1
-go test ./internal/harness/universe ./internal/harness/plan-delegate -run 'Test.*Harness|TestPlanDelegateEndToEnd|TestPlanDelegateFlowHandoff' -count=1
+run_step "first-agent app: runnable provider-free example" \
+  go test ./examples/first-agent -run TestRunFirstAgent -count=1
+run_step "0→hero app: support lifecycle smoke" \
+  go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle|TestZeroToHeroInspectTranscript' -count=1
+run_step "flow history: deterministic services → agents → workflows harnesses" \
+  go test ./internal/harness/universe ./internal/harness/plan-delegate -run 'Test.*Harness|TestPlanDelegateEndToEnd|TestPlanDelegateFlowHandoff' -count=1

internal/website/_data/navigation.yml

@@ -42,6 +42,8 @@ examples:
 guides:
   - title: Debugging your agent
     url: /docs/guides/debugging-agents.html
+  - title: micro loop quickstart
+    url: /docs/guides/micro-loop.html
   - title: Plan & Delegate
     url: /docs/guides/plan-delegate.html
   - title: Agent Guardrails
@@ -86,6 +88,7 @@ search_order:
   - /docs/guides/your-first-agent.html
   - /docs/guides/zero-to-hero.html
   - /docs/guides/debugging-agents.html
+  - /docs/guides/micro-loop.html
   - /docs/getting-started.html
   - /docs/mcp.html
   - /docs/architecture.html

internal/website/blog/34.md

@@ -0,0 +1,45 @@
+---
+layout: blog
+title: "What's New in Go Micro: v6.3.15"
+permalink: /blog/34
+description: "Go Micro v6.3.15 tightens the first-agent on-ramp, adds Anthropic streaming, and hardens plan/delegate plus text tool-call recovery."
+---
+
+# What's New in Go Micro: v6.3.15
+
+*July 5, 2026 • By the Go Micro Team*
+
+Go Micro v6.3.15 is a small but useful harness release: less friction for the first agent, better streaming provider coverage, and more reliable execution when models and delegates do not behave perfectly.
+
+## Anthropic now streams
+
+The Anthropic provider now supports Messages SSE streaming and is registered as a streaming-capable provider. That means Go Micro agents can use Anthropic in the same streaming path as the other streaming-capable providers, with request/response parser coverage and provider capability docs kept in sync.
+
+## The first-agent path is easier to start
+
+The on-ramp now has a smallest runnable first-agent example: a mock-model, no-secret agent you can run before adding provider keys. The CLI and docs also point new users toward the maintained first-agent path after scaffold/run milestones, so the next step after a service is clearer: run the example, build the agent, debug it, then walk the 0→hero services → agents → workflows path.
+
+## Plan/delegate is more deterministic
+
+Plan/delegate runs got another reliability pass. Completed plan steps are preserved, ordering is guarded, notify-before-completion is required in the flow path, and checkpoint continuation is more stable. These are the kinds of harness fixes that matter when an agent does real work over multiple tool calls instead of just answering a prompt.
+
+## Tool-call recovery keeps improving
+
+Provider text tool-call fallback paths now recover more of the awkward cases: tagged calls, `Create`-suffixed calls, mixed text/tool-call output, and AtlasCloud follow-up calls. The goal is pragmatic: when a weaker or non-standard provider emits something close to a tool call, the harness should still make progress when it can do so safely.
+
+## A2A payment groundwork
+
+The A2A gateway now has the shared payment-mandate foundation needed for AP2-style agent payment flows. It is groundwork, not a full product story yet, but it keeps Go Micro's agent interop and paid-tool direction moving together.
+
+## Read the changelog
+
+The full release notes are in the [CHANGELOG](https://github.com/micro/go-micro/blob/master/CHANGELOG.md).
+
+---
+
+*Go Micro is an open source agent harness and service framework for Go. [Star us on GitHub](https://github.com/micro/go-micro).*
+
+<div class="post-nav">
+  <div><a href="/blog/33">&larr; The Loop, Shipped: Introducing micro loop</a></div>
+  <div><a href="/blog/">All Posts</a></div>
+</div>

internal/website/blog/35.md

@@ -0,0 +1,43 @@
+---
+layout: blog
+title: "What's New in Go Micro: v6.6.0"
+permalink: /blog/35
+description: "Go Micro v6.6.0 strengthens the first-agent on-ramp, hardens plan/delegate recovery, and adds CI-backed security checks."
+---
+
+# What's New in Go Micro: v6.6.0
+
+*July 11, 2026 • By the Go Micro Team*
+
+Go Micro v6.6.0 is a harness reliability release. The theme is the same services → agents → workflows lifecycle, but with more of the first-agent path covered by local checks and more recovery paths made deterministic when agents resume, retry, delegate, or notify.
+
+## The first-agent path is harder to break
+
+The README, website docs, examples, and 0→hero guide chain now have more harness coverage. The CLI and docs keep the path from install troubleshooting through `micro agent demo`, quickcheck, examples, the smallest first-agent, debugging, and 0→hero in one consistent order.
+
+That matters because the first agent is where framework promises become real: scaffold a service, run it, chat with an agent, inspect what happened, and then graduate to workflows.
+
+## Plan/delegate recovery is steadier
+
+Plan/delegate got another reliability pass across side effects, notification replay, plan-only actions, timeout completion, and completed-plan recovery. These fixes are not flashy, but they are exactly the kind of harness work that keeps an agent from repeating work or losing state when a multi-step run is interrupted.
+
+## Provider fallback keeps improving
+
+AtlasCloud fallback handling now recovers more awkward provider outputs, including workspace repair calls, empty-argument text tool calls, spoken notification replays, and A2A fallback artifact text. The goal is pragmatic interop: when a provider response is close enough to a safe tool call, the harness should repair it; when it is not, the failure should stay visible.
+
+## Security checks joined the loop
+
+CI now includes a govulncheck gate and the autonomous loop can route vulnerability failures into triage. The release also includes toolchain and dependency updates for reachable CVEs, keeping the service framework side of the harness current while agent features continue to land.
+
+## Read the changelog
+
+The full release notes are in the [CHANGELOG](https://github.com/micro/go-micro/blob/master/CHANGELOG.md).
+
+---
+
+*Go Micro is an open source agent harness and service framework for Go. [Star us on GitHub](https://github.com/micro/go-micro).*
+
+<div class="post-nav">
+  <div><a href="/blog/34">&larr; What's New in Go Micro: v6.3.15</a></div>
+  <div><a href="/blog/">All Posts</a></div>
+</div>

internal/website/blog/index.html

@@ -11,6 +11,20 @@ permalink: /blog/
 
 <div class="posts">
 
+  <article style="margin-bottom: 2rem; padding-bottom: 1.5rem; border-bottom: 1px solid #e5e5e5;">
+    <h2 style="margin: 0 0 0.5rem;"><a href="/blog/35">What's New in Go Micro: v6.6.0</a></h2>
+    <p class="meta" style="color: #666; font-size: 0.85rem;">July 11, 2026</p>
+    <p>Go Micro v6.6.0 strengthens the first-agent on-ramp, hardens plan/delegate recovery, improves provider fallback repair, and adds CI-backed security checks.</p>
+    <a href="/blog/35">Read more &rarr;</a>
+  </article>
+
+  <article style="margin-bottom: 2rem; padding-bottom: 1.5rem; border-bottom: 1px solid #e5e5e5;">
+    <h2 style="margin: 0 0 0.5rem;"><a href="/blog/34">What's New in Go Micro: v6.3.15</a></h2>
+    <p class="meta" style="color: #666; font-size: 0.85rem;">July 5, 2026</p>
+    <p>Go Micro v6.3.15 tightens the first-agent on-ramp, adds Anthropic streaming, hardens plan/delegate execution, and improves provider text tool-call recovery.</p>
+    <a href="/blog/34">Read more &rarr;</a>
+  </article>
+
   <article style="margin-bottom: 2rem; padding-bottom: 1.5rem; border-bottom: 1px solid #e5e5e5;">
     <h2 style="margin: 0 0 0.5rem;"><a href="/blog/33">The Loop, Shipped: Introducing micro loop</a></h2>
     <p class="meta" style="color: #666; font-size: 0.85rem;">July 2, 2026</p>

internal/website/docs/architecture.md

@@ -104,16 +104,25 @@ If you are new, follow the architecture in the same order the runtime composes i
    CLI, `PATH`, version, and no-secret smoke path are healthy.
 2. [`micro agent demo`](getting-started.html#first-agent-on-ramp) — print the
    provider-free first-agent command and next docs steps from the installed CLI.
-3. [Smallest first-agent example](https://github.com/micro/go-micro/tree/master/examples/first-agent)
+3. `micro agent quickcheck` (or `micro agent debug`) — print the short recovery
+   map when scaffold → run → chat → inspect stalls.
+4. `micro examples` — list the maintained provider-free runnable examples in
+   copy/paste order.
+5. `micro zero-to-hero` — print the maintained one-command no-secret lifecycle
+   harness and runnable examples.
+6. [Examples wayfinding index](https://github.com/micro/go-micro/blob/master/examples/INDEX.md)
+   — choose the smallest no-secret first-agent, support reference, and interop
+   examples from one map.
+7. [Smallest first-agent example](https://github.com/micro/go-micro/tree/master/examples/first-agent)
    — run one service-backed agent with a mock model.
-4. [No-secret first-agent transcript](guides/no-secret-first-agent.html) — see the
+8. [No-secret first-agent transcript](guides/no-secret-first-agent.html) — see the
    maintained support-agent path work without a provider key.
-5. [Your First Agent](guides/your-first-agent.html) — build and chat with a
+9. [Your First Agent](guides/your-first-agent.html) — build and chat with a
    service-backed agent.
-6. [Debugging your agent](guides/debugging-agents.html) — inspect service
-   registration, tools, memory, providers, and run history.
-7. [0→hero Reference](guides/zero-to-hero.html) — walk scaffold → run → chat →
-   inspect → flow → deploy dry-run as the maintained lifecycle contract.
+10. [Debugging your agent](guides/debugging-agents.html) — inspect service
+    registration, tools, memory, providers, and run history.
+11. [0→hero Reference](guides/zero-to-hero.html) — walk scaffold → run → chat →
+    inspect → flow → deploy dry-run as the maintained lifecycle contract.
 
 ## Related
 

internal/website/docs/getting-started.md

@@ -56,12 +56,19 @@ That install → scaffold → run → call loop is the 0→1 contract. It requir
 After this quick start, follow the agent path in order:
 
 1. [Install troubleshooting](guides/install-troubleshooting.html) — verify the CLI install before agent work.
+
+Run `make docs-wayfinding` to verify the focused no-secret docs/CLI contract that keeps these website and README commands aligned with the installed CLI.
+
 2. `micro agent demo` — print the provider-free first-agent demo command and next docs steps from the installed CLI.
-3. [Smallest first-agent example](https://github.com/micro/go-micro/tree/master/examples/first-agent) — run one service-backed agent with a mock model and no provider key.
-4. [No-secret first-agent transcript](guides/no-secret-first-agent.html) — run a useful support agent with a mock model before setting up a provider key.
-5. [Your First Agent](guides/your-first-agent.html) — build a service-backed agent and talk to it with `micro chat`.
-6. [Debugging your agent](guides/debugging-agents.html) — inspect service registration, tool calls, run history, memory, provider failures, and flow handoffs when the agent surprises you.
-7. [0→hero reference path](guides/zero-to-hero.html) — prove the full scaffold → run → chat → inspect → deploy dry-run lifecycle with commands exercised by `make harness`.
+3. `micro agent quickcheck` (or `micro agent debug`) — when scaffold → run → chat → inspect stalls, print the short recovery map before you dive into the full debugging guide.
+4. `micro examples` — print the maintained provider-free runnable examples in copy/paste order.
+5. `micro zero-to-hero` — print the maintained one-command no-secret lifecycle harness and runnable examples.
+6. [Examples wayfinding index](https://github.com/micro/go-micro/blob/master/examples/INDEX.md) — choose the smallest no-secret first-agent, maintained [0→hero support reference](https://github.com/micro/go-micro/tree/master/examples/support), and next interop examples from one map.
+7. [Smallest first-agent example](https://github.com/micro/go-micro/tree/master/examples/first-agent) — run one service-backed agent with a mock model and no provider key.
+8. [No-secret first-agent transcript](guides/no-secret-first-agent.html) — run a useful support agent with a mock model before setting up a provider key.
+9. [Your First Agent](guides/your-first-agent.html) — build a service-backed agent and talk to it with `micro chat`.
+10. [Debugging your agent](guides/debugging-agents.html) — use `micro agent preflight` before `micro run`, `micro agent doctor` after `micro run`, then `micro chat` and `micro inspect agent <name>` to recover service registration, tool calls, run history, memory, provider failures, and flow handoffs when the agent surprises you.
+11. [0→hero reference path](guides/zero-to-hero.html) — prove the full scaffold → run → chat → inspect → deploy dry-run lifecycle with commands exercised by `make harness`.
 
 ## Write a Service
 
@@ -257,4 +264,5 @@ The flow discovers all services as tools and lets the LLM decide which RPCs to c
 - [Agent Design](https://github.com/micro/go-micro/blob/master/internal/docs/AGENT_DESIGN.md) — the full agent interface specification
 - [MCP & AI Agents](mcp.html) — MCP gateway, tool discovery, and auth
 - [Data Model](model.html) — typed persistence with CRUD and queries
+- [`micro loop` quickstart](guides/micro-loop.html) — scaffold a CI-gated autonomous improvement loop for a repository
 - [Deployment](deployment.html) — deploy via SSH + systemd

internal/website/docs/guides/ai-provider-guide.md

@@ -30,23 +30,23 @@ imports are linked in:
 
 ```go
 for _, row := range ai.CapabilityRows() {
-    fmt.Printf("%s: chat=%t image=%t video=%t stream=%t\n", row.Provider, row.Model, row.Image, row.Video, row.Stream)
+    fmt.Printf("%s: chat=%t image=%t video=%t stream=%t tool_stream=%t\n", row.Provider, row.Model, row.Image, row.Video, row.Stream, row.ToolStream)
 }
 ```
 
 The built-in providers currently register these capability interfaces:
 
-| Provider | Chat/text (`ai.Model`) | Image (`ai.ImageModel`) | Video (`ai.VideoModel`) | Streaming (`ai.Stream`) |
-| --- | --- | --- | --- | --- |
-| `anthropic` | Yes | No | No | Yes |
-| `atlascloud` | Yes | Yes | Yes | Yes |
-| `gemini` | Yes | No | No | No |
-| `groq` | Yes | No | No | Yes |
-| `minimax` | Yes | No | No | Yes |
-| `mistral` | Yes | No | No | Yes |
-| `ollama` | Yes | No | No | Yes |
-| `openai` | Yes | Yes | No | Yes |
-| `together` | Yes | No | No | Yes |
+| Provider | Chat/text (`ai.Model`) | Image (`ai.ImageModel`) | Video (`ai.VideoModel`) | Streaming (`ai.Stream`) | Tool streaming |
+| --- | --- | --- | --- | --- | --- |
+| `anthropic` | Yes | No | No | Yes | Yes |
+| `atlascloud` | Yes | Yes | Yes | Yes | No |
+| `gemini` | Yes | No | No | No | No |
+| `groq` | Yes | No | No | Yes | Yes |
+| `minimax` | Yes | No | No | Yes | Yes |
+| `mistral` | Yes | No | No | Yes | Yes |
+| `ollama` | Yes | No | No | Yes | Yes |
+| `openai` | Yes | Yes | No | Yes | Yes |
+| `together` | Yes | No | No | Yes | Yes |
 
 ## Step 1: Implement the `ai.Model` Interface
 

internal/website/docs/guides/debugging-agents.md

@@ -24,10 +24,11 @@ Use the recovery command that matches where you are in the first-agent journey:
 | Checkpoint | When to use it | Command |
 | --- | --- | --- |
 | Install troubleshooting | `micro` is not installed, not on `PATH`, or the shell cannot run it. | [Install troubleshooting](install-troubleshooting.html) |
+| Quick recovery map | The first-agent loop stalled and you want the short scaffold → run → chat → inspect checklist before reading this full guide. | `micro agent quickcheck` (alias: `micro agent debug`) |
 | Preflight before `micro run` | You have not started the local runtime yet and want to verify Go, CLI, provider-key, and gateway-port prerequisites. | `micro agent preflight` |
 | Doctor after `micro run` | `micro run` is active, but chat, the `/agent` gateway, agent registration, provider settings, or inspect/run history is not behaving. | `micro agent doctor` |
 
-`micro agent preflight` is read-only and runs before the first local run; failed
+`micro agent quickcheck` is the quickest breadcrumb when you are unsure where the first-agent path failed: it prints the preflight, run, doctor, inspect, and no-secret fallback commands in one place. `micro agent preflight` is read-only and runs before the first local run; failed
 checks include `Fix:` and `Next:` lines for Go, CLI installation, provider-key
 setup, and the local gateway port. Once `micro run` is already up, switch to
 `micro agent doctor` so the recovery output follows the live gateway, chat
@@ -116,6 +117,18 @@ state (`agent/<name>/runs/...`). The persisted timeline is recorded even without
 an OpenTelemetry exporter, so `micro inspect agent` remains useful in local
 no-secret development.
 
+Provider-free quickcheck: if you want to verify the documented inspect path
+before involving a live model, run the same smoke check CI uses:
+
+```sh
+go test ./internal/harness/zero-to-hero-ci -run TestNoSecretFirstAgentDebuggingSmoke -count=1
+```
+
+That test seeds a local `assistant` run history and memory transcript, then runs
+`micro inspect agent assistant --limit 1`, `micro inspect agent --status done
+--json assistant`, and `micro agent history assistant` with provider credentials
+cleared.
+
 ## 4. See tool calls as they happen
 
 When you are embedding an agent in Go and need live tool visibility, use the

internal/website/docs/guides/micro-loop.md

@@ -0,0 +1,119 @@
+---
+layout: default
+---
+
+# `micro loop` quickstart
+
+`micro loop` scaffolds the autonomous improvement loop that Go Micro uses on
+this repository: GitHub Actions workflows for planning, building, evaluation
+feedback, coherence, security, and release. Use it when you want a repository to
+continuously turn a ranked queue into small PRs while CI remains the merge gate.
+
+## 1. Initialize the loop
+
+Run the default loop from the repository root:
+
+```bash
+micro loop init
+```
+
+For every role used by Go Micro itself, scaffold all workflows:
+
+```bash
+micro loop init --roles all
+```
+
+The command writes:
+
+- `.github/loop/NORTH_STAR.md` — the direction every increment should optimize.
+- `.github/loop/PRIORITIES.md` — the ranked queue; the builder takes the top open issue.
+- `.github/loop/prompts/*.md` — editable policy for planner, builder, triage, coherence, and security roles.
+- `.github/workflows/loop-*.yml` — generated GitHub Actions mechanics.
+
+Edit the files under `.github/loop/` to steer the loop. Re-run
+`micro loop init --roles all --force` only when you want to regenerate workflow
+mechanics from the installed CLI.
+
+## 2. Configure the dispatch token
+
+The scheduled builder needs a repository secret containing a token from a user
+account that the coding agent will answer. Go Micro names that secret
+`CODEX_TRIGGER_TOKEN` by default. If you use another secret name, pass it when
+you initialize the loop:
+
+```bash
+micro loop init --agent @codex --token-secret LOOP_TOKEN --roles all
+```
+
+The token needs enough repository permission to open issues, comment, push
+branches, create pull requests, and enable auto-merge. Run `gh auth setup-git` in
+the environment that will push branches so `git push` uses the same credentials
+as `gh`.
+
+## Choosing an agent
+
+The loop is **agent-agnostic by design**. Each run opens a fresh tracking issue
+and summons the agent with an `@mention` comment; the prompt file
+(`.github/loop/prompts/<role>.md`) is the instruction. Any coding agent that
+(a) responds to an `@mention` on an issue and (b) can open a PR with `gh` works —
+you select it with `--agent`.
+
+- **Codex** (`--agent @codex`, the default). Point `--token-secret` at a PAT for
+  the user account Codex follows, and make sure the Codex environment installs
+  `gh` and runs `gh auth setup-git`. This is the path Go Micro itself runs on.
+- **Claude Code** (`--agent @claude`). Install
+  [`anthropics/claude-code-action`](https://github.com/anthropics/claude-code-action)
+  in the repo so a workflow responds to `@claude` comments and runs Claude with a
+  repo-scoped token; then the loop's dispatch triggers it like any other mention.
+- **Any other mention-driven agent** — pass its handle to `--agent`. The
+  mechanics don't care which agent it is.
+
+Not supported by the mention model: agents triggered by **issue assignment**
+rather than a comment (e.g. GitHub Copilot's coding agent, which you assign an
+issue to). The dispatch would need an "assign" adapter for those; it isn't wired
+yet, so stick to mention-driven agents.
+
+## 3. Make CI the gate
+
+The loop should not be its own reviewer. Protect the default branch so PRs merge
+only after the required checks pass. At minimum, require the same commands the
+Go Micro loop verifies locally and in CI:
+
+```bash
+go build ./...
+go test ./...
+golangci-lint run ./...
+```
+
+If your repository has a harness or end-to-end grader, make that required too.
+Keep human approval requirements out of the autonomous path unless you intend the
+loop to pause for review.
+
+## 4. Verify the wiring
+
+After editing the North Star, queue, prompts, token secret, and branch
+protection, run:
+
+```bash
+micro loop verify
+```
+
+`micro loop verify` checks that the loop direction, queue, prompts, role
+workflows, and non-loop CI gate are present. Fix any reported missing items
+before relying on scheduled increments.
+
+## 5. Operate the queue
+
+Keep one ranked list in `.github/loop/PRIORITIES.md`. Each item should link a
+scoped issue and be small enough for one PR. The builder closes both the priority
+issue and the per-run tracker issue in the PR body, for example:
+
+```text
+Closes #1234
+Closes #5678
+```
+
+Use the North Star to keep the queue honest: favor small improvements that move
+developers through the services → agents → workflows lifecycle, and surface
+breaking API or brand/positioning decisions for humans instead of auto-merging
+them.