docs(priorities): refresh architect adoption queue

docs: add agent debugging guide (#3596 )
Co-authored-by: Codex <codex@openai.com>
2026-07-01 21:41:39 +00:00 · 2026-07-01 22:13:48 +01:00 · 2026-07-01 21:45:21 +01:00 · 2026-07-01 21:21:39 +01:00 · 2026-07-01 20:41:31 +01:00 · 2026-07-01 20:29:53 +01:00
78 changed files with 2120 additions and 187 deletions
@@ -48,4 +48,4 @@ Add any other context about the problem here.
 - [Troubleshooting Guide](https://github.com/micro/go-micro/tree/master/internal/website/docs/getting-started.md)
 - [Examples](https://github.com/micro/go-micro/tree/master/examples)
 - [API Reference](https://pkg.go.dev/go-micro.dev/v5)
- [Discord Community](https://discord.gg/WeMU5AGxD)
+- [Discord Community](https://discord.gg/G8Gk5j3uXr)
@@ -39,4 +39,4 @@ Add any other context, code examples, or screenshots about the feature request h
 - [Roadmap](https://github.com/micro/go-micro/blob/master/ROADMAP.md)
 - [Contributing Guide](https://github.com/micro/go-micro/blob/master/CONTRIBUTING.md)
 - [Architecture Docs](https://github.com/micro/go-micro/tree/master/internal/website/docs/architecture.md)
- [Discord Community](https://discord.gg/WeMU5AGxD)
+- [Discord Community](https://discord.gg/G8Gk5j3uXr)
@@ -1,47 +0,0 @@
-name: DevRel Review
-
-# Daily higher-altitude coherence pass over the PUBLIC surface — README,
-# website (landing + docs), and blog — part of the autonomous loop
-# (internal/docs/CONTINUOUS_IMPROVEMENT.md). The hourly increment loop ships
-# code; this keeps the story coherent: docs/website aligned, README crisp, and
-# a steady supply of things worth blogging about.
-#
-# Like the increment loop it opens a fresh issue and dispatches Codex via
-# CODEX_TRIGGER_TOKEN (Codex ignores Actions-bot comments). Autonomy boundary:
-# SAFE factual-alignment and crispness fixes auto-merge; brand/positioning copy
-# and blog drafts are surfaced in the report for the human, never auto-merged.
-
-on:
-  workflow_dispatch: {}
-  schedule:
-    - cron: "0 7 * * *" # daily, 07:00 UTC (tunable)
-
-permissions:
-  issues: write
-
-concurrency:
-  group: devrel-review
-  cancel-in-progress: false
-
-jobs:
-  dispatch:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Open a DevRel review issue and dispatch Codex
-        env:
-          GH_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN || github.token }}
-          HAS_TRIGGER_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN != '' }}
-          REPO: ${{ github.repository }}
-          RUN_NUMBER: ${{ github.run_number }}
-        run: |
-          if [ "$HAS_TRIGGER_TOKEN" != "true" ]; then
-            echo "CODEX_TRIGGER_TOKEN is not set — skipping (Codex ignores Actions-bot comments)."
-            exit 0
-          fi
-          ISSUE_URL=$(gh issue create --repo "$REPO" \
-            --title "DevRel coherence review #$RUN_NUMBER" \
-            --body "Daily DevRel / coherence pass over README, website (landing + docs), and the blog. North Star: internal/docs/THESIS.md.")
-          ISSUE_NUM="${ISSUE_URL##*/}"
-          echo "Opened issue #$ISSUE_NUM — dispatching Codex (DevRel)."
-          gh issue comment "$ISSUE_NUM" --repo "$REPO" --body \
-          "@codex Act as DevRel for go-micro. Audit the PUBLIC surface — \`README.md\`, \`internal/website/\` (landing \`index.html\` + \`docs/\`), and the blog under \`internal/website/blog/\` — for coherence with the North Star in internal/docs/THESIS.md (an agent harness and service framework; the services → agents → workflows lifecycle). Look for: (1) places where README / website / docs contradict each other, are stale, or describe behavior that has since changed (cross-check against the code and recent merged PRs / CHANGELOG.md); (2) whether the README is crisp and leads with the harness positioning; (3) one to three genuinely blog-worthy items from recently shipped work. Then do BOTH of these: (A) post a concise findings report as a comment on this issue (#$ISSUE_NUM) — what is aligned, what drifted, what you fixed, and the blog ideas; (B) for SAFE factual-alignment and crispness fixes only (NOT brand/marketing/positioning rewrites), open one PR: \`git switch -c codex/devrel-$ISSUE_NUM\`, \`git push -u origin codex/devrel-$ISSUE_NUM\`, \`gh pr create --base master --label codex --title \"<title>\" --body \"<summary, including 'Closes #$ISSUE_NUM'>\"\`, then \`gh pr merge --squash --auto --delete-branch\`. Leave brand/positioning copy and blog drafts for the human — describe them in the report, do NOT open auto-merging PRs for them. Do not use the make_pr tool (it is a no-op stub). If you touch code, verify go build/test/golangci-lint. Stay out of breaking public-API changes."
@@ -12,7 +12,7 @@ on:
  pull_request:
    branches: ["**"]
  schedule:
-    - cron: "17 6 * * *" # daily, so the world is exercised even without changes
+    - cron: "17 * * * *" # hourly, so real-model conformance keeps pace with the dev/loop velocity
  workflow_dispatch:
    inputs:
      providers:
@@ -67,6 +67,11 @@ jobs:
          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
          ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}
+          # Atlas Cloud's default chat model was failing the agent/tool-use
+          # conformance harnesses; run it against a stronger tool-use model.
+          # Override with an Actions variable ATLASCLOUD_MODEL if the exact
+          # catalog id differs (Atlas uses org/model ids).
+          ATLASCLOUD_MODEL: ${{ vars.ATLASCLOUD_MODEL || 'minimaxai/minimax-m3' }}
        run: |
          PROVIDERS="${{ github.event.inputs.providers || 'anthropic,openai,gemini,groq,mistral,together,atlascloud' }}"
          HARNESSES="${{ github.event.inputs.harnesses || 'agent,universe,agent-flow,plan-delegate,a2a-stream-fallback' }}"
@@ -1,4 +1,4 @@
-name: Architecture Review
+name: "Loop: Architect (Planner)"

 # Continuous high-altitude oversight of the whole framework and harness — the
 # "founder lens" of the autonomous loop (internal/docs/CONTINUOUS_IMPROVEMENT.md).
@@ -48,4 +48,4 @@ jobs:
          ISSUE_NUM="${ISSUE_URL##*/}"
          echo "Opened issue #$ISSUE_NUM — dispatching Codex (Architect)."
          gh issue comment "$ISSUE_NUM" --repo "$REPO" --body \
-          "@codex Act as the architect — the founder lens — for go-micro, running continuously alongside the builders. Hold the whole picture: how the harness, the framework, and the developer UX fit together cohesively, what is in flight and what just merged, what to prioritize next on the roadmap, and what is missing or has drifted. Each run: (1) TRACK STATE — scan recently merged PRs and open codex PRs/issues to see what shipped and what is being built right now, so the queue reflects reality (drop done items, don't re-queue in-flight work). (2) ASSESS against the North Star in internal/docs/THESIS.md — lead with its Mission (*the problem we solve: make building an agent as easy as building a service, on one runtime*) and re-derive alignment from the CANON it names (the blog under internal/website/blog, the README, and the website — read these, don't rely on THESIS.md alone), then ROADMAP.md (Now → Next → Later). Judge every priority against the mission: does it make the services → agents → workflows lifecycle simpler, more cohesive, and more operable? Look at coherence and seams across the core packages (agent, ai, flow, gateway/mcp, gateway/a2a, model, server, store, registry), the dev inner loop (scaffold → run → chat → inspect → deploy), missing pieces, duplication/drift, and realignment. Flag drift in EITHER direction: work drifting from the mission, or the North Star/website drifting from the lived story in the blog (which needs re-grounding in the canon). (3) MAINTAIN THE QUEUE in internal/docs/PRIORITIES.md — a SINGLE ordered list, highest-value first, each item linking a scoped CI-verifiable issue (#N); roadmap phase is the primary ordering, internal findings (cohesion gaps, DX friction, missing pieces) interleaved by value. For any prioritized gap that has no issue yet, file one: \`gh issue create --label codex --label enhancement --title \"<scoped task>\" --body \"<goal, scope, acceptance criteria>\"\`. OUTPUT: post a concise assessment as a comment on this issue (#$ISSUE_NUM) — what shipped, what's in flight, the top risks/gaps/missing pieces, and the reasoning behind the ranking. If the ranking actually changed, open ONE PR for PRIORITIES.md: \`git switch -c codex/architect-$ISSUE_NUM\`, \`git push -u origin codex/architect-$ISSUE_NUM\`, \`gh pr create --base master --label codex --title \"<title>\" --body \"<summary, Closes #$ISSUE_NUM>\"\`, then \`gh pr merge --squash --auto --delete-branch\`. If the queue is already accurate and correctly ranked, do NOT open a PR — just close this issue (\`gh issue close $ISSUE_NUM\`). Do NOT make breaking public-API or architectural changes yourself — surface those in the assessment as notes for the human, never as auto-merged changes. Do not use the make_pr tool (it is a no-op stub)."
+          "@codex Act as the architect — the founder lens — for go-micro, running continuously alongside the builders. Hold the whole picture: how the harness, the framework, and the developer UX fit together cohesively, what is in flight and what just merged, what to prioritize next on the roadmap, and what is missing or has drifted. Each run: (1) TRACK STATE — scan recently merged PRs and open codex PRs/issues to see what shipped and what is being built right now, so the queue reflects reality (drop done items, don't re-queue in-flight work). (2) ASSESS against the North Star in internal/docs/THESIS.md — lead with its Mission (*the problem we solve: make building an agent as easy as building a service, on one runtime*) and re-derive alignment from the CANON it names (the blog under internal/website/blog, the README, and the website — read these, don't rely on THESIS.md alone), then ROADMAP.md (Now → Next → Later). Judge every priority against the mission: does it make the services → agents → workflows lifecycle simpler, more cohesive, and more operable? CURRENT GOAL — DEVELOPER ADOPTION: the framework's depth is strong but its ON-RAMP is the gap, and the strategic priority right now is developer adoption / reviving real usage. Weight the developer on-ramp and DX — a walkable first-agent tutorial, discoverable examples, docs wayfinding/nav, install friction, debugging, the 0→1 and 0→hero experience — AT LEAST as highly as internal hardening. A developer succeeding on their first agent matters more right now than another conformance/observability/interop increment; do NOT let the queue fill entirely with internal depth work — keep open adoption/on-ramp items near the top. Look at coherence and seams across the core packages (agent, ai, flow, gateway/mcp, gateway/a2a, model, server, store, registry), the dev inner loop (scaffold → run → chat → inspect → deploy), missing pieces, duplication/drift, and realignment. Flag drift in EITHER direction: work drifting from the mission, or the North Star/website drifting from the lived story in the blog (which needs re-grounding in the canon). (3) MAINTAIN THE QUEUE in internal/docs/PRIORITIES.md — a SINGLE ordered list, highest-value first, each item linking a scoped CI-verifiable issue (#N); roadmap phase is the primary ordering, internal findings (cohesion gaps, DX friction, missing pieces) interleaved by value. For any prioritized gap that has no issue yet, file one: \`gh issue create --label codex --label enhancement --title \"<scoped task>\" --body \"<goal, scope, acceptance criteria>\"\`. OUTPUT: post a concise assessment as a comment on this issue (#$ISSUE_NUM) — what shipped, what's in flight, the top risks/gaps/missing pieces, and the reasoning behind the ranking. If the ranking actually changed, open ONE PR for PRIORITIES.md: \`git switch -c codex/architect-$ISSUE_NUM\`, \`git push -u origin codex/architect-$ISSUE_NUM\`, \`gh pr create --base master --label codex --title \"<title>\" --body \"<summary, Closes #$ISSUE_NUM>\"\`, then \`gh pr merge --squash --auto --delete-branch\`. If the queue is already accurate and correctly ranked, do NOT open a PR — just close this issue (\`gh issue close $ISSUE_NUM\`). Do NOT make breaking public-API or architectural changes yourself — surface those in the assessment as notes for the human, never as auto-merged changes. Do not use the make_pr tool (it is a no-op stub)."
@@ -1,4 +1,4 @@
-name: Continuous Improvement
+name: "Loop: Builder (Generator)"

 # Durable backbone for the autonomous improvement loop
 # (see internal/docs/CONTINUOUS_IMPROVEMENT.md).
@@ -0,0 +1,61 @@
+name: "Loop: DevRel"
+
+# Daily higher-altitude coherence pass over the PUBLIC surface — README,
+# website (landing + docs), and blog — part of the autonomous loop
+# (internal/docs/CONTINUOUS_IMPROVEMENT.md). The hourly increment loop ships
+# code; this keeps the story coherent: docs/website aligned, README crisp, and
+# a steady supply of things worth blogging about.
+#
+# It also keeps the CHANGELOG living: each run reconciles the `[Unreleased]`
+# section of CHANGELOG.md against what actually merged (rolling it into a dated
+# version heading whenever a new tag was cut), and — when enough has shipped —
+# drafts a "what's new" changelog blog post narrating it.
+#
+# Like the increment loop it opens a fresh issue and dispatches Codex via
+# CODEX_TRIGGER_TOKEN (Codex ignores Actions-bot comments). Autonomy boundary:
+# SAFE factual-alignment and crispness fixes — including CHANGELOG.md upkeep —
+# auto-merge; brand/positioning copy and the changelog blog post are opened as a
+# PR but left for the human to review/merge (blog voice stays with the human).
+
+on:
+  workflow_dispatch: {}
+  schedule:
+    - cron: "0 7 * * *" # daily, 07:00 UTC (tunable)
+
+permissions:
+  issues: write
+
+concurrency:
+  group: devrel-review
+  cancel-in-progress: false
+
+jobs:
+  dispatch:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Open a DevRel review issue and dispatch Codex
+        env:
+          GH_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN || github.token }}
+          HAS_TRIGGER_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN != '' }}
+          REPO: ${{ github.repository }}
+          RUN_NUMBER: ${{ github.run_number }}
+        run: |
+          if [ "$HAS_TRIGGER_TOKEN" != "true" ]; then
+            echo "CODEX_TRIGGER_TOKEN is not set — skipping (Codex ignores Actions-bot comments)."
+            exit 0
+          fi
+          ISSUE_URL=$(gh issue create --repo "$REPO" \
+            --title "DevRel coherence review #$RUN_NUMBER" \
+            --body "Daily DevRel / coherence pass over README, website (landing + docs), and the blog, plus CHANGELOG.md upkeep and a changelog blog post. North Star: internal/docs/THESIS.md.")
+          ISSUE_NUM="${ISSUE_URL##*/}"
+          echo "Opened issue #$ISSUE_NUM — dispatching Codex (DevRel)."
+          gh issue comment "$ISSUE_NUM" --repo "$REPO" --body \
+          "@codex Act as DevRel for go-micro. Do FOUR things this run.
+
+          COHERENCE AUDIT. Audit the PUBLIC surface — \`README.md\`, \`internal/website/\` (landing \`index.html\` + \`docs/\`), and the blog under \`internal/website/blog/\` — for coherence with the North Star in internal/docs/THESIS.md (an agent harness and service framework; the services → agents → workflows lifecycle). Look for: (1) places where README / website / docs contradict each other, are stale, or describe behavior that has since changed (cross-check against the code and recent merged PRs); (2) whether the README is crisp and leads with the harness positioning; (3) one to three genuinely blog-worthy items from recently shipped work.
+
+          CHANGELOG UPKEEP (this is a SAFE factual task — it goes in the auto-merged PR). Keep CHANGELOG.md living, in [Keep a Changelog](https://keepachangelog.com/) format with the newest content at the top under \`## [Unreleased]\`. (a) Enumerate PRs merged to master since the last CHANGELOG update — \`gh pr list --repo $REPO --state merged --base master --limit 60 --json number,title,mergedAt,labels\` — and compare against what CHANGELOG.md already lists. (b) For each genuinely user-facing change not yet recorded (new capability, behavior/API change, notable fix — SKIP purely internal loop/CI/priorities-refresh churn), add a concise entry under the right \`### Added\` / \`### Changed\` / \`### Fixed\` / \`### Documentation\` subheading of \`## [Unreleased]\`, phrased for a user (what it does, which package), not a commit subject. (c) If a new \`v6.MINOR.PATCH\` tag has been cut since the last run (\`git fetch --tags --force\`; compare the newest \`v6.*\` tag to the versions already in CHANGELOG.md), RENAME the current \`## [Unreleased]\` heading to \`## [MINOR.PATCH] - <Month YYYY>\` for that tag and open a fresh empty \`## [Unreleased]\` above it. Keep it accurate — do not invent entries; if nothing user-facing merged, leave [Unreleased] as-is.
+
+          CHANGELOG BLOG POST (blog voice — open a PR but do NOT auto-merge; leave it for the human). If — and only if — enough user-facing work has accumulated since the last changelog post to be worth reading (a meaningful batch, roughly a week's worth; do NOT post an almost-empty update every day), draft a short 'What's new in Go Micro' post that narrates what shipped in plain language (grouped by theme, linking the docs/examples, closing with install/upgrade). Create it as the next-numbered file in \`internal/website/blog/\` (find the highest N, use N+1), mirroring the frontmatter (layout/title/permalink/description) and the post-nav 'previous post' link of the latest existing post, and add an entry at the TOP of \`internal/website/blog/index.html\`. Base it strictly on the CHANGELOG — no speculation.
+
+          THEN do all of these: (A) post a concise findings report as a comment on this issue (#$ISSUE_NUM) — what is aligned, what drifted, what you fixed, the CHANGELOG entries you added, whether you drafted a changelog post (and why / why not), and any other blog ideas. (B) Open ONE auto-merging PR for the SAFE factual work only — coherence/crispness fixes AND the CHANGELOG.md update (NOT brand/marketing/positioning rewrites, NOT the blog post): \`git switch -c codex/devrel-$ISSUE_NUM\`, \`git push -u origin codex/devrel-$ISSUE_NUM\`, \`gh pr create --base master --label codex --title \"<title>\" --body \"<summary, including 'Closes #$ISSUE_NUM'>\"\`, then \`gh pr merge --squash --auto --delete-branch\`. (C) If you drafted a changelog blog post, open it as a SEPARATE PR on its own branch (\`codex/devrel-blog-$ISSUE_NUM\`) with a title prefixed 'blog:' and do NOT enable auto-merge — leave it open for the human to review and merge. Do the same (separate, non-auto-merged PR or just a report note) for any brand/positioning copy. Do not use the make_pr tool (it is a no-op stub). If you touch code, verify go build/test/golangci-lint. Stay out of breaking public-API changes."
@@ -0,0 +1,76 @@
+name: "Loop: Release (daily patch)"
+
+# Keeps the installable framework tracking the loop's daily improvements. Once a
+# day, if master has new commits since the latest v6 tag, this cuts the next
+# PATCH release (v6.MINOR.PATCH+1) and pushes the tag — which triggers the
+# existing goreleaser workflow (release.yml, tag-triggered) to build the release,
+# binaries, and images.
+#
+# The tag is pushed with a PAT (CODEX_TRIGGER_TOKEN), NOT the default GITHUB_TOKEN:
+# a tag pushed by GITHUB_TOKEN would not trigger release.yml (Actions blocks that
+# recursion). Minor/major bumps stay with the human (notable / breaking releases).
+
+on:
+  workflow_dispatch: {}
+  schedule:
+    - cron: "0 23 * * *" # daily 23:00 UTC — captures the day's merges (tunable)
+
+permissions:
+  contents: read
+
+concurrency:
+  group: loop-release
+  cancel-in-progress: false
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0 # need full history + all tags
+      - name: Cut the next patch release if there are new commits
+        env:
+          RELEASE_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN }}
+          REPO: ${{ github.repository }}
+        run: |
+          if [ -z "$RELEASE_TOKEN" ]; then
+            echo "CODEX_TRIGGER_TOKEN is not set — skipping."
+            echo "A tag pushed by the default GITHUB_TOKEN would not trigger the"
+            echo "goreleaser workflow, so a user PAT is required to cut releases."
+            exit 0
+          fi
+          git fetch --tags --force
+
+          LATEST=$(git tag --list 'v6.*.*' --sort=-v:refname | head -1)
+          if [ -z "$LATEST" ]; then
+            echo "no v6.x.x tag found — aborting so nothing weird gets tagged."
+            exit 1
+          fi
+          echo "latest release tag: $LATEST"
+
+          COUNT=$(git rev-list --count "$LATEST"..HEAD)
+          echo "commits on HEAD since $LATEST: $COUNT"
+          if [ "$COUNT" -eq 0 ]; then
+            echo "no new commits since $LATEST — no release today."
+            exit 0
+          fi
+
+          # Bump the patch: v6.MINOR.PATCH -> v6.MINOR.(PATCH+1)
+          ver="${LATEST#v}"          # 6.3.10
+          major="${ver%%.*}"         # 6
+          rest="${ver#*.}"           # 3.10
+          minor="${rest%%.*}"        # 3
+          patch="${rest#*.}"         # 10
+          case "$major.$minor.$patch" in
+            [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 $LATEST)"
+
+          git config user.name "go-micro release bot"
+          git config user.email "noreply@go-micro.dev"
+          git tag -a "$NEXT" -m "Release $NEXT — automated daily patch ($COUNT commits since $LATEST)"
+          git push "https://x-access-token:${RELEASE_TOKEN}@github.com/${REPO}.git" "$NEXT"
+          echo "Pushed $NEXT. goreleaser (release.yml) will build and publish it."
@@ -0,0 +1,59 @@
+name: "Loop: Triage (Evaluator feedback)"
+
+# Closes the autonomous loop's feedback path: when the live provider-conformance
+# harness fails, dispatch Codex to TRIAGE the failing run and file scoped, deduped
+# issues that the hourly increment loop then fixes — no human in the middle. It
+# only triages the scheduled/manual live run (not every push/PR mock run), dedupes
+# against open issues so hourly repeats don't spam, ignores transient flakes, and
+# ESCALATES anything needing a breaking/architectural change as needs-human rather
+# than auto-building it.
+#
+# Gated on CODEX_TRIGGER_TOKEN like the rest of the loop (Codex ignores comments
+# authored by the github-actions bot).
+#
+# Note: Codex is serial, so this competes with the hourly increment + architect
+# dispatches for the single task slot. If it saturates, lower the harness cadence
+# or gate this to a slower schedule.
+
+on:
+  workflow_run:
+    workflows: ["Harness (E2E)"]
+    types: [completed]
+
+permissions:
+  issues: write
+
+concurrency:
+  group: harness-triage
+  cancel-in-progress: false
+
+jobs:
+  triage:
+    runs-on: ubuntu-latest
+    # Only when the harness actually failed, and only for the scheduled or manual
+    # live run — never the per-push/PR mock run.
+    if: github.event.workflow_run.conclusion == 'failure' && (github.event.workflow_run.event == 'schedule' || github.event.workflow_run.event == 'workflow_dispatch')
+    steps:
+      - name: Open a triage issue and dispatch Codex
+        env:
+          GH_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN || github.token }}
+          HAS_TRIGGER_TOKEN: ${{ secrets.CODEX_TRIGGER_TOKEN != '' }}
+          REPO: ${{ github.repository }}
+          RUN_ID: ${{ github.event.workflow_run.id }}
+          RUN_URL: ${{ github.event.workflow_run.html_url }}
+        run: |
+          if [ "$HAS_TRIGGER_TOKEN" != "true" ]; then
+            echo "CODEX_TRIGGER_TOKEN is not set — skipping (Codex ignores Actions-bot comments)."
+            exit 0
+          fi
+          # Ensure the escalation label exists (idempotent).
+          gh label create needs-human --repo "$REPO" --color FBCA04 \
+            --description "Requires a human/architect decision (breaking or architectural)" --force || true
+
+          ISSUE_URL=$(gh issue create --repo "$REPO" \
+            --title "Harness failure triage: run $RUN_ID" \
+            --body "Automated triage of a failed live provider-conformance harness run: $RUN_URL")
+          ISSUE_NUM="${ISSUE_URL##*/}"
+          echo "Opened triage issue #$ISSUE_NUM — dispatching Codex."
+          gh issue comment "$ISSUE_NUM" --repo "$REPO" --body \
+          "@codex Act as failure triage for the autonomous loop. The live provider-conformance harness failed: $RUN_URL (run id $RUN_ID). Do this, and do NOT change code or open a PR — triage only: (1) Read the failing logs (\`gh run view $RUN_ID --repo $REPO --log-failed\`) and the provider-conformance artifact/summary. (2) Root-cause each DISTINCT failure. (3) DEDUPE against existing work — list open issues (\`gh issue list --repo $REPO --label codex --state open --limit 100\`); if a matching issue already exists for a failure, add a one-line 'recurred in $RUN_URL' comment to it and do NOT open a duplicate. (4) For each genuine, self-contained, CI-verifiable defect that is NOT already tracked, open a scoped issue: \`gh issue create --repo $REPO --label codex --label enhancement --title \"<scoped task>\" --body \"<root cause, scope, acceptance criteria, and the failing run link>\"\` — the hourly increment loop will build it. (5) If a failure is transient/flaky and not a code defect (e.g. a live-model latency timeout or provider outage), note it in a comment and file NOTHING. (6) If a real fix would require a breaking public-API change or an architectural change, do NOT file it as an auto-buildable task — open an issue labeled \`needs-human\` describing it for the architect/human. When finished, close this triage issue (\`gh issue close $ISSUE_NUM\`)."
@@ -2,8 +2,33 @@

 All notable changes to Go Micro are documented here.

-Format follows [Keep a Changelog](https://keepachangelog.com/). Go Micro uses
-calendar-based versions (YYYY.MM) for the AI-native era.
+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.
+
+> Earlier `2026.0x` headings are historical calendar-style markers from before
+> v6 tagging; they are kept for continuity and not reused.
+
+---
+
+## [Unreleased]
+
+### Added
+- **Retrieval-backed agent memory** — agents can recall relevant prior turns by similarity, not just the recent window, with a summarizer hook that compacts older history so long conversations stay in budget. (`agent/`)
+- **Scheduled flows** — a flow can run an agent (or any step) on a cron-style schedule, with the dispatch traced end to end. (`flow/`)
+- **Flow verification/grader loop** — a workflow can grade its own step output against a rubric and retry until it passes, plus run-trace analysis to surface where a flow spends its time. (`flow/`)
+- **A2A streaming & continuity** — outbound agent streaming flows through the A2A binding (`message/stream`), with `tasks/resubscribe` and `input-required` handoffs for multi-turn interop. (`gateway/a2a/`)
+
+### Changed
+- **Agent tool-call resilience** — opt-in retries around agent tool calls, and a fallback that executes tool calls emitted as text by weaker models so they still make progress. (`agent/`)
+- **Hardened agent durability** — terminal failure statuses are classified and surfaced, and durable resume-after-restart is covered by tests. (`agent/`)
+
+### Documentation
+- **"Your first agent" walkthrough** and a canonical 0-to-hero reference path, lowering the on-ramp from install to a running agent. (`internal/website/docs/`)
+- **Discord** linked prominently across the README, website nav/footer, and docs. (`https://discord.gg/G8Gk5j3uXr`)

 ---

@@ -6,6 +6,17 @@ Thank you for your interest in contributing to Go Micro! This document provides

 Be respectful, inclusive, and collaborative. We're all here to build great software together.

+## How Go Micro is built
+
+Go Micro is developed by an **autonomous improvement loop** — a planner, a
+generator, and a separate evaluator, running as scheduled GitHub Actions with a
+human setting direction. It's the framework's own thesis (an agent operating a
+system) pointed at itself: an agent harness, built by agents. The full process —
+the planner → generator → evaluator pipeline, the correctness-only merge gate, and
+the guardrails — is documented in
+[`internal/docs/CONTINUOUS_IMPROVEMENT.md`](internal/docs/CONTINUOUS_IMPROVEMENT.md).
+Human contributions follow the same gate: green CI, one concern per PR.
+
 ## Getting Started

 1. Fork the repository
@@ -1,7 +1,9 @@
-# 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)
+# 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 is an **agent harness** and service framework for Go.

+**Community:** questions, ideas, or just want to build alongside us? [Join the Discord](https://discord.gg/G8Gk5j3uXr).
+
 A harness is the runtime around an agent: the tools it can call, the memory it keeps, the guardrails that bound it, the workflows that trigger it, the services it depends on, and the protocols other agents use to reach it. 

 Go Micro gives you the harness as Go code. Build an agent and it gets a model, memory, tools, planning, delegation, guardrails, and service discovery; it is reachable over [MCP](https://modelcontextprotocol.io/) and [A2A](https://a2a-protocol.org). Write services and every endpoint becomes an AI-callable tool. Orchestrate the deterministic parts with durable flows. Agents, services, and flows share one runtime because an agent is a distributed system, and building one is building a service.
@@ -14,7 +16,7 @@ Go Micro gives you the harness as Go code. Build an agent and it gets a model, m
 &nbsp;&nbsp;
 <a href="https://go-micro.dev/blog/8"><img src="https://www.atlascloud.ai/logo.svg" height="26" /></a>

-**Want to support Go Micro and see your logo here?** [Become a sponsor](https://discord.gg/WeMU5AGxD) — reach out on Discord.
+**Want to support Go Micro and see your logo here?** [Become a sponsor](https://discord.gg/G8Gk5j3uXr) — reach out on Discord.

 ## Commercial Support

@@ -44,7 +46,7 @@ Install the CLI:
 curl -fsSL https://go-micro.dev/install.sh | sh

 # Or with Go
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

 ### Fastest start — no API key
@@ -65,7 +67,7 @@ curl -X POST http://localhost:8080/api/helloworld/Helloworld.Call \
 ```

 This scaffold → run → call path is covered by the no-secret CI harness. To run
-the same local contract (including the 0→hero services → agents → workflows path,
+the same 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:

 ```bash
@@ -401,8 +403,8 @@ Swap providers with a single import — same interface everywhere:
 | Google Gemini | `gemini-2.5-flash` |
 | Groq | `llama-3.3-70b-versatile` |
 | Mistral | `mistral-large-latest` |
-| Together AI | `Llama-3.3-70B-Instruct-Turbo` |
-| Atlas Cloud | `llama-3.3-70b` |
+| Together AI | `meta-llama/Llama-3.3-70B-Instruct-Turbo` |
+| Atlas Cloud | `deepseek-ai/DeepSeek-V3-0324` |

 ```go
 m := ai.New("anthropic", ai.WithAPIKey(key))
@@ -423,6 +425,8 @@ See [all examples](examples/README.md).

 - [Getting Started](internal/website/docs/getting-started.md)
 - [AI Integration](internal/website/docs/ai-integration.md)
+- [Your First Agent](internal/website/docs/guides/your-first-agent.md)
+- [0→hero Reference](internal/website/docs/guides/zero-to-hero.md)
 - [Agents and Workflows](internal/website/docs/guides/agents-and-workflows.md)
 - [Agent Design](internal/docs/AGENT_DESIGN.md)
 - [Plan & Delegate](internal/website/docs/guides/plan-delegate.md)
@@ -66,7 +66,7 @@ hosted service, enterprise tier, or venture funding. See
 ## Contributing & feedback

 Pick an item, open an issue to discuss the approach, and submit a PR. Or join the
-[Discord](https://discord.gg/WeMU5AGxD). Include tests, run `make test` and
+[Discord](https://discord.gg/G8Gk5j3uXr). Include tests, run `make test` and
 `make lint`.

 ## Version support
@@ -174,6 +174,6 @@ We currently do not offer a bug bounty program, but we greatly appreciate respon

 For security questions that are not vulnerabilities, please:
 - Open a discussion: https://github.com/micro/go-micro/discussions
- Join Discord: https://discord.gg/WeMU5AGxD
+- Join Discord: https://discord.gg/G8Gk5j3uXr
 - Email: support@go-micro.dev

@@ -179,6 +179,8 @@ func (a *agentImpl) setupWithToolHandler(handler ai.ToolHandler) {
 		a.mem = NewInMemory(a.opts.HistoryLimit)
 	case a.opts.MemoryCompaction.MaxMessages > 0:
 		a.mem = NewCompactingMemoryWithOptions(a.stateStore(), "history", a.opts.MemoryCompaction)
+	case a.opts.MemoryRetrievalLimit > 0:
+		a.mem = NewRetrievalMemory(a.stateStore(), "history", a.opts.MemoryRetrievalLimit)
 	default:
 		a.mem = NewMemory(a.stateStore(), "history", a.opts.HistoryLimit)
 	}
@@ -327,6 +329,19 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 		return nil, fmt.Errorf("agent run %s paused for approval: %s", run.ID, a.pause.Message)
 	}

+	if len(resp.ToolCalls) == 0 {
+		if calls, answer, ok := a.executeTextToolCalls(ctx, resp.Reply, toolList); ok {
+			resp.ToolCalls = calls
+			if resp.Answer == "" {
+				resp.Answer = answer
+			}
+			trimmedReply := strings.TrimSpace(resp.Reply)
+			if strings.HasPrefix(trimmedReply, "{") || strings.HasPrefix(trimmedReply, "[") || strings.HasPrefix(trimmedReply, "```") {
+				resp.Reply = ""
+			}
+		}
+	}
+
 	if resp.Reply != "" {
 		a.mem.Add("assistant", resp.Reply)
 	}
@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"strings"
+	"time"

 	"go-micro.dev/v6/ai"
 	codecBytes "go-micro.dev/v6/codec/bytes"
@@ -121,6 +122,7 @@ func (a *agentImpl) toolHandler() ai.ToolHandler {
 	// so the result runs plan → step → loop → approve → checkpoint → base.
 	h := a.baseHandler()
 	h = a.toolTimeoutWrap(h)
+	h = a.toolRetryWrap(h)
 	h = a.checkpointToolWrap(h)
 	h = a.approveWrap(h)
 	h = a.loopWrap(h)
@@ -164,6 +166,99 @@ func (a *agentImpl) toolTimeoutWrap(next ai.ToolHandler) ai.ToolHandler {
 	}
 }

+// toolRetryWrap retries transient tool failures with bounded backoff. It is
+// opt-in because tools can have side effects; guardrail refusals and caller
+// cancellation are never retried.
+func (a *agentImpl) toolRetryWrap(next ai.ToolHandler) ai.ToolHandler {
+	return func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+		maxAttempts := a.opts.ToolMaxAttempts
+		if maxAttempts <= 0 {
+			maxAttempts = 1
+		}
+
+		var res ai.ToolResult
+		for attempt := 1; attempt <= maxAttempts; attempt++ {
+			if err := ctx.Err(); err != nil {
+				return errResult(call.ID, err.Error())
+			}
+			res = next(ctx, call)
+			if !retryableToolResult(res) || attempt == maxAttempts || ctx.Err() != nil {
+				return annotateToolAttempts(res, attempt)
+			}
+
+			t := time.NewTimer(toolRetryBackoff(attempt, a.opts.ToolRetryBackoff))
+			select {
+			case <-ctx.Done():
+				if !t.Stop() {
+					<-t.C
+				}
+				return errResult(call.ID, ctx.Err().Error())
+			case <-t.C:
+			}
+		}
+		return annotateToolAttempts(res, maxAttempts)
+	}
+}
+
+func retryableToolResult(res ai.ToolResult) bool {
+	if res.Refused != "" {
+		return false
+	}
+	msg := toolErrorMessage(res)
+	if msg == "" {
+		return false
+	}
+	return ai.IsTransientError(fmt.Errorf("%s", msg))
+}
+
+func toolErrorMessage(res ai.ToolResult) string {
+	if m, ok := res.Value.(map[string]string); ok {
+		return m["error"]
+	}
+	if m, ok := res.Value.(map[string]any); ok {
+		if v, ok := m["error"].(string); ok {
+			return v
+		}
+	}
+	var decoded map[string]string
+	if err := json.Unmarshal([]byte(res.Content), &decoded); err == nil {
+		return decoded["error"]
+	}
+	return ""
+}
+
+func annotateToolAttempts(res ai.ToolResult, attempts int) ai.ToolResult {
+	if attempts <= 1 {
+		return res
+	}
+	res.Attempts = attempts
+	if m, ok := res.Value.(map[string]string); ok {
+		cp := map[string]any{}
+		for k, v := range m {
+			cp[k] = v
+		}
+		cp["attempts"] = attempts
+		res.Value = cp
+		if b, err := json.Marshal(cp); err == nil {
+			res.Content = string(b)
+		}
+	}
+	return res
+}
+
+func toolRetryBackoff(attempt int, base time.Duration) time.Duration {
+	if base <= 0 {
+		base = 200 * time.Millisecond
+	}
+	if shift := attempt - 1; shift > 0 {
+		base <<= shift
+	}
+	if base > 30*time.Second {
+		return 30 * time.Second
+	}
+	return base
+}
+
 // baseHandler executes a tool call: a developer custom tool, the built-in
 // delegate, or an RPC to the service. It is the innermost handler.
 func (a *agentImpl) baseHandler() ai.ToolHandler {
@@ -338,6 +433,7 @@ func (a *agentImpl) handleDelegate(ctx context.Context, call ai.ToolCall) ai.Too
 		ModelCallTimeout(a.opts.ModelTimeout),
 		ModelRetry(a.opts.ModelMaxAttempts, a.opts.ModelRetryBackoff),
 		ToolCallTimeout(a.opts.ToolTimeout),
+		ToolRetry(a.opts.ToolMaxAttempts, a.opts.ToolRetryBackoff),
 		TraceProvider(a.opts.TraceProvider),
 	)
 	// Record lineage so the sub-agent's tool calls carry this run as parent.
@@ -102,6 +102,75 @@ func TestResumeFailedCheckpointDoesNotReplayCompletedTool(t *testing.T) {
 	}
 }

+func TestResumeFailedCheckpointAfterFreshAgentRestart(t *testing.T) {
+	ctx := context.Background()
+	cp := flow.StoreCheckpoint(store.NewMemoryStore(), "restart-resume-agent")
+	toolRuns := 0
+	modelCalls := 0
+	failFirst := true
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		modelCalls++
+		if opts.ToolHandler != nil {
+			res := opts.ToolHandler(ctx, ai.ToolCall{ID: "call-1", Name: "external.provision", Input: map[string]any{"service": "api"}})
+			if res.Content != "provisioned" {
+				t.Fatalf("tool result = %q, want provisioned", res.Content)
+			}
+		}
+		if failFirst {
+			failFirst = false
+			return nil, errors.New("process stopped after tool checkpoint")
+		}
+		return &ai.Response{Reply: "resumed after restart"}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	newAgent := func() *agentImpl {
+		return newTestAgent(Name("restart-resume-agent"), WithCheckpoint(cp),
+			WithTool("external.provision", "provision service once", nil, func(context.Context, map[string]any) (string, error) {
+				toolRuns++
+				return "provisioned", nil
+			}))
+	}
+
+	first := newAgent()
+	_, err := first.Ask(ctx, "provision api")
+	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)
+	}
+	runs, err := Pending(ctx, first)
+	if err != nil {
+		t.Fatalf("Pending before restart: %v", err)
+	}
+	if len(runs) != 1 {
+		t.Fatalf("Pending before restart returned %d runs, want 1", len(runs))
+	}
+
+	restarted := newAgent()
+	resp, err := Resume(ctx, restarted, runs[0].ID)
+	if err != nil {
+		t.Fatalf("Resume after restart: %v", err)
+	}
+	if resp.Reply != "resumed after restart" || resp.RunID != runs[0].ID {
+		t.Fatalf("response = %#v, want resumed reply on original run id", resp)
+	}
+	if toolRuns != 1 {
+		t.Fatalf("tool executions after restart resume = %d, want checkpointed tool not replayed", toolRuns)
+	}
+	if modelCalls != 2 {
+		t.Fatalf("model calls = %d, want initial call plus resumed call", modelCalls)
+	}
+	loaded, ok, err := cp.Load(ctx, runs[0].ID)
+	if err != nil || !ok {
+		t.Fatalf("Load resumed run ok=%v err=%v", ok, err)
+	}
+	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)
+	}
+}
+
 func TestResumeFailedCheckpointDoesNotDuplicateCompactedMemory(t *testing.T) {
 	ctx := context.Background()
 	st := store.NewMemoryStore()
@@ -171,3 +171,50 @@ func TestAgentProviderConformanceFakeError(t *testing.T) {
 		t.Fatalf("Ask error = %v, want conformance provider failure", err)
 	}
 }
+
+func TestAgentExecutesProviderTextToolCallFallback(t *testing.T) {
+	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")
+		}
+		return &ai.Response{
+			Reply: `{"name":"conformance_echo","input":{"value":"agent-conformance"}}`,
+		}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	var sawTool bool
+	a := New(
+		Name("conformance-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 text tool call fallback.")
+	if err != nil {
+		t.Fatalf("Ask: %v", err)
+	}
+	if !sawTool {
+		t.Fatal("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)
+	}
+	if strings.Contains(resp.Reply, `"name":"conformance_echo"`) {
+		t.Fatalf("Reply = %q, want tool result instead of raw JSON", resp.Reply)
+	}
+}
@@ -56,6 +56,16 @@ func NewMemory(s store.Store, key string, limit int) Memory {
 	return m
 }

+// NewRetrievalMemory returns store-backed memory that keeps a bounded active
+// conversation and archives every turn for retrieval. It is useful when callers
+// want relevant durable recall without summary compaction in the active context.
+// A nil store or empty key keeps only the active in-process buffer.
+func NewRetrievalMemory(s store.Store, key string, activeLimit int) Memory {
+	m := &storeMemory{store: s, key: key, hist: ai.NewHistory(activeLimit), retrieveAll: true}
+	m.load()
+	return m
+}
+
 // NewCompactingMemory returns store-backed memory with explicit compaction and
 // retrieval controls. It keeps all messages in the backing store, compacts older
 // turns into a deterministic summary when the conversation exceeds maxMessages,
@@ -100,16 +110,20 @@ func NewInMemory(limit int) Memory {
 // storeMemory is the default Memory: an ai.History buffer optionally
 // persisted to a store.
 type storeMemory struct {
-	mu         sync.Mutex
-	store      store.Store
-	key        string
-	hist       *ai.History
-	compaction MemoryCompaction
-	archive    []ai.Message
+	mu          sync.Mutex
+	store       store.Store
+	key         string
+	hist        *ai.History
+	compaction  MemoryCompaction
+	archive     []ai.Message
+	retrieveAll bool
 }

 func (m *storeMemory) Add(role, content string) {
 	m.mu.Lock()
+	if m.retrieveAll {
+		m.archive = append(m.archive, ai.Message{Role: role, Content: content})
+	}
 	m.hist.Add(role, content)
 	m.mu.Unlock()
 	m.compact()
@@ -133,6 +147,8 @@ func (m *storeMemory) Clear() {
 // Recall returns archived messages whose content contains words from query.
 // It is deterministic and provider-neutral: no embeddings or model calls are
 // required, but semantic/vector stores can replace Memory for richer retrieval.
+// When created with NewRetrievalMemory the archive contains every persisted
+// turn; when created with NewCompactingMemory it contains compacted older turns.
 func (m *storeMemory) Recall(query string, limit int) []ai.Message {
 	m.mu.Lock()
 	defer m.mu.Unlock()
@@ -186,6 +202,9 @@ func (m *storeMemory) load() {
 	}
 	m.mu.Lock()
 	m.archive = state.Archive
+	if m.retrieveAll && len(m.archive) == 0 {
+		m.archive = append(m.archive, state.Messages...)
+	}
 	for _, msg := range state.Messages {
 		m.hist.Add(msg.Role, msg.Content)
 	}
@@ -64,6 +64,49 @@ func TestWithMemoryUsed(t *testing.T) {
 	}
 }

+func TestRetrievalMemoryArchivesAllTurnsAndRanksRelevant(t *testing.T) {
+	st := store.NewMemoryStore()
+	m := NewRetrievalMemory(st, "agent/retrieval/history", 2)
+	m.Add("user", "alpha budget is 42")
+	m.Add("assistant", "noted")
+	m.Add("user", "beta owner is lee")
+	m.Add("assistant", "tracked")
+	m.Add("user", "alpha owner is sam")
+
+	if got := len(m.Messages()); got != 2 {
+		t.Fatalf("active messages = %d, want bounded history of 2", got)
+	}
+
+	recall, ok := m.(MemoryRecall)
+	if !ok {
+		t.Fatal("retrieval memory should support recall")
+	}
+	recalled := recall.Recall("alpha budget", 2)
+	if len(recalled) == 0 {
+		t.Fatal("expected relevant recalled turns")
+	}
+	if got := recalled[0].Content.(string); !strings.Contains(got, "alpha budget is 42") {
+		t.Fatalf("top recall = %q, want archived alpha budget turn", got)
+	}
+}
+
+func TestRetrievalMemoryPersistsArchiveAcrossReload(t *testing.T) {
+	st := store.NewMemoryStore()
+	m := NewRetrievalMemory(st, "agent/retrieval/reload", 1)
+	m.Add("user", "alpha budget is 42")
+	m.Add("assistant", "noted")
+	m.Add("user", "beta budget is 7")
+
+	reloaded := NewRetrievalMemory(st, "agent/retrieval/reload", 1)
+	recalled := reloaded.(MemoryRecall).Recall("alpha budget", 1)
+	if len(recalled) != 1 {
+		t.Fatalf("recalled %d messages, want 1", len(recalled))
+	}
+	if got := recalled[0].Content.(string); !strings.Contains(got, "alpha budget is 42") {
+		t.Fatalf("reloaded recall = %q, want alpha budget", got)
+	}
+}
+
 func TestCompactingMemoryRecallRanksSpecificMatches(t *testing.T) {
 	m := NewCompactingMemory(store.NewMemoryStore(), "agent/rank/history", 3, 1).(MemoryRecall)
 	writer := m.(Memory)
@@ -60,10 +60,19 @@ type Options struct {
 	// applied before custom tools, delegate, and service RPC calls so context
 	// deadlines propagate consistently through the agent loop.
 	ToolTimeout time.Duration
+	// ToolMaxAttempts bounds tool execution attempts including the first call.
+	// Default 1; retries are opt-in because tools can have side effects.
+	ToolMaxAttempts int
+	// ToolRetryBackoff is the base delay between transient tool failures.
+	ToolRetryBackoff time.Duration

 	// Memory is the agent's conversation memory. Nil = the default
 	// store-backed memory (durable across restarts).
 	Memory Memory
+	// MemoryRetrievalLimit enables retrieval-backed default memory without
+	// compaction. The active conversation stays bounded to this many messages
+	// while every turn is archived for deterministic recall.
+	MemoryRetrievalLimit int
 	// MemoryCompaction enables deterministic compaction/retrieval on the
 	// default store-backed memory. Custom Memory implementations can expose
 	// retrieval by implementing MemoryRecall.
@@ -117,6 +126,8 @@ func newOptions(opts ...Option) Options {
 		ModelMaxAttempts:  1, // retries opt-in via ModelRetry (see field doc)
 		ModelRetryBackoff: 100 * time.Millisecond,
 		ToolTimeout:       30 * time.Second,
+		ToolMaxAttempts:   1,
+		ToolRetryBackoff:  100 * time.Millisecond,
 		// On by default and lenient: identical repeated calls are a
 		// no-progress loop, never useful. Set LoopLimit(0) to disable.
 		LoopLimit: 3,
@@ -225,6 +236,16 @@ func ModelRetry(maxAttempts int, backoff time.Duration) Option {
 	}
 }

+// ToolRetry sets the tool retry budget and backoff for transient failures.
+// Attempts include the first call. Retries are opt-in because tools may have
+// side effects; keep handlers idempotent before enabling this.
+func ToolRetry(maxAttempts int, backoff time.Duration) Option {
+	return func(o *Options) {
+		o.ToolMaxAttempts = maxAttempts
+		o.ToolRetryBackoff = backoff
+	}
+}
+
 // WithA2A makes Run serve the agent over the A2A protocol on addr (e.g.
 // ":4000"), so other agents can reach it directly by URL without a
 // separate gateway. The agent stays a normal go-micro service as well;
@@ -240,6 +261,18 @@ func WithMemory(m Memory) Option {
 	return func(o *Options) { o.Memory = m }
 }

+// RetrievalMemory enables deterministic, store-backed retrieval memory for
+// the default agent memory without compaction. Active context is capped at
+// activeLimit messages while every turn is archived in the store for Recall.
+func RetrievalMemory(activeLimit int) Option {
+	return func(o *Options) {
+		o.MemoryRetrievalLimit = activeLimit
+		if o.MemoryRecallLimit == 0 {
+			o.MemoryRecallLimit = 5
+		}
+	}
+}
+
 // CompactMemory enables deterministic, store-backed memory compaction for the
 // default agent memory. Older turns are summarized once active context exceeds
 // maxMessages, keepRecent newest turns remain verbatim, and recalled archived
@@ -41,6 +41,10 @@ const (
 	AttrErrorKind        = "agent.error.kind"
 	AttrCheckpointStatus = "agent.checkpoint.status"
 	AttrCheckpointStage  = "agent.checkpoint.stage"
+	AttrFlowName         = "agent.flow.name"
+	AttrFlowStep         = "agent.flow.step"
+	AttrDispatch         = "agent.dispatch"
+	AttrTrigger          = "agent.trigger"
 )

 type RunEvent struct {
@@ -124,8 +128,12 @@ func (a *agentImpl) startRun(ctx context.Context, message string) (context.Conte
 		}
 	}

-	ctx, span := a.tracer().Start(ctx, spanNameRun, trace.WithSpanKind(trace.SpanKindInternal), trace.WithAttributes(
-		attribute.String(AttrRunID, info.RunID), attribute.String(AttrParentRunID, info.ParentID), attribute.String(AttrAgentName, info.Agent)))
+	attrs := appendRunInfoAttributes([]attribute.KeyValue{
+		attribute.String(AttrRunID, info.RunID),
+		attribute.String(AttrParentRunID, info.ParentID),
+		attribute.String(AttrAgentName, info.Agent),
+	}, info)
+	ctx, span := a.tracer().Start(ctx, spanNameRun, trace.WithSpanKind(trace.SpanKindInternal), trace.WithAttributes(attrs...))
 	a.recordSpanEvent(span, runEvent)
 	return ctx, func(err error) {
 		latency := time.Since(start).Milliseconds()
@@ -171,16 +179,17 @@ func (m *tracedModel) Generate(ctx context.Context, req *ai.Request, opts ...ai.
 		return resp, err
 	}

-	ctx, span := m.a.tracer().Start(ctx, spanNameModelCall, trace.WithAttributes(
+	attrs := appendRunInfoAttributes([]attribute.KeyValue{
 		attribute.String(AttrRunID, info.RunID),
 		attribute.String(AttrParentRunID, info.ParentID),
 		attribute.String(AttrAgentName, info.Agent),
 		attribute.String(AttrProvider, provider),
 		attribute.String(AttrModel, model),
-	))
+	}, info)
+	ctx, span := m.a.tracer().Start(ctx, spanNameModelCall, trace.WithAttributes(attrs...))
 	resp, err := m.Model.Generate(ctx, req, opts...)
 	dur := time.Since(start).Milliseconds()
-	attrs := []attribute.KeyValue{attribute.Int64(AttrLatencyMS, dur)}
+	attrs = []attribute.KeyValue{attribute.Int64(AttrLatencyMS, dur)}
 	if info.Attempt > 0 {
 		attrs = append(attrs, attribute.Int(AttrAttempt, info.Attempt))
 	}
@@ -360,6 +369,22 @@ func runEventAttributes(e RunEvent) []attribute.KeyValue {
 	return attrs
 }

+func appendRunInfoAttributes(attrs []attribute.KeyValue, info ai.RunInfo) []attribute.KeyValue {
+	if info.Flow != "" {
+		attrs = append(attrs, attribute.String(AttrFlowName, info.Flow))
+	}
+	if info.Step != "" {
+		attrs = append(attrs, attribute.String(AttrFlowStep, info.Step))
+	}
+	if info.Dispatch != "" {
+		attrs = append(attrs, attribute.String(AttrDispatch, info.Dispatch))
+	}
+	if info.Trigger != "" {
+		attrs = append(attrs, attribute.String(AttrTrigger, info.Trigger))
+	}
+	return attrs
+}
+
 func (a *agentImpl) recordRunEvent(e RunEvent) {
 	if e.RunID == "" {
 		return
@@ -184,3 +184,48 @@ type testStatusError struct {
 func (e testStatusError) Error() string { return "provider status error" }

 func (e testStatusError) StatusCode() int { return e.code }
+
+func TestToolRetryRetriesTransientToolErrorsThenSucceeds(t *testing.T) {
+	attempts := 0
+	a := newTestAgent(
+		Name("tool-retry-success"),
+		ToolRetry(3, time.Millisecond),
+		WithTool("flaky", "flaky tool", nil, func(context.Context, map[string]any) (string, error) {
+			attempts++
+			if attempts < 3 {
+				return "", context.DeadlineExceeded
+			}
+			return "ok", nil
+		}),
+	)
+
+	content := toolContent(a.toolHandler(), "flaky", nil)
+	if content != "ok" {
+		t.Fatalf("tool result = %q, want ok", content)
+	}
+	if attempts != 3 {
+		t.Fatalf("attempts = %d, want 3", attempts)
+	}
+}
+
+func TestToolRetryDoesNotRetryGuardrailRefusals(t *testing.T) {
+	attempts := 0
+	a := newTestAgent(
+		Name("tool-retry-refusal"),
+		MaxSteps(1),
+		ToolRetry(3, time.Millisecond),
+		WithTool("counted", "counted tool", nil, func(context.Context, map[string]any) (string, error) {
+			attempts++
+			return "ok", nil
+		}),
+	)
+	h := a.toolHandler()
+	_ = toolContent(h, "counted", nil)
+	content := toolContent(h, "counted", nil)
+	if !strings.Contains(content, "step limit reached") {
+		t.Fatalf("tool result = %q, want step-limit refusal", content)
+	}
+	if attempts != 1 {
+		t.Fatalf("attempts = %d, want only the allowed tool call to execute", attempts)
+	}
+}
@@ -0,0 +1,141 @@
+package agent
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"regexp"
+	"strings"
+
+	"go-micro.dev/v6/ai"
+)
+
+var fencedJSONBlock = regexp.MustCompile("(?s)```(?:json)?\\s*(.*?)\\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"`
+}
+
+// executeTextToolCalls is a compatibility fallback for providers that return a
+// tool call as text JSON instead of a structured tool_calls field. It only runs
+// calls whose names match the tools offered to the model, so ordinary JSON
+// answers are left untouched.
+func (a *agentImpl) executeTextToolCalls(ctx context.Context, reply string, tools []ai.Tool) ([]ai.ToolCall, string, bool) {
+	calls := parseTextToolCalls(reply, tools)
+	if len(calls) == 0 {
+		return nil, "", false
+	}
+
+	handler := a.toolHandler()
+	results := make([]string, 0, len(calls))
+	for i := range calls {
+		result := handler(ctx, calls[i])
+		calls[i].Result = result.Content
+		if result.Refused != "" {
+			calls[i].Error = result.Refused
+		}
+		if result.Content != "" {
+			results = append(results, result.Content)
+		}
+	}
+	return calls, strings.Join(results, "\n"), true
+}
+
+func parseTextToolCalls(text string, tools []ai.Tool) []ai.ToolCall {
+	allowed := map[string]bool{}
+	for _, tool := range tools {
+		allowed[tool.Name] = true
+		if tool.OriginalName != "" {
+			allowed[tool.OriginalName] = true
+		}
+	}
+	if len(allowed) == 0 {
+		return nil
+	}
+
+	for _, candidate := range jsonCandidates(text) {
+		if calls := decodeTextToolCalls(candidate, allowed); len(calls) > 0 {
+			return calls
+		}
+	}
+	return nil
+}
+
+func jsonCandidates(text string) []string {
+	trimmed := strings.TrimSpace(text)
+	var out []string
+	if trimmed != "" {
+		out = append(out, trimmed)
+	}
+	for _, match := range fencedJSONBlock.FindAllStringSubmatch(text, -1) {
+		if len(match) > 1 {
+			out = append(out, strings.TrimSpace(match[1]))
+		}
+	}
+	if start, end := strings.IndexAny(text, "[{"), strings.LastIndexAny(text, "]}"); start >= 0 && end > start {
+		out = append(out, strings.TrimSpace(text[start:end+1]))
+	}
+	return out
+}
+
+func decodeTextToolCalls(candidate string, allowed map[string]bool) []ai.ToolCall {
+	var root any
+	if err := json.Unmarshal([]byte(candidate), &root); err != nil {
+		return nil
+	}
+	return collectTextToolCalls(root, allowed)
+}
+
+func collectTextToolCalls(v any, allowed map[string]bool) []ai.ToolCall {
+	switch x := v.(type) {
+	case []any:
+		var out []ai.ToolCall
+		for _, item := range x {
+			out = append(out, collectTextToolCalls(item, allowed)...)
+		}
+		return out
+	case map[string]any:
+		if nested, ok := firstNestedToolCalls(x); ok {
+			return collectTextToolCalls(nested, allowed)
+		}
+		call := mapToTextToolCall(x)
+		name := call.Name
+		if name == "" {
+			name = call.Tool
+		}
+		input := call.Input
+		if input == nil {
+			input = call.Arguments
+		}
+		if name == "" || !allowed[name] || input == nil {
+			return nil
+		}
+		id := call.ID
+		if id == "" {
+			id = fmt.Sprintf("text-call-%s", strings.ReplaceAll(name, ".", "_"))
+		}
+		return []ai.ToolCall{{ID: id, Name: name, Input: input}}
+	default:
+		return nil
+	}
+}
+
+func firstNestedToolCalls(m map[string]any) (any, bool) {
+	for _, key := range []string{"tool_calls", "toolCalls", "calls"} {
+		if v, ok := m[key]; ok {
+			return v, true
+		}
+	}
+	return nil, false
+}
+
+func mapToTextToolCall(m map[string]any) textToolCall {
+	b, _ := json.Marshal(m)
+	var call textToolCall
+	_ = json.Unmarshal(b, &call)
+	return call
+}
@@ -27,6 +27,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"os"
 	"strings"
 	"time"

@@ -56,7 +57,14 @@ func NewProvider(opts ...ai.Option) *Provider {
 	options := ai.NewOptions(opts...)

 	if options.Model == "" {
-		options.Model = "deepseek-ai/DeepSeek-V3-0324"
+		// Allow the chat model to be selected via the ATLASCLOUD_MODEL env var
+		// (e.g. to run CI conformance against a stronger tool-use model) without
+		// a code change; fall back to a sensible default otherwise.
+		if m := os.Getenv("ATLASCLOUD_MODEL"); m != "" {
+			options.Model = m
+		} else {
+			options.Model = "deepseek-ai/DeepSeek-V3-0324"
+		}
 	}
 	if options.BaseURL == "" {
 		options.BaseURL = "https://api.atlascloud.ai"
@@ -93,9 +93,10 @@ func (c ToolCall) Scan(v any) error {

 // ToolResult represents the result of a tool execution
 type ToolResult struct {
-	ID      string // Tool call ID (for correlation)
-	Value   any    // Structured result (optional)
-	Content string // Tool execution result (JSON string), shown to the model
+	ID       string // Tool call ID (for correlation)
+	Value    any    // Structured result (optional)
+	Content  string // Tool execution result (JSON string), shown to the model
+	Attempts int    `json:"attempts,omitempty"` // Tool execution attempts, set when retried.
 	// Refused names the reason a guardrail blocked the call before it ran
 	// ("max_steps", "loop", "approval"); empty when the call executed. A
 	// tool wrapper can switch on it to build reliability tooling — react to
@@ -129,6 +130,8 @@ type RunInfo struct {
 	Attempt              int    // current model Generate attempt, starting at 1 when known
 	MaxAttempts          int    // configured model Generate attempt budget when known
 	VerificationFeedback string // feedback from the previous failed verifier attempt, when retrying a flow step
+	Dispatch             string // how the run was dispatched (direct, broker, schedule, resume) when known
+	Trigger              string // external trigger or schedule label that started the run, when known
 }

 type runInfoKey struct{}
@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/http"
 	"net/http/httptest"
+	"os"
 	"reflect"
 	"strings"
 	"testing"
@@ -150,6 +151,109 @@ func TestStreamProvidersCloseCancelsInFlightRequest(t *testing.T) {
 	}
 }

+func TestStreamProvidersPropagateProviderErrors(t *testing.T) {
+	for _, provider := range conformingStreamProviders(t) {
+		provider := provider
+		t.Run(provider, func(t *testing.T) {
+			ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				http.Error(w, "upstream quota exhausted", http.StatusTooManyRequests)
+			}))
+			defer ts.Close()
+
+			stream, err := ai.New(provider, ai.WithAPIKey("test-key"), ai.WithBaseURL(ts.URL)).Stream(context.Background(), &ai.Request{Prompt: "Hello"})
+			if err == nil {
+				_ = stream.Close()
+				t.Fatal("Stream returned nil error for provider failure")
+			}
+			if !strings.Contains(err.Error(), "429") || !strings.Contains(err.Error(), "upstream quota exhausted") {
+				t.Fatalf("Stream error = %v, want provider status and body", err)
+			}
+			if strings.Contains(err.Error(), "test-key") {
+				t.Fatal("provider error leaked API key")
+			}
+		})
+	}
+}
+
+func TestStreamProvidersHonorCanceledContextBeforeRequest(t *testing.T) {
+	for _, provider := range conformingStreamProviders(t) {
+		provider := provider
+		t.Run(provider, func(t *testing.T) {
+			var sawRequest bool
+			ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+				sawRequest = true
+				http.Error(w, "unexpected request", http.StatusInternalServerError)
+			}))
+			defer ts.Close()
+
+			ctx, cancel := context.WithCancel(context.Background())
+			cancel()
+			stream, err := ai.New(provider, ai.WithAPIKey("test-key"), ai.WithBaseURL(ts.URL)).Stream(ctx, &ai.Request{Prompt: "Hello"})
+			if err == nil {
+				_ = stream.Close()
+				t.Fatal("Stream returned nil error for canceled context")
+			}
+			if !errors.Is(err, context.Canceled) {
+				t.Fatalf("Stream error = %v, want context.Canceled", err)
+			}
+			if sawRequest {
+				t.Fatal("provider sent request after context was already canceled")
+			}
+		})
+	}
+}
+
+func TestConfiguredProviderStreamsSkipWithoutCredentials(t *testing.T) {
+	for _, tc := range []struct {
+		provider string
+		keyEnv   string
+		modelEnv string
+	}{
+		{provider: "openai", keyEnv: "OPENAI_API_KEY", modelEnv: "OPENAI_MODEL"},
+		{provider: "groq", keyEnv: "GROQ_API_KEY", modelEnv: "GROQ_MODEL"},
+		{provider: "mistral", keyEnv: "MISTRAL_API_KEY", modelEnv: "MISTRAL_MODEL"},
+		{provider: "together", keyEnv: "TOGETHER_API_KEY", modelEnv: "TOGETHER_MODEL"},
+		{provider: "atlascloud", keyEnv: "ATLASCLOUD_API_KEY", modelEnv: "ATLASCLOUD_MODEL"},
+	} {
+		tc := tc
+		t.Run(tc.provider, func(t *testing.T) {
+			key := os.Getenv(tc.keyEnv)
+			if key == "" {
+				t.Skipf("%s not set; skipping configured provider stream check", tc.keyEnv)
+			}
+
+			opts := []ai.Option{ai.WithAPIKey(key)}
+			if model := os.Getenv(tc.modelEnv); model != "" {
+				opts = append(opts, ai.WithModel(model))
+			}
+			stream, err := ai.New(tc.provider, opts...).Stream(context.Background(), &ai.Request{Prompt: "Reply with exactly: ok"})
+			if err != nil {
+				t.Fatalf("Stream returned error: %v", err)
+			}
+			defer stream.Close()
+
+			deadline := time.After(30 * time.Second)
+			for {
+				select {
+				case <-deadline:
+					t.Fatal("timed out waiting for provider stream chunk")
+				default:
+				}
+				chunk, err := stream.Recv()
+				if err != nil {
+					if errors.Is(err, io.EOF) {
+						t.Fatal("provider stream ended without content")
+					}
+					t.Fatalf("Recv returned error: %v", err)
+				}
+				if chunk.Reply != "" {
+					return
+				}
+			}
+		})
+	}
+}
+
 func TestUnsupportedProvidersReturnStreamingUnsupportedAndStayUnregistered(t *testing.T) {
 	for _, provider := range []string{"anthropic", "gemini"} {
 		provider := provider
@@ -324,4 +324,4 @@ Apache 2.0 - See [LICENSE](../../LICENSE) for details.
 ## Support

 - GitHub Discussions: https://github.com/micro/go-micro/discussions
- Discord: https://discord.gg/WeMU5AGxD
+- Discord: https://discord.gg/G8Gk5j3uXr
@@ -102,4 +102,4 @@ pytest tests/integration/ -v
 ## Questions?

 - GitHub Discussions: https://github.com/micro/go-micro/discussions
- Discord: https://discord.gg/WeMU5AGxD
+- Discord: https://discord.gg/G8Gk5j3uXr
@@ -370,4 +370,4 @@ Apache 2.0 - See [LICENSE](../../LICENSE) for details.
 ## Support

 - GitHub Discussions: https://github.com/micro/go-micro/discussions
- Discord: https://discord.gg/WeMU5AGxD
+- Discord: https://discord.gg/G8Gk5j3uXr
@@ -7,6 +7,7 @@ import (

 	"go-micro.dev/v6/client"
 	codecbytes "go-micro.dev/v6/codec/bytes"
+	"go-micro.dev/v6/store"
 )

 // fakeClient embeds the default client (so NewRequest works) and
@@ -65,3 +66,65 @@ func TestExecuteDispatchesToAgent(t *testing.T) {
 		t.Errorf("rendered prompt = %q, want %q", results[0].Prompt, "welcome bob")
 	}
 }
+
+// A caller-owned schedule can trigger an agent workflow without a human chat
+// prompt and still leave the normal flow run metadata behind for inspection.
+func TestScheduledAgentRunHarnessContract(t *testing.T) {
+	ctx := context.Background()
+	cp := StoreCheckpoint(store.NewMemoryStore(), "scheduled-contract")
+	f := New("scheduled-contract",
+		Trigger("schedule.daily"),
+		WithCheckpoint(cp),
+		Steps(Step{Name: "summarize", Run: Dispatch("ops-agent")}),
+	)
+
+	var parentID string
+	f.client = &fakeClient{
+		Client: client.DefaultClient,
+		callFn: func(req client.Request, rsp interface{}) error {
+			if req.Service() != "ops-agent" || req.Endpoint() != "Agent.Chat" {
+				t.Fatalf("dispatched to %s.%s, want ops-agent.Agent.Chat", req.Service(), req.Endpoint())
+			}
+			reqFrame := req.Body().(*codecbytes.Frame)
+			var body map[string]string
+			if err := json.Unmarshal(reqFrame.Data, &body); err != nil {
+				t.Fatalf("request body: %v", err)
+			}
+			parentID = body["parent_id"]
+			if body["message"] != "run unattended daily ops review" {
+				t.Fatalf("message = %q, want scheduled payload", body["message"])
+			}
+			frame := rsp.(*codecbytes.Frame)
+			frame.Data = []byte(`{"reply":"review queued","agent":"ops-agent","parent_id":"` + parentID + `"}`)
+			return nil
+		},
+	}
+
+	if err := Scheduled(f, "run unattended daily ops review").Tick(ctx); err != nil {
+		t.Fatalf("scheduled tick: %v", err)
+	}
+	if parentID == "" {
+		t.Fatal("dispatch did not receive the scheduled flow run id as parent_id")
+	}
+
+	runs, err := cp.List(ctx)
+	if err != nil {
+		t.Fatalf("list scheduled runs: %v", err)
+	}
+	if len(runs) != 1 {
+		t.Fatalf("got %d runs, want 1", len(runs))
+	}
+	run := runs[0]
+	if run.ID != parentID {
+		t.Fatalf("run ID = %q, parent_id = %q", run.ID, parentID)
+	}
+	if run.Flow != "scheduled-contract" || run.Status != "done" {
+		t.Fatalf("run = %+v, want scheduled-contract done", run)
+	}
+	if got := run.State.String(); got != "review queued" {
+		t.Fatalf("run result = %q, want agent reply", got)
+	}
+	if len(run.Steps) != 1 || run.Steps[0].Name != "summarize" || run.Steps[0].Status != "done" {
+		t.Fatalf("steps = %+v, want summarize done", run.Steps)
+	}
+}
@@ -142,7 +142,8 @@ func (f *Flow) Register(reg registry.Registry, br broker.Broker, cl client.Clien
 	if f.opts.TriggerTopic != "" {
 		sub, err := br.Subscribe(f.opts.TriggerTopic, func(p broker.Event) error {
 			data := string(p.Message().Body)
-			if err := f.Execute(context.Background(), data); err != nil {
+			ctx := ai.WithRunInfo(context.Background(), ai.RunInfo{Dispatch: "broker", Trigger: f.opts.TriggerTopic})
+			if err := f.Execute(ctx, data); err != nil {
 				f.log.Logf(logger.ErrorLevel, "Flow %s failed: %v", f.name, err)
 			}
 			return nil
@@ -223,7 +224,10 @@ func (f *Flow) Execute(ctx context.Context, data string) error {
 	}

 	runID := uuid.New().String()
-	ctx = ai.WithRunInfo(ctx, ai.RunInfo{RunID: runID, Flow: f.name})
+	info, _ := ai.RunInfoFrom(ctx)
+	info.RunID = runID
+	info.Flow = f.name
+	ctx = ai.WithRunInfo(ctx, info)

 	start := time.Now()

@@ -26,6 +26,8 @@ const (
 	AttrFlowErrorKind          = "flow.error.kind"
 	AttrFlowVerificationStatus = "flow.verification.status"
 	AttrFlowVerificationNote   = "flow.verification.note"
+	AttrFlowDispatch           = "flow.dispatch"
+	AttrFlowTrigger            = "flow.trigger"
 )

 func (f *Flow) tracer() trace.Tracer {
@@ -36,12 +38,15 @@ func (f *Flow) startRunSpan(ctx context.Context, run Run) (context.Context, func
 	if f.opts.TraceProvider == nil {
 		return ctx, func(Run, error) {}
 	}
-	ctx, span := f.tracer().Start(ctx, spanNameFlowRun, trace.WithSpanKind(trace.SpanKindInternal), trace.WithAttributes(
+	info, _ := ai.RunInfoFrom(ctx)
+	attrs := []attribute.KeyValue{
 		attribute.String(AttrFlowRunID, run.ID),
 		attribute.String(AttrFlowParentID, run.ParentID),
 		attribute.String(AttrFlowName, f.name),
 		attribute.String(AttrFlowStatus, run.Status),
-	))
+	}
+	attrs = appendRunInfoDispatch(attrs, info)
+	ctx, span := f.tracer().Start(ctx, spanNameFlowRun, trace.WithSpanKind(trace.SpanKindInternal), trace.WithAttributes(attrs...))
 	start := time.Now()
 	return ctx, func(done Run, err error) {
 		span.SetAttributes(
@@ -64,12 +69,14 @@ func (f *Flow) runStepSpan(ctx context.Context, step Step, in State) (State, int
 		return f.runStep(ctx, step, in)
 	}
 	info, _ := ai.RunInfoFrom(ctx)
-	ctx, span := f.tracer().Start(ctx, spanNameFlowStep, trace.WithAttributes(
+	attrs := []attribute.KeyValue{
 		attribute.String(AttrFlowRunID, info.RunID),
 		attribute.String(AttrFlowParentID, info.ParentID),
 		attribute.String(AttrFlowName, f.name),
 		attribute.String(AttrFlowStepName, step.Name),
-	))
+	}
+	attrs = appendRunInfoDispatch(attrs, info)
+	ctx, span := f.tracer().Start(ctx, spanNameFlowStep, trace.WithAttributes(attrs...))
 	start := time.Now()
 	out, attempts, verification, err := f.runStep(ctx, step, in)
 	span.SetAttributes(
@@ -95,3 +102,13 @@ func (f *Flow) runStepSpan(ctx context.Context, step Step, in State) (State, int
 	span.End()
 	return out, attempts, verification, err
 }
+
+func appendRunInfoDispatch(attrs []attribute.KeyValue, info ai.RunInfo) []attribute.KeyValue {
+	if info.Dispatch != "" {
+		attrs = append(attrs, attribute.String(AttrFlowDispatch, info.Dispatch))
+	}
+	if info.Trigger != "" {
+		attrs = append(attrs, attribute.String(AttrFlowTrigger, info.Trigger))
+	}
+	return attrs
+}
@@ -74,3 +74,29 @@ func flowSpanAttributes(attrs []attribute.KeyValue) map[string]string {
 func withTestRunInfo(ctx context.Context, runID string) context.Context {
 	return ai.WithRunInfo(ctx, ai.RunInfo{RunID: runID, Agent: "planner"})
 }
+
+func TestScheduledFlowOpenTelemetryDispatchAttributes(t *testing.T) {
+	exp := tracetest.NewInMemoryExporter()
+	tp := trace.NewTracerProvider(trace.WithSyncer(exp))
+
+	step := Step{Name: "summarize", Run: func(ctx context.Context, in State) (State, error) {
+		in.Data = []byte("queued")
+		return in, nil
+	}}
+	f := New("scheduled-observed", Trigger("schedule.daily"), WithCheckpoint(StoreCheckpoint(store.NewMemoryStore(), "scheduled-observed")), TraceProvider(tp), Steps(step))
+	if err := Scheduled(f, "daily ops review").Tick(context.Background()); err != nil {
+		t.Fatal(err)
+	}
+
+	for _, span := range exp.GetSpans().Snapshots() {
+		if span.Name() != spanNameFlowRun {
+			continue
+		}
+		attrs := flowSpanAttributes(span.Attributes())
+		if attrs[AttrFlowDispatch] != "schedule" || attrs[AttrFlowTrigger] != "schedule.daily" {
+			t.Fatalf("scheduled run span dispatch attributes = %#v", attrs)
+		}
+		return
+	}
+	t.Fatal("flow run span not emitted")
+}
@@ -0,0 +1,60 @@
+package flow
+
+import (
+	"context"
+	"time"
+
+	"go-micro.dev/v6/ai"
+)
+
+// Schedule binds a flow to a recurring work item without introducing a
+// scheduler service. It is a small harness contract: callers own the clock,
+// Go Micro owns turning each tick into the same inspectable flow run used for
+// broker events and direct Execute calls.
+type Schedule struct {
+	flow *Flow
+	data string
+}
+
+// Scheduled returns a deterministic scheduled-run harness for this flow.
+// Tests and event loops can call Tick directly; production processes can wire
+// the same contract to time.Ticker through RunEvery. Each tick calls Execute, so
+// checkpointed run history, parent/run metadata, cancellation, and inspection
+// stay on the normal flow surfaces.
+func Scheduled(f *Flow, data string) Schedule {
+	return Schedule{flow: f, data: data}
+}
+
+// Tick starts one scheduled run immediately and returns when that run finishes.
+func (s Schedule) Tick(ctx context.Context) error {
+	if ctx == nil {
+		ctx = context.Background()
+	}
+	info, _ := ai.RunInfoFrom(ctx)
+	info.Dispatch = "schedule"
+	if info.Trigger == "" {
+		info.Trigger = s.flow.opts.TriggerTopic
+	}
+	if info.Trigger == "" {
+		info.Trigger = "schedule"
+	}
+	return s.flow.Execute(ai.WithRunInfo(ctx, info), s.data)
+}
+
+// RunEvery drives scheduled runs from a ticker until ctx is canceled. It does
+// not persist schedule definitions or host a scheduler; it only adapts a caller
+// owned cadence to Tick.
+func (s Schedule) RunEvery(ctx context.Context, interval time.Duration) error {
+	ticker := time.NewTicker(interval)
+	defer ticker.Stop()
+	for {
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-ticker.C:
+			if err := s.Tick(ctx); err != nil {
+				return err
+			}
+		}
+	}
+}
@@ -433,7 +433,12 @@ func (f *Flow) Pending(ctx context.Context) ([]Run, error) {
 func (f *Flow) runFrom(ctx context.Context, run Run) (Run, error) {
 	steps := f.opts.Steps
 	ctx = withDeps(ctx, &runDeps{client: f.client, model: f.model, tools: f.toolSet})
-	ctx = ai.WithRunInfo(ctx, ai.RunInfo{RunID: run.ID, ParentID: run.ParentID, Agent: f.name, Flow: f.name})
+	info, _ := ai.RunInfoFrom(ctx)
+	info.RunID = run.ID
+	info.ParentID = run.ParentID
+	info.Agent = f.name
+	info.Flow = f.name
+	ctx = ai.WithRunInfo(ctx, info)
 	ctx, finishSpan := f.startRunSpan(ctx, run)
 	var spanErr error
 	defer func() { finishSpan(run, spanErr) }()
@@ -10,6 +10,26 @@ and can stop or revert anything at any time.
 > **services → agents → workflows**. Judge each change against it — work that
 > doesn't move toward that lifecycle isn't an improvement, however clean.

+## The pipeline (planner → generator → evaluator)
+
+The development process is an operational instance of the long-running-agent
+harness pattern ([Anthropic on harness design](https://www.anthropic.com/engineering/harness-design-long-running-apps)) —
+a planner, a generator, and a *separate* evaluator — distributed across GitHub
+Actions instead of subagents. Each role is a workflow:
+
+| Role | Workflow (action name) | What it does |
+|------|------------------------|--------------|
+| **Planner** | `loop-architect.yml` — *Loop: Architect (Planner)* | Tracks live state, prioritizes the roadmap + an internal scan, and maintains the ranked queue in [`PRIORITIES.md`](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)* | On harness failure, root-causes, dedupes, and files scoped fix issues back into the planner's queue. The hill-climbing feedback path. |
+| **Coherence** | `loop-devrel.yml` — *Loop: DevRel* | 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. |
+| **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. |
+
+Generation is separated from evaluation on purpose: an agent grading its own work
+reliably over-rates it, so **CI and the harness — not the builder — are the gate**.
+The human sets direction and owns the calls that need taste (see Guardrails).
+
 ## Autonomy

 Full autonomy, **no approval gates**. Each increment: Claude Code picks the work,
@@ -72,7 +92,7 @@ Grounded in real signal, never speculative rewrites. Each cycle draws from:
  tracking issue for each increment and dispatches Codex there. It needs a
  `CODEX_TRIGGER_TOKEN` repo secret from a user account Codex responds to;
  without that secret the workflow deliberately no-ops to avoid ignored bot
-  comments. See `.github/workflows/continuous-improvement.yml` and the mechanics
+  comments. See `.github/workflows/loop-builder.yml` and the mechanics
  below.

 ## How the durable loop works (mechanics)
@@ -127,13 +147,20 @@ The hourly loop ships increments; two periodic passes keep the *whole* heading i
 the right direction. Both use the same mechanism (fresh issue → `@codex` →
 output) but produce direction and coherence, not just code.

- **DevRel — daily** (`.github/workflows/devrel-review.yml`). Audits the public
+- **DevRel — daily** (`.github/workflows/loop-devrel.yml`). Audits the public
  surface (README, website landing + docs, blog) for coherence with the North
-  Star, README crispness, and blog-worthy material. **Autonomy boundary:** safe
-  factual-alignment and crispness fixes auto-merge like any increment;
-  brand/positioning copy and blog drafts are *surfaced in a report* for the
-  human, never auto-merged.
- **Architect — continuous (hourly)** (`.github/workflows/architecture-review.yml`).
+  Star, README crispness, and blog-worthy material. It also keeps `CHANGELOG.md`
+  living: each run reconciles the `[Unreleased]` section against the PRs that
+  actually merged (Keep-a-Changelog format, user-facing entries only — internal
+  loop/CI churn is skipped), and rolls `[Unreleased]` into a dated version
+  heading whenever a new `v6.MINOR.PATCH` tag has been cut (by `loop-release`).
+  When enough user-facing work has accumulated (roughly weekly, not a near-empty
+  post every day) it also drafts a "what's new" changelog blog post narrating it.
+  **Autonomy boundary:** safe factual-alignment and crispness fixes — *including
+  the `CHANGELOG.md` upkeep* — auto-merge like any increment; brand/positioning
+  copy and the changelog blog post are opened as a PR (or surfaced in the report)
+  and left for the human to review/merge — blog voice stays with the human.
+- **Architect — continuous (hourly)** (`.github/workflows/loop-architect.yml`).
  The *founder lens*, running alongside the builders. Each run it **tracks live
  state** (what just merged, what's in flight), **prioritizes the roadmap**
  (`ROADMAP.md`, Now → Next → Later) against an internal scan (lifecycle gaps, API
@@ -154,6 +181,20 @@ roadmap-driven by default, not a fresh guess every hour. Cadence is tunable in e
 workflow's `cron`; the human can reorder `PRIORITIES.md` or its issues at any time
 to redirect. Codex is serial, so these passes queue behind any in-flight increment.

+## Failure triage (the feedback loop)
+
+The loop also closes on its own failures. `.github/workflows/loop-triage.yml`
+fires when the live provider-conformance harness finishes with `conclusion:
+failure` (scheduled/manual runs only), and dispatches Codex to **triage** the
+failing run: read the logs, root-cause each distinct failure, **dedupe** against
+open issues (comment "recurred" rather than filing a duplicate), and file a scoped
+`codex`/`enhancement` issue for each genuine, self-contained defect — which the
+increment loop then builds and the next harness run verifies. Transient flakes
+(live-model latency, provider outages) are ignored; anything needing a breaking or
+architectural change is escalated as `needs-human` instead of auto-built. This is
+the hill-climbing layer: CI/harness failures become fixes with no human in the
+middle, short of a decision that's genuinely the human's.
+
 ## Stop / redirect

 - In-session: `CronDelete <id>` (or end the session).
@@ -21,11 +21,13 @@ changes, architectural rewrites. Those go to the human.

 ## Work queue (ranked)

-1. **Add a scheduled agent run harness contract** ([#3486](https://github.com/micro/go-micro/issues/3486)) — with conformance, failure/cancellation hardening, checkpoint resume, memory summarization, and A2A continuity now shipped, the highest-value remaining gap is proving unattended agents as first-class operational-harness workloads. This should compose existing services, agents, flows, store-backed memory, verification, conformance, and run inspection so the scaffold → run → chat → inspect lifecycle extends to scheduled/looping work without adding a hosted scheduler, graph DSL, or breaking public APIs.
-
-2. **Export agent `RunInfo` as OpenTelemetry spans** ([#3501](https://github.com/micro/go-micro/issues/3501)) — once agents can run unattended, operators need production-grade visibility that lines up with the existing tracing stack. Map run lifecycle, checkpoints/resume, tool/delegate steps, and terminal failure/cancellation metadata into OpenTelemetry rather than creating a separate observability surface.
-
-3. **Broaden provider-backed `ai.Stream` conformance** ([#3502](https://github.com/micro/go-micro/issues/3502)) — A2A/chat streaming is now a visible UX seam, but the trust story depends on every provider adapter behaving consistently for streaming deltas, cancellation, and errors. Keep this as a conformance extension with mock/no-secret coverage plus provider-gated checks, so interop hardening stays CI-verifiable.
+1. **Make the 0→hero path runnable from the docs** ([#3598](https://github.com/micro/go-micro/issues/3598)) — the debugging guide shipped, so the next highest adoption gap is wayfinding across install, first agent, examples, chat/inspect, and deploy dry-run. Keep this first because the current strategic goal is developer adoption: a new user should be able to walk scaffold → run → chat → inspect → deploy without guessing which guide comes next, and the docs should point at the CI-backed harness that proves it.
+2. **Finalize the universe notify step after an agent-backed timeout** ([#3589](https://github.com/micro/go-micro/issues/3589)) — recent live-provider CI exposed a real services → agents → workflows seam: an agent-backed notify side effect can complete while the client observes a timeout, leaving pending flow state and late duplicate notifications. Keep this high because it protects the 0→hero/reliability contract, but leave the adoption guide first so the queue does not drift back to only internal hardening.
+3. **Prevent duplicate tool side effects in the plan/delegate harness** ([#3559](https://github.com/micro/go-micro/issues/3559)) — correctness still matters where it protects real user trust. Plan/delegate is central to the services → agents lifecycle, and duplicate side effects undermine the “agent as dependable service” story.
+4. **Expose `fallback_echo` during A2A streaming fallback conformance** ([#3560](https://github.com/micro/go-micro/issues/3560)) — keep interop conformance trustworthy without letting it dominate the adoption queue. This is scoped, testable, and protects the A2A promise developers see in the README and site.
+5. **Propagate agent run cancellation and deadlines through model and tool calls** ([#3544](https://github.com/micro/go-micro/issues/3544)) — after the on-ramp items, the highest-value remaining Now-phase resilience gap is predictable failure semantics across agent runs, model calls, tool calls, plan/delegate, and flow handoffs. Tool retries and live-provider deadline tuning are in place; the lifecycle still needs cancellation/deadline propagation so work fails safely instead of becoming opaque loops.
+6. **Emit OpenTelemetry spans for agent run timelines** ([#3525](https://github.com/micro/go-micro/issues/3525)) — recent work made runs inspectable, correlated trace metadata through scheduled dispatch, verified restart resume, added opt-in tool retries, hardened provider conformance, and fixed provider-emitted text tool calls. The next Next-phase step is to turn that RunInfo foundation into standard OTel spans for agent runs, model calls, tool calls, checkpoint/resume, cancellation/deadlines, and failures.
+7. **Add an AP2 mandate layer over A2A and x402** ([#3552](https://github.com/micro/go-micro/issues/3552)) — this is a forward interop investment, not a Now-phase blocker: Go Micro already has A2A agents and x402 paid tools, so a small signed-mandate foundation can keep agent payments aligned with the open-protocol story without pulling the queue away from adoption, resilience, or observability. Keep it additive and opt-in while the AP2/FIDO work settles.

 _Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
 architecture-review pass._
@@ -24,6 +24,7 @@ import (
 	"go-micro.dev/v6/agent"
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/gateway/a2a"
+	"go-micro.dev/v6/internal/harness/harnessutil"
 	"go-micro.dev/v6/registry"
 	"go-micro.dev/v6/store"
 )
@@ -95,7 +96,7 @@ func main() {
 	reg := registry.NewMemoryRegistry()
 	st := store.NewMemoryStore()
 	var sawTool, sawRunInfo bool
-	ag := agent.New(
+	agentOpts := []agent.Option{
 		agent.Name("a2a-fallback"),
 		agent.Provider(*provider),
 		agent.APIKey(apiKey),
@@ -103,7 +104,7 @@ func main() {
 		agent.WithRegistry(reg),
 		agent.WithStore(st),
 		agent.WithMemory(agent.NewInMemory(8)),
-		agent.ModelCallTimeout(45*time.Second),
+		agent.ModelCallTimeout(45 * time.Second),
 		agent.WithTool("fallback_echo", "Echo the A2A fallback marker.", map[string]any{
 			"value": map[string]any{"type": "string", "description": "value to echo"},
 		}, func(ctx context.Context, input map[string]any) (string, error) {
@@ -118,7 +119,9 @@ func main() {
 			}
 			return `{"marker":"a2a-fallback-ok"}`, nil
 		}),
-	)
+	}
+	agentOpts = append(agentOpts, harnessutil.AgentOptions(*provider)...)
+	ag := agent.New(agentOpts...)

 	card := a2a.Card("a2a-fallback", "http://example.invalid/a2a-fallback", "", nil)
 	handler := a2a.NewAgentStreamHandler(card, func(ctx context.Context, text string) (string, error) {
@@ -25,10 +25,9 @@ import (
 	"go-micro.dev/v6/agent"
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/broker"
-	"go-micro.dev/v6/client"
 	"go-micro.dev/v6/flow"
+	"go-micro.dev/v6/internal/harness/harnessutil"
 	"go-micro.dev/v6/registry"
-	"go-micro.dev/v6/selector"
 	"go-micro.dev/v6/service"
 	"go-micro.dev/v6/store"
 )
@@ -203,8 +202,9 @@ func main() {
 		fmt.Println("broker connect:", err)
 		os.Exit(1)
 	}
-	cl := client.NewClient(client.Registry(reg), client.Selector(selector.NewSelector(selector.Registry(reg))))
+	cl := harnessutil.Client(*provider, reg)
 	mem := store.NewMemoryStore()
+	liveAgentOpts := harnessutil.AgentOptions(*provider)

 	wsSvc := new(WorkspaceService)
 	ws := service.New(service.Name("workspace"), service.Address("127.0.0.1:0"), service.Registry(reg), service.Client(cl))
@@ -217,7 +217,7 @@ func main() {
 	go nt.Run()

 	// The onboarder agent, registered so the flow can reach it over RPC.
-	onboarder := agent.New(
+	onboarderOpts := []agent.Option{
 		agent.Name("onboarder"),
 		agent.Address("127.0.0.1:0"),
 		agent.Services("workspace", "notify"),
@@ -225,7 +225,9 @@ func main() {
 		agent.Provider(*provider),
 		agent.APIKey(apiKey),
 		agent.WithRegistry(reg), agent.WithClient(cl), agent.WithStore(mem),
-	)
+	}
+	onboarderOpts = append(onboarderOpts, liveAgentOpts...)
+	onboarder := agent.New(onboarderOpts...)
 	go onboarder.Run()
 	defer onboarder.Stop()

@@ -238,6 +240,7 @@ func main() {
 		flow.Trigger("events.user.created"),
 		flow.Agent("onboarder"),
 		flow.Prompt("A new user signed up: {{.Data}}. Get them set up."),
+		flow.Timeout(harnessutil.LiveTimeout(*provider)),
 	)
 	if err := f.Register(reg, br, cl); err != nil {
 		fmt.Println("flow register:", err)
@@ -0,0 +1,61 @@
+package harnessutil
+
+import (
+	"fmt"
+	"os"
+	"time"
+
+	"go-micro.dev/v6/agent"
+	"go-micro.dev/v6/client"
+	"go-micro.dev/v6/registry"
+	"go-micro.dev/v6/selector"
+)
+
+const (
+	// LiveTimeoutEnv overrides the per-call deadline used by live-provider
+	// harness runs. It intentionally does not affect deterministic mock runs.
+	LiveTimeoutEnv = "GO_MICRO_HARNESS_LIVE_TIMEOUT"
+	// DefaultLiveTimeout is generous enough for slow but correct hosted models
+	// while still bounding genuinely stuck live conformance runs.
+	DefaultLiveTimeout = 5 * time.Minute
+)
+
+// LiveTimeout returns the harness per-call timeout for live providers. Mock runs
+// keep their historical fast defaults by returning zero.
+func LiveTimeout(provider string) time.Duration {
+	if provider == "mock" {
+		return 0
+	}
+	if raw := os.Getenv(LiveTimeoutEnv); raw != "" {
+		d, err := time.ParseDuration(raw)
+		if err != nil {
+			fmt.Fprintf(os.Stderr, "invalid %s=%q; using %s\n", LiveTimeoutEnv, raw, DefaultLiveTimeout)
+			return DefaultLiveTimeout
+		}
+		return d
+	}
+	return DefaultLiveTimeout
+}
+
+// Client returns an in-memory-registry client. Live provider harnesses get a
+// larger request timeout so an otherwise correct agent run is not cut off by the
+// default 30-second RPC deadline; mock runs are unchanged.
+func Client(provider string, reg registry.Registry) client.Client {
+	opts := []client.Option{
+		client.Registry(reg),
+		client.Selector(selector.NewSelector(selector.Registry(reg))),
+	}
+	if d := LiveTimeout(provider); d > 0 {
+		opts = append(opts, client.RequestTimeout(d))
+	}
+	return client.NewClient(opts...)
+}
+
+// AgentOptions applies the same live-provider timeout to model and tool calls.
+// The empty result for mock runs preserves their deterministic timing.
+func AgentOptions(provider string) []agent.Option {
+	if d := LiveTimeout(provider); d > 0 {
+		return []agent.Option{agent.ModelCallTimeout(d), agent.ToolCallTimeout(d)}
+	}
+	return nil
+}
@@ -0,0 +1,33 @@
+package harnessutil
+
+import (
+	"testing"
+	"time"
+)
+
+func TestLiveTimeoutLeavesMockUnchanged(t *testing.T) {
+	t.Setenv(LiveTimeoutEnv, "2m")
+	if got := LiveTimeout("mock"); got != 0 {
+		t.Fatalf("LiveTimeout(mock) = %s, want 0", got)
+	}
+	if opts := AgentOptions("mock"); len(opts) != 0 {
+		t.Fatalf("AgentOptions(mock) length = %d, want 0", len(opts))
+	}
+}
+
+func TestLiveTimeoutUsesDefaultForLiveProviders(t *testing.T) {
+	t.Setenv(LiveTimeoutEnv, "")
+	if got := LiveTimeout("atlascloud"); got != DefaultLiveTimeout {
+		t.Fatalf("LiveTimeout(live) = %s, want %s", got, DefaultLiveTimeout)
+	}
+	if opts := AgentOptions("atlascloud"); len(opts) != 2 {
+		t.Fatalf("AgentOptions(live) length = %d, want 2", len(opts))
+	}
+}
+
+func TestLiveTimeoutCanBeOverridden(t *testing.T) {
+	t.Setenv(LiveTimeoutEnv, "90s")
+	if got := LiveTimeout("anthropic"); got != 90*time.Second {
+		t.Fatalf("LiveTimeout override = %s, want 90s", got)
+	}
+}
@@ -26,10 +26,9 @@ import (
 	"go-micro.dev/v6/agent"
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/broker"
-	"go-micro.dev/v6/client"
 	"go-micro.dev/v6/flow"
+	"go-micro.dev/v6/internal/harness/harnessutil"
 	"go-micro.dev/v6/registry"
-	"go-micro.dev/v6/selector"
 	"go-micro.dev/v6/service"
 	"go-micro.dev/v6/store"
 )
@@ -241,8 +240,9 @@ func runPlanDelegate(provider string) error {
 	fmt.Print("Real services, registry, RPC, agent loop, store, delegation.\n\n")

 	reg := registry.NewMemoryRegistry()
-	cl := client.NewClient(client.Registry(reg), client.Selector(selector.NewSelector(selector.Registry(reg))))
+	cl := harnessutil.Client(provider, reg)
 	mem := store.NewMemoryStore()
+	liveAgentOpts := harnessutil.AgentOptions(provider)

 	// Real services.
 	taskSvc := new(TaskService)
@@ -260,26 +260,30 @@ func runPlanDelegate(provider string) error {
 	go notify.Run()

 	// Real comms agent (owns notify), registered so delegate reaches it over RPC.
-	comms := agent.New(
+	commsOpts := []agent.Option{
 		agent.Name("comms"),
 		agent.Address("127.0.0.1:0"),
 		agent.Services("notify"),
 		agent.Prompt("You handle outbound notifications. Use the notify service."),
 		agent.Provider(provider), agent.APIKey(apiKey),
 		agent.WithRegistry(reg), agent.WithClient(cl), agent.WithStore(mem),
-	)
+	}
+	commsOpts = append(commsOpts, liveAgentOpts...)
+	comms := agent.New(commsOpts...)
 	go comms.Run()
 	defer comms.Stop()

 	// Real conductor agent (owns task), registered so the flow can reach it over RPC.
-	conductor := agent.New(
+	conductorOpts := []agent.Option{
 		agent.Name("conductor"),
 		agent.Address("127.0.0.1:0"),
 		agent.Services("task"),
 		agent.Prompt("You coordinate launch work. Plan first, create tasks, and delegate notifications to the \"comms\" agent."),
 		agent.Provider(provider), agent.APIKey(apiKey),
 		agent.WithRegistry(reg), agent.WithClient(cl), agent.WithStore(mem),
-	)
+	}
+	conductorOpts = append(conductorOpts, liveAgentOpts...)
+	conductor := agent.New(conductorOpts...)
 	go conductor.Run()
 	defer conductor.Stop()

@@ -303,6 +307,7 @@ func runPlanDelegate(provider string) error {
 	f := flow.New("zero-to-hero",
 		flow.Agent("conductor"),
 		flow.Prompt("Create three launch tasks (Design, Build, Ship), then make sure owner@acme.com is notified: {{.Data}}"),
+		flow.Timeout(harnessutil.LiveTimeout(provider)),
 	)
 	if err := f.Register(reg, broker.DefaultBroker, cl); err != nil {
 		return fmt.Errorf("flow register: %w", err)
@@ -20,7 +20,11 @@ agent test and the harnesses in `internal/harness`:
  preserving run metadata.

 The command also emits the registered provider capability matrix so the run shows
-which providers advertise model, image, video, and streaming support.
+which providers advertise model, image, video, and streaming support. Console output
+and summary artifacts label each harness with the phase it is proving (for example,
+model call + tool call, workflow event + tool call, or streaming fallback + tool
+call), so provider failures identify the failed lifecycle phase instead of only the
+provider name.

 ## Local usage

@@ -36,6 +36,14 @@ import (

 const defaultHarnesses = "agent,universe,agent-flow,plan-delegate,a2a-stream-fallback"

+var harnessPhases = map[string]string{
+	"agent":               "model call + tool call",
+	"universe":            "service discovery + tool call",
+	"agent-flow":          "workflow event + tool call",
+	"plan-delegate":       "plan persistence + delegation + tool call",
+	"a2a-stream-fallback": "streaming fallback + tool call",
+}
+
 var providerEnv = map[string]string{
 	"anthropic":  "ANTHROPIC_API_KEY",
 	"openai":     "OPENAI_API_KEY",
@@ -92,15 +100,16 @@ func main() {
 		}

 		for _, harness := range harnesses {
-			fmt.Printf("\n==> %s / %s\n", provider, harness)
+			phase := harnessPhase(harness)
+			fmt.Printf("\n==> %s / %s (%s)\n", provider, harness, phase)
 			if err := runHarness(provider, harness, *timeoutFlag); err != nil {
-				fmt.Printf("FAIL %s / %s: %v\n", provider, harness, err)
+				fmt.Printf("FAIL %s / %s (%s): %v\n", provider, harness, phase, err)
 				failed++
-				results = append(results, conformanceResult{Provider: provider, Harness: harness, Status: statusFailed, Error: err.Error()})
+				results = append(results, conformanceResult{Provider: provider, Harness: harness, Phase: phase, Status: statusFailed, Error: err.Error()})
 				continue
 			}
 			ran++
-			results = append(results, conformanceResult{Provider: provider, Harness: harness, Status: statusPassed})
+			results = append(results, conformanceResult{Provider: provider, Harness: harness, Phase: phase, Status: statusPassed})
 		}
 	}

@@ -140,6 +149,7 @@ const (
 type conformanceResult struct {
 	Provider string `json:"provider"`
 	Harness  string `json:"harness,omitempty"`
+	Phase    string `json:"phase,omitempty"`
 	Status   string `json:"status"`
 	Error    string `json:"error,omitempty"`
 }
@@ -176,14 +186,18 @@ func writeSummaryMarkdown(path string, summary conformanceSummary) error {
 	b.WriteString("## Capability matrix\n\n")
 	b.WriteString(capabilityMarkdown(summary.Capabilities))
 	b.WriteString("\n## Harness results\n\n")
-	b.WriteString("| Provider | Harness | Status | Detail |\n")
-	b.WriteString("| --- | --- | --- | --- |\n")
+	b.WriteString("| Provider | Harness | Phase | Status | Detail |\n")
+	b.WriteString("| --- | --- | --- | --- | --- |\n")
 	for _, result := range summary.Results {
 		harness := result.Harness
 		if harness == "" {
 			harness = "—"
 		}
-		fmt.Fprintf(&b, "| %s | %s | %s | %s |\n", result.Provider, harness, result.Status, markdownCell(result.Error))
+		phase := result.Phase
+		if phase == "" {
+			phase = "—"
+		}
+		fmt.Fprintf(&b, "| %s | %s | %s | %s | %s |\n", result.Provider, harness, markdownCell(phase), result.Status, markdownCell(result.Error))
 	}
 	return os.WriteFile(path, []byte(b.String()), 0o644)
 }
@@ -209,6 +223,13 @@ func markdownList(values []string) string {
 	return strings.Join(escaped, ", ")
 }

+func harnessPhase(harness string) string {
+	if phase, ok := harnessPhases[harness]; ok {
+		return phase
+	}
+	return "harness"
+}
+
 func markdownCell(s string) string {
 	if s == "" {
 		return "—"
@@ -99,7 +99,7 @@ func TestWriteSummaryMarkdown(t *testing.T) {
 	summary := conformanceSummary{
 		Capabilities: []ai.CapabilityRow{{Provider: "mock", Capabilities: ai.Capabilities{Model: true}}},
 		Results: []conformanceResult{
-			{Provider: "mock", Harness: "agent-flow", Status: statusPassed},
+			{Provider: "mock", Harness: "agent-flow", Phase: harnessPhase("agent-flow"), Status: statusPassed},
 			{Provider: "live", Status: statusSkipped, Error: "missing | key"},
 		},
 		Passed:  1,
@@ -120,8 +120,8 @@ func TestWriteSummaryMarkdown(t *testing.T) {
 		"Providers: —.",
 		"Harnesses: —.",
 		"| mock | ✅ | — | — | — |",
-		"| mock | agent-flow | passed | — |",
-		"| live | — | skipped | missing \\| key |",
+		"| mock | agent-flow | workflow event + tool call | passed | — |",
+		"| live | — | — | skipped | missing \\| key |",
 	} {
 		if !strings.Contains(got, want) {
 			t.Fatalf("summary markdown = %q, want %q", got, want)
@@ -129,6 +129,15 @@ func TestWriteSummaryMarkdown(t *testing.T) {
 	}
 }

+func TestHarnessPhaseLabelsKnownHarnesses(t *testing.T) {
+	if got := harnessPhase("a2a-stream-fallback"); got != "streaming fallback + tool call" {
+		t.Fatalf("harnessPhase() = %q, want streaming fallback phase", got)
+	}
+	if got := harnessPhase("custom"); got != "harness" {
+		t.Fatalf("harnessPhase(custom) = %q, want fallback phase", got)
+	}
+}
+
 func TestMarkdownListEscapesBackticks(t *testing.T) {
 	got := markdownList([]string{"agent", "bad`name"})
 	want := "`agent`, `bad\\`name`"
@@ -38,11 +38,10 @@ import (
 	"go-micro.dev/v6/agent"
 	"go-micro.dev/v6/ai"
 	"go-micro.dev/v6/broker"
-	"go-micro.dev/v6/client"
 	"go-micro.dev/v6/flow"
 	"go-micro.dev/v6/gateway/a2a"
+	"go-micro.dev/v6/internal/harness/harnessutil"
 	"go-micro.dev/v6/registry"
-	"go-micro.dev/v6/selector"
 	"go-micro.dev/v6/service"
 	"go-micro.dev/v6/store"
 )
@@ -229,8 +228,9 @@ func runUniverse(provider string) int {
 		fmt.Println("broker connect:", err)
 		return 2
 	}
-	cl := client.NewClient(client.Registry(reg), client.Selector(selector.NewSelector(selector.Registry(reg))))
+	cl := harnessutil.Client(provider, reg)
 	st := store.NewMemoryStore()
+	liveAgentOpts := harnessutil.AgentOptions(provider)

 	// Services.
 	inv, pay, ord, ntf := new(Inventory), new(Payment), new(Orders), new(Notify)
@@ -243,7 +243,7 @@ func runUniverse(provider string) int {
 	// The concierge agent: guardrails on, plus a tool-execution wrapper
 	// that counts calls — to prove the wrapper seam runs end-to-end.
 	var wrapped int64
-	concierge := agent.New(
+	conciergeOpts := []agent.Option{
 		agent.Name("concierge"),
 		agent.Services("notify"),
 		agent.Prompt("You notify buyers when their order is confirmed."),
@@ -257,7 +257,9 @@ func runUniverse(provider string) int {
 			}
 		}),
 		agent.WithRegistry(reg), agent.WithClient(cl), agent.WithStore(st),
-	)
+	}
+	conciergeOpts = append(conciergeOpts, liveAgentOpts...)
+	concierge := agent.New(conciergeOpts...)
 	go concierge.Run()
 	defer concierge.Stop()

@@ -268,6 +270,7 @@ func runUniverse(provider string) int {
 	checkout := flow.New("checkout",
 		flow.Trigger("events.order.placed"),
 		flow.WithCheckpoint(flow.StoreCheckpoint(st, "checkout")),
+		flow.Timeout(harnessutil.LiveTimeout(provider)),
 		flow.Steps(
 			flow.Step{Name: "reserve", Run: flow.Call("inventory", "Inventory.Reserve")},
 			flow.Step{Name: "charge", Run: flow.Call("payment", "Payment.Charge")},
@@ -0,0 +1,81 @@
+package zerotoheroci
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestZeroToHeroReferenceDocs(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+
+	guide := readFile(t, filepath.Join(root, "internal", "website", "docs", "guides", "zero-to-hero.md"))
+	for _, want := range []string{
+		"make harness",
+		"go test ./cmd/micro/cli/new -run TestZeroToOne -count=1",
+		"go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1",
+		"go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1",
+		"./internal/harness/zero-to-hero-ci/run.sh",
+		"go run ./internal/harness/agent-flow",
+		"make provider-conformance-mock",
+		"internal/harness/plan-delegate",
+		"internal/harness/universe",
+	} {
+		if !strings.Contains(guide, want) {
+			t.Fatalf("0→hero guide missing %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")
+	}
+
+	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") {
+		t.Fatal("website navigation does not expose the canonical 0→hero guide")
+	}
+}
+
+func TestGuidesNavigationLeadsWithDoing(t *testing.T) {
+	root := filepath.Clean(filepath.Join("..", "..", ".."))
+	nav := readFile(t, filepath.Join(root, "internal", "website", "_data", "navigation.yml"))
+
+	orderedGuides := []string{
+		"/docs/guides/your-first-agent.html",
+		"/docs/guides/zero-to-hero.html",
+		"/docs/guides/plan-delegate.html",
+		"/docs/guides/agent-guardrails.html",
+		"/docs/guides/agents-and-workflows.html",
+		"/docs/guides/agent-patterns.html",
+		"/docs/guides/agent-harness.html",
+		"/docs/guides/agent-loops.html",
+	}
+
+	last := -1
+	for _, guide := range orderedGuides {
+		idx := strings.Index(nav, guide)
+		if idx == -1 {
+			t.Fatalf("website navigation does not expose %s", guide)
+		}
+		if idx < last {
+			t.Fatalf("website navigation should lead with hands-on guides; %s appeared out of order", guide)
+		}
+		last = idx
+
+		doc := strings.TrimPrefix(strings.TrimSuffix(guide, ".html"), "/docs/") + ".md"
+		if _, err := os.Stat(filepath.Join(root, "internal", "website", "docs", doc)); err != nil {
+			t.Fatalf("navigation links to missing guide %s: %v", guide, err)
+		}
+	}
+}
+
+func readFile(t *testing.T, name string) string {
+	t.Helper()
+	data, err := os.ReadFile(name)
+	if err != nil {
+		t.Fatalf("read %s: %v", name, err)
+	}
+	return string(data)
+}
@@ -32,26 +32,34 @@ examples:
  - title: Real-World Examples
    url: /docs/examples/realworld/
 guides:
-  - title: The Agent Harness
-    url: /docs/guides/agent-harness.html
-  - title: Agents and Workflows
-    url: /docs/guides/agents-and-workflows.html
-  - title: Agent Loops
-    url: /docs/guides/agent-loops.html
+  - title: Your First Agent
+    url: /docs/guides/your-first-agent.html
+  - title: Debugging your agent
+    url: /docs/guides/debugging-agents.html
+  - title: 0→hero Reference
+    url: /docs/guides/zero-to-hero.html
  - title: Plan & Delegate
    url: /docs/guides/plan-delegate.html
  - title: Agent Guardrails
    url: /docs/guides/agent-guardrails.html
-  - title: Payments (x402)
-    url: /docs/guides/x402-payments.html
+  - title: Agents and Workflows
+    url: /docs/guides/agents-and-workflows.html
+  - title: Agent Integration Patterns
+    url: /docs/guides/agent-patterns.html
+  - title: The Agent Harness
+    url: /docs/guides/agent-harness.html
+  - title: Agent Loops
+    url: /docs/guides/agent-loops.html
  - title: Agent2Agent (A2A)
    url: /docs/guides/a2a-protocol.html
-  - title: Atlas Cloud Integration
-    url: /docs/guides/atlascloud-integration.html
  - title: AI Provider Guide
    url: /docs/guides/ai-provider-guide.html
  - title: Provider Conformance
    url: /docs/guides/provider-conformance.html
+  - title: Atlas Cloud Integration
+    url: /docs/guides/atlascloud-integration.html
+  - title: Payments (x402)
+    url: /docs/guides/x402-payments.html
  - title: Comparison
    url: /docs/guides/comparison.html
  - title: Migration Guides
@@ -70,6 +78,8 @@ project:
  - title: Server (optional)
    url: /docs/server.html
 search_order:
+  - /docs/guides/zero-to-hero.html
+  - /docs/guides/debugging-agents.html
  - /docs/getting-started.html
  - /docs/mcp.html
  - /docs/architecture.html
@@ -1,4 +1,5 @@
 <a href="/docs/">Docs</a> &middot;
 <a href="/blog/">Blog</a> &middot;
 <a href="https://github.com/micro/go-micro">GitHub</a> &middot;
+<a href="https://discord.gg/G8Gk5j3uXr">Discord</a> &middot;
 <a href="/support">Support</a>
@@ -1,4 +1,5 @@
 <a href="/docs/">Docs</a>
 <a href="/blog/">Blog</a>
 <a href="/support"{% if page.nav_active == 'support' %} class="active"{% endif %}>Support</a>
+<a href="https://discord.gg/G8Gk5j3uXr">Discord</a>
 <a href="https://github.com/micro/go-micro">GitHub</a>
@@ -177,4 +177,4 @@ The future of microservices isn't fewer services. It's making them so easy to cr

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -102,4 +102,4 @@ micro chat --provider anthropic

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -144,4 +144,4 @@ The agent for your services answers. Not because you wired it up. Because the sy

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -135,8 +135,8 @@ The store backend determines durability — file-backed by default, Postgres or
 | **What** | Capability | Intelligence | Event orchestration |
 | **Does** | Handles requests | Manages services | Reacts to events |
 | **Knows** | Its endpoints | Its services' endpoints | Its trigger topic |
-| **State** | Store | Store (memory) | Stateless per event |
-| **Create** | `micro.NewService()` | `micro.NewAgent()` | `micro.NewFlow()` |
+| **State** | Store | Store-backed memory | Checkpointed run history |
+| **Create** | `micro.NewService("name")` | `micro.NewAgent("name")` | `micro.NewFlow("name")` |
 | **Package** | `service/` | `agent/` | `flow/` |

 They compose:
@@ -164,7 +164,7 @@ Or build an agent in Go:
 ```go
 package main

-import "go-micro.dev/v5"
+import "go-micro.dev/v6"

 func main() {
    agent := micro.NewAgent("task-mgr",
@@ -176,8 +176,8 @@ func main() {
 }
 ```

-The agent package is at `go-micro.dev/v5/agent`. The full interface design is documented in [AGENT_DESIGN.md](https://github.com/micro/go-micro/blob/master/internal/docs/AGENT_DESIGN.md).
+The agent implementation lives under `go-micro.dev/v6/agent`; most users create agents through the top-level `go-micro.dev/v6` API. The full interface design is documented in [AGENT_DESIGN.md](https://github.com/micro/go-micro/blob/master/internal/docs/AGENT_DESIGN.md).

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -165,4 +165,4 @@ Read the [Plan & Delegate guide](/docs/guides/plan-delegate) for the full refere

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -90,4 +90,4 @@ curl -fsSL https://go-micro.dev/install.sh | sh

 ---

-*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/WeMU5AGxD), or read the [docs](https://go-micro.dev/docs).*
+*Go Micro is open source. Star us on [GitHub](https://github.com/micro/go-micro), join the [Discord](https://discord.gg/G8Gk5j3uXr), or read the [docs](https://go-micro.dev/docs).*
@@ -58,4 +58,4 @@ A small end-to-end harness now boots a real world (services, a durable flow that

 The upshot is that building an agent in Go Micro looks like building a service, because underneath it is one. The infrastructure for a system of agents is, for the most part, the infrastructure for a system of services, and that is the decade of work already in the framework. Services remain the foundation; agents are what we are building on top of them.

-Thanks to Anthropic for the sponsorship. Join us in a new [Discord](https://discord.gg/WeMU5AGxD) to discuss the future of the project. 
+Thanks to Anthropic for the sponsorship. Join us in a new [Discord](https://discord.gg/G8Gk5j3uXr) to discuss the future of the project. 
@@ -49,4 +49,4 @@ V6 is the beginning of something real. It's secure by default, leads with agents

 Projects dont come back from the dead like this. AI brought it back from the dead. Agents made services more relevant. And Claude Code made it possible for me to ship code again.

-Thanks to Anthropic for the grant and the sponsorship. Join me in the [Discord](https://discord.gg/WeMU5AGxD) to discuss further.
+Thanks to Anthropic for the grant and the sponsorship. Join me in the [Discord](https://discord.gg/G8Gk5j3uXr) to discuss further.
@@ -4,14 +4,44 @@ layout: default

 # Learn by Example

-A collection of small, focused examples demonstrating common patterns with Go Micro.
+Runnable examples are the fastest way to move from reading the guides to changing
+one thing. Start with the path that matches where you are in the services →
+agents → workflows lifecycle.

- [Hello Service](hello-service.md)
- [RPC Client](rpc-client.md)
- [Pub/Sub with NATS Broker](pubsub-nats.md)
- [Service Discovery with Consul](registry-consul.md)
- [State with Postgres Store](store-postgres.md)
- [NATS Transport](transport-nats.md)
+## Start here
+
+| Goal | Runnable example | Why it is useful |
+| --- | --- | --- |
+| 0→1 service | [`examples/hello-world`](https://github.com/micro/go-micro/tree/master/examples/hello-world) | Smallest RPC service with a client call and health checks. |
+| First service-backed agent | [`examples/agent-demo`](https://github.com/micro/go-micro/tree/master/examples/agent-demo) | Multi-service project/task/team app with agent playground integration. |
+| 0→hero lifecycle | [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support) | No-secret support-desk story: typed services, an agent, an event-driven flow, and a guardrail. |
+| Planning and delegation | [`examples/agent-plan-delegate`](https://github.com/micro/go-micro/tree/master/examples/agent-plan-delegate) | Two agents collaborate through `plan` and `delegate` over normal Go Micro RPC. |
+| Durable workflows | [`examples/flow-durable`](https://github.com/micro/go-micro/tree/master/examples/flow-durable) | Ordered, checkpointed flow steps resume without duplicating completed side effects. |
+| AI-callable services | [`examples/mcp`](https://github.com/micro/go-micro/tree/master/examples/mcp) | MCP examples that expose service endpoints as model tools. |
+
+## Guide-to-example map
+
+- [Getting Started](../getting-started.html) → run
+  [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support)
+  to see the full lifecycle before generating your own service.
+- [Your First Agent](../guides/your-first-agent.html) → run
+  [`examples/agent-demo`](https://github.com/micro/go-micro/tree/master/examples/agent-demo)
+  or [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support)
+  when you want a complete service-backed agent to inspect.
+- [0→hero Reference](../guides/zero-to-hero.html) → run
+  [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support)
+  for the human-readable scenario, then `make harness` for the full CI contract.
+- [Plan & Delegate](../guides/plan-delegate.html) → run
+  [`examples/agent-plan-delegate`](https://github.com/micro/go-micro/tree/master/examples/agent-plan-delegate).
+- [Agents and Workflows](../guides/agents-and-workflows.html) → run
+  [`examples/flow-durable`](https://github.com/micro/go-micro/tree/master/examples/flow-durable)
+  and [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support).
+
+## Repository examples
+
+See the repository [examples index](https://github.com/micro/go-micro/tree/master/examples)
+for the complete runnable list, including deployment, auth, gRPC interop, MCP,
+agent, and flow examples.

 ## More

@@ -26,13 +26,21 @@ Go Micro has three core abstractions:
 curl -fsSL https://go-micro.dev/install.sh | sh

 # Or with Go
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

-> Use `@v6` (not `@latest`). It selects the newest `v6.x.x` release. Plain `@latest` can currently resolve to a stale pre-rename tag through the public module proxy and fail with a "version constraints conflict"; `@v6` avoids that. To pin an exact version use e.g. `@v6.2.0` (see [releases](https://github.com/micro/go-micro/releases)).
-
 ## Quick Start: Generate from a Prompt

+Prefer to start from a runnable reference? Clone the repository and run the maintained support-desk lifecycle example first:
+
+```bash
+git clone https://github.com/micro/go-micro.git
+cd go-micro
+go run ./examples/support
+```
+
+That example is the no-secret 0→hero path: services expose ticket/customer/notification tools, an agent handles the work, and an event-driven flow triggers the agent. See [Learn by Example](examples/) when you want more runnable starting points.
+
 Describe what you need. The AI designs services, writes handlers, compiles, and starts them:

 ```bash
@@ -70,6 +78,8 @@ Created project Launch and added task 'Write docs' to it.

 The console discovers services from the registry and orchestrates across them via the agent. Use `micro run -d` for detached mode without the console, or `micro chat` as a standalone command.

+If the agent surprises you while iterating, use the [Debugging your agent](guides/debugging-agents.html) guide to inspect service registration, tool calls, run history, memory, provider failures, and flow handoffs.
+
 ## Quick Start: Write a Service

 Create and run a service manually:
@@ -136,6 +146,8 @@ micro new gateway --template api

 ## Building Agents

+For a complete service-backed walkthrough, start with [Your First Agent](guides/your-first-agent.html). If you want to run before you write, use [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support) for the full services → agents → workflows lifecycle or [`examples/agent-plan-delegate`](https://github.com/micro/go-micro/tree/master/examples/agent-plan-delegate) for the smallest multi-agent planning/delegation path.
+
 An Agent is an intelligent layer that manages one or more services:

 ```go
@@ -219,6 +231,8 @@ The flow discovers all services as tools and lets the LLM decide which RPCs to c

 ## Next Steps

+- [Learn by Example](examples/) — runnable examples mapped to services, agents, and workflows
+- [0→hero Reference](guides/zero-to-hero.html) — the maintained no-secret lifecycle contract
 - [AI Integration](ai-integration.html) — how services, agents, MCP, and LLMs fit together
 - [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
@@ -31,7 +31,7 @@ your stack — the harness *is* the stack.
 | Tools | Every service endpoint is an MCP-callable tool from registry metadata — no extra code | Shipped |
 | Memory | Store-backed agent memory (`AgentMemory`), durable across restarts | Shipped |
 | Guardrails | `MaxSteps`, `LoopLimit`, `ApproveTool`, tool wrappers — enforced at the call site | Shipped |
-| Workflows | Durable flows; `flow.Loop` for run-until-done | Shipped |
+| Workflows | Durable flows; `micro.FlowLoop` for run-until-done | Shipped |
 | Planning / delegation | Built-in `plan` and `delegate` tools on every agent | Shipped |
 | Discovery & RPC | Registry + client; agents and services find and call each other | Shipped |
 | Interop | MCP (tools), A2A (agents), x402 (paid tools) | Shipped |
@@ -18,11 +18,11 @@ you're done") has no natural ceiling. So a usable loop needs two things:
 1. a **stop condition** — how it decides it's done, and
 2. a **hard cap** — a guardrail that guarantees it always terminates.

-Go Micro gives you both as a flow step: `flow.Loop`.
+Go Micro gives you both as a flow step: `micro.FlowLoop`.

 ## The shape

-`flow.Loop` is a `StepFunc`, so it drops into a flow's ordered, checkpointed
+`micro.FlowLoop` is a `StepFunc`, so it drops into a flow's ordered, checkpointed
 step list like any other step. It runs a **body** step repeatedly, carrying the
 flow `State` from one pass to the next, until a stop condition fires or the
 iteration cap is hit — whichever comes first.
@@ -89,14 +89,32 @@ Agents use store-backed conversation memory by default, scoped under the agent's
 name. That makes short restarts boring: the next `Ask` reloads the retained
 history from the same store backend you already use for services and flows.
 Long-running agents can also keep model context bounded without losing useful
-prior context:
+prior context. If you want retrieval without summaries, enable bounded active
+context plus a durable archive of every turn:
+
+```go
+a := micro.NewAgent("conductor",
+    micro.AgentServices("task"),
+    micro.AgentProvider("anthropic"),
+    micro.AgentRetrievalMemory(40),        // active messages kept in prompt context
+    micro.AgentMemoryRecallLimit(5),       // archived turns recalled per Ask
+)
+```
+
+`AgentRetrievalMemory(activeLimit)` switches the default memory to a store-backed
+retriever. The active conversation is capped at `activeLimit`, every turn is
+archived in the same scoped store used by the agent, and future asks inject
+matching archived turns ahead of active context. The built-in ranking is
+deterministic and credential-free for CI.
+
+When you also want a rolling summary in active context, use compacting memory:

 ```go
 a := micro.NewAgent("conductor",
    micro.AgentServices("task"),
    micro.AgentProvider("anthropic"),
    micro.AgentCompactMemory(40, 12),      // max active messages, recent messages kept verbatim
-    micro.AgentMemoryRecallLimit(5),       // archived turns recalled per Ask
+    micro.AgentMemoryRecallLimit(5),       // compacted turns recalled per Ask
 )
 ```

@@ -105,8 +123,7 @@ deterministic compactor. Once active history grows past `maxMessages`, older
 turns move into the durable archive, a provider-neutral summary is injected into
 active context, and the newest `keepRecent` messages stay verbatim. On future
 asks, archived turns whose text matches the current request are recalled ahead of
-the active context. The built-in retrieval is intentionally simple and
-credential-free for CI; teams that need embeddings or a vector database can still
+the active context. Teams that need embeddings or a vector database can still
 provide their own `AgentMemory` implementation.

 This is harness memory, not prompt-layer orchestration: services remain the
@@ -17,7 +17,7 @@ A **task management service** with full CRUD operations that:
 ## Prerequisites

 ```bash
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

 ## Step 1: Create the Service
@@ -423,5 +423,5 @@ micro server --address :9000
 ## Need Help?

 - **Issues**: [github.com/micro/go-micro/issues](https://github.com/micro/go-micro/issues)
- **Discord**: [discord.gg/WeMU5AGxD](https://discord.gg/WeMU5AGxD)
+- **Discord**: [discord.gg/G8Gk5j3uXr](https://discord.gg/G8Gk5j3uXr)
 - **Docs**: [go-micro.dev/docs](https://go-micro.dev/docs)
@@ -0,0 +1,235 @@
+---
+layout: default
+title: Debugging your agent
+---
+
+# Debugging your agent
+
+Use this guide when an agent surprises you: it answered without using a service,
+called the wrong endpoint, looped, lost memory, refused a tool, or behaved
+differently when a flow handed work to it. The local inner loop is:
+
+```sh
+micro run          # start services, agents, gateway, dashboard
+micro chat         # reproduce one turn
+micro inspect ...  # read the recorded run or workflow history
+```
+
+Debug the lifecycle in the same order Go Micro runs it: first prove the service is
+registered and callable, then inspect the agent run that chose tools, then inspect
+any workflow that handed off to the agent.
+
+## 1. Reproduce one small turn
+
+Start from the application directory and keep the prompt narrow enough that you
+can tell which tool should have run:
+
+```sh
+micro run
+micro chat --prompt "Create a ticket for Pat, then list open tickets."
+```
+
+For a live provider, make the provider choice explicit so a later retry uses the
+same model boundary:
+
+```sh
+MICRO_AI_PROVIDER=anthropic \
+ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
+micro chat --prompt "Create a ticket for Pat, then list open tickets."
+```
+
+If the provider supports streaming, turn it on while you reproduce the issue:
+
+```sh
+micro chat --provider anthropic --stream
+```
+
+Streaming shows the final answer as it arrives. Tool execution still goes through
+the same agent run and is visible through inspection after the turn completes.
+
+## 2. Prove the service side before blaming the model
+
+Agents only call tools that the runtime can discover and describe. Check the
+service boundary first:
+
+```sh
+micro services
+micro call ticket TicketService.List '{}'
+```
+
+If the service is missing, restart the service under `micro run` and verify it is
+using the same registry as the agent. If the direct `micro call` fails, fix the
+handler, request shape, or auth error there before debugging prompts.
+
+When the agent calls the wrong tool or sends the wrong fields, improve the tool
+description at the service source:
+
+```go
+// Create opens a customer support ticket and returns its stable ticket ID.
+// @example {"customer":"Pat","subject":"Cannot log in"}
+func (s *TicketService) Create(ctx context.Context, req *CreateRequest, rsp *CreateResponse) error {
+```
+
+Endpoint comments, request field names, `description` tags, and `@example` blocks
+are the model's map of your service. A vague handler comment often looks like a
+reasoning failure from the outside.
+
+## 3. Inspect agent run history
+
+After a chat turn, list recent runs for that agent:
+
+```sh
+micro inspect agent support
+```
+
+The output shows the run id, status, number of recorded events, the last event,
+errors, and a short trace id when tracing is configured. Narrow the list while you
+iterate:
+
+```sh
+micro inspect agent support --limit 5
+micro inspect agent support --status timeout
+micro inspect agent support --trace abc123
+micro inspect agent support --json
+```
+
+Useful statuses include `done`, `refused`, `timeout`, `rate_limited`, `canceled`,
+and `error`. Use `--json` when you want exact timestamps, trace/span ids, and error
+kinds for a bug report.
+
+Run timelines are stored in the agent's state store under that agent's scoped
+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.
+
+## 4. See tool calls as they happen
+
+When you are embedding an agent in Go and need live tool visibility, use the
+streaming API instead of waiting for the final answer:
+
+```go
+stream, err := agent.StreamAsk(ctx, ag, "Create a ticket for Pat")
+if err != nil {
+    return err
+}
+for {
+    ev, err := stream.Recv()
+    if err != nil {
+        break
+    }
+    switch ev.Type {
+    case agent.StreamEventToolStart:
+        log.Printf("tool start: %s %#v", ev.ToolCall.Name, ev.ToolCall.Input)
+    case agent.StreamEventToolEnd:
+        log.Printf("tool end: %s %#v", ev.ToolCall.Name, ev.Result)
+    case agent.StreamEventToken:
+        fmt.Print(ev.Token)
+    }
+}
+```
+
+For custom audit logging, wrap the tool execution boundary. Wrappers observe every
+call and result, including guardrail refusals:
+
+```go
+wrapped := micro.AgentWrapTool(func(next ai.ToolHandler) ai.ToolHandler {
+    return func(ctx context.Context, call ai.ToolCall) ai.ToolResult {
+        if run, ok := ai.RunInfoFrom(ctx); ok {
+            log.Printf("run=%s agent=%s tool=%s", run.RunID, run.Agent, call.Name)
+        }
+        res := next(ctx, call)
+        if res.Refused != "" {
+            log.Printf("tool refused: %s reason=%s", call.Name, res.Refused)
+        }
+        return res
+    }
+})
+
+ag := micro.NewAgent("support", wrapped)
+```
+
+Use this when you need request/response payloads in your own logs. By default,
+Go Micro records safe run metadata; raw prompt input is not persisted unless the
+agent is configured with `agent.TraceInputs(true)`.
+
+## 5. Inspect memory and plans
+
+Default agent memory is store-backed and scoped to the agent name. A restarted
+agent with the same `micro.WithStore(...)` and name reloads conversation history
+from the `history` key in `agent/<name>` state. If you pass `micro.WithMemory(...)`,
+you own that backend; if you pass `agent.NewInMemory(...)`, memory disappears on
+restart.
+
+The built-in `plan` tool also saves the current plan to the same scoped agent
+state, so a later turn can pick up the saved plan. When memory does not persist,
+check that all of these are stable across restarts:
+
+- the agent name (`micro.NewAgent("support", ...)`),
+- the configured store backend (`micro.WithStore(...)` or the process default),
+- whether a custom in-memory `Memory` implementation replaced the default,
+- whether compaction/retrieval limits are intentionally hiding older turns from
+  the active model context.
+
+## 6. Inspect workflow handoffs
+
+If a flow triggered the agent, inspect the flow too. The flow history tells you
+which durable stage dispatched to the agent and whether a run is still pending:
+
+```sh
+micro inspect flow intake
+micro inspect flow intake --pending
+micro inspect flow intake --stage notify
+micro inspect flow intake --json
+```
+
+The older flow-specific command remains available for listing runs:
+
+```sh
+micro flow runs intake
+```
+
+Use the flow run id and the agent run id together when debugging handoffs: the
+flow explains why work started and where it checkpointed; the agent run explains
+which model/tool steps happened after the handoff.
+
+## 7. Add traces when metadata is not enough
+
+For local CLI debugging, `micro inspect` is the fastest path. For production or
+multi-service debugging, configure an OpenTelemetry tracer provider on the agent:
+
+```go
+ag := micro.NewAgent("support",
+    micro.AgentTraceProvider(tp),
+)
+```
+
+Trace ids flow into the recorded run summaries, so you can pivot between
+`micro inspect agent support --trace <prefix>` and your trace backend. Keep
+`agent.TraceInputs(true)` off unless your observability backend is approved to
+store prompt content.
+
+## Troubleshooting table
+
+| Symptom | What to inspect | Common fix |
+| --- | --- | --- |
+| Agent answers without calling a service | `micro services`, direct `micro call`, then `micro inspect agent <name>` | Register the service, include it in `micro.AgentServices(...)`, or improve endpoint comments and examples. |
+| Agent loops or burns steps | `micro inspect agent <name> --status error` and wrapper logs | Add or lower `micro.AgentMaxSteps(...)` / `micro.AgentLoopLimit(...)`; move predictable work into a flow. |
+| Tool is refused before it runs | Wrapper logs, `ToolResult.Refused`, `micro inspect agent <name> --status refused` | Update `micro.AgentApproveTool(...)` policy or prompt the user for explicit approval before retrying. |
+| Memory is missing after restart | Agent name, store backend, `WithMemory`, compaction/retrieval settings | Use the default store-backed memory with a persistent store, or persist your custom memory backend. |
+| Flow handoff appears stuck | `micro inspect flow <flow> --pending`, then `micro inspect agent <agent>` | Resume or fail the pending flow run; confirm the dispatched agent completed or timed out. |
+| Provider failed or timed out | `micro inspect agent <name> --status timeout` / `--status rate_limited` | Retry with the same provider/model, raise deadlines where appropriate, or enable provider retries for transient errors. |
+| Tool call appears as assistant text | Agent run history and provider conformance checks | Keep provider packages current; Go Micro normalizes provider-emitted text tool calls, and conformance tests guard this behavior. |
+
+## What to include in a bug report
+
+When you cannot explain the run locally, include:
+
+```sh
+micro inspect agent <agent> --limit 5 --json
+micro inspect flow <flow> --limit 5 --json
+micro services
+micro call <service> <Handler.Method> '{}'
+```
+
+Redact secrets and user data. If you enabled `agent.TraceInputs(true)`, inspect the
+JSON before sharing it because prompts may be present.
@@ -84,7 +84,7 @@ message Response {

 ```bash
 # Install protoc-gen-micro
-go install go-micro.dev/v6/cmd/protoc-gen-micro@v6
+go install go-micro.dev/v6/cmd/protoc-gen-micro@latest

 # Generate Go code
 protoc --proto_path=. \
@@ -93,8 +93,6 @@ protoc --proto_path=. \
    proto/helloworld.proto
 ```

-> **Note:** Use a specific version instead of `@latest` to avoid module path conflicts. See [releases](https://github.com/micro/go-micro/releases) for the latest version.
-
 ### Server Implementation

 ```go
@@ -90,7 +90,7 @@ Update your proto generation:

 ```bash
 # Install protoc-gen-micro
-go install go-micro.dev/v6/cmd/protoc-gen-micro@v6
+go install go-micro.dev/v6/cmd/protoc-gen-micro@latest

 # Generate both gRPC and Go Micro code
 protoc --proto_path=. \
@@ -100,7 +100,6 @@ protoc --proto_path=. \
  proto/hello.proto
 ```

-> **Note:** Use a specific version instead of `@latest` to avoid module path conflicts. See [releases](https://github.com/micro/go-micro/releases) for the latest version.

 This generates:
 - `hello.pb.go` - Protocol Buffers types
@@ -32,7 +32,7 @@ go mod tidy
 Update the CLI too:

 ```bash
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

 ## 2. TLS is verified by default
@@ -0,0 +1,219 @@
+---
+layout: default
+---
+
+# Your First Agent
+
+This walkthrough builds the smallest useful Go Micro agent path: one service
+with typed endpoints, one agent scoped to that service, and one CLI conversation
+that proves the agent can use the service as a tool. It is the 0→1 version of
+the services → agents → workflows lifecycle: build capability first, add
+intelligence on top, then keep a clear path toward flows when the work needs to
+run on events or schedules.
+
+## Runnable reference first
+
+If you want to run the lifecycle before copying code, start with the maintained support-desk example from the repository root:
+
+```sh
+go run ./examples/support
+```
+
+It uses a deterministic mock model by default, so it needs no provider key, and it exercises the same shape this guide teaches: services become tools, an agent uses them, and a flow can trigger the work. Use this guide when you are ready to build the smaller 0→1 version yourself.
+
+## What you'll build
+
+A tiny task assistant:
+
+1. A `task` service exposes `Create` and `List` endpoints.
+2. An `assistant` agent is scoped to the `task` service.
+3. `micro run` starts both in the local harness.
+4. `micro chat` asks the agent to create and list tasks.
+
+The same service endpoints are normal RPC methods, dashboard/API actions, MCP
+tools, and agent tools. You do not write a second integration layer for the
+agent.
+
+## Prerequisites
+
+- Go 1.24 or newer.
+- The `micro` CLI installed.
+- An LLM provider key for live agent calls. For example:
+
+```sh
+export ANTHROPIC_API_KEY=sk-ant-...
+```
+
+Plain service calls work without a model key; the key is only needed when the
+agent reasons over tools.
+
+## 1. Create a workspace
+
+```sh
+mkdir first-agent
+cd first-agent
+go mod init example.com/first-agent
+go get go-micro.dev/v6@v6
+```
+
+Add `main.go`:
+
+```go
+package main
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"sync"
+
+	micro "go-micro.dev/v6"
+)
+
+type CreateRequest struct {
+	Title string `json:"title"`
+}
+
+type CreateResponse struct {
+	ID    string `json:"id"`
+	Title string `json:"title"`
+}
+
+type ListRequest struct{}
+
+type ListResponse struct {
+	Tasks []CreateResponse `json:"tasks"`
+}
+
+type TaskService struct {
+	mu    sync.Mutex
+	next  int
+	tasks []CreateResponse
+}
+
+// Create adds a task to the list.
+// @example {"title":"Write first agent guide"}
+func (t *TaskService) Create(ctx context.Context, req *CreateRequest, rsp *CreateResponse) error {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+
+	t.next++
+	*rsp = CreateResponse{ID: fmt.Sprintf("task-%d", t.next), Title: req.Title}
+	t.tasks = append(t.tasks, *rsp)
+	return nil
+}
+
+// List returns all known tasks.
+// @example {}
+func (t *TaskService) List(ctx context.Context, req *ListRequest, rsp *ListResponse) error {
+	t.mu.Lock()
+	defer t.mu.Unlock()
+
+	rsp.Tasks = append([]CreateResponse(nil), t.tasks...)
+	return nil
+}
+
+func main() {
+	service := micro.NewService("task")
+	service.Handle(new(TaskService))
+
+	agent := micro.NewAgent("assistant",
+		micro.AgentServices("task"),
+		micro.AgentPrompt("You help manage tasks. Use the task service before answering."),
+		micro.AgentProvider("anthropic"),
+		micro.AgentAPIKey(os.Getenv("ANTHROPIC_API_KEY")),
+	)
+
+	go agent.Run()
+	service.Run()
+}
+```
+
+> Why the comments matter: endpoint comments and `@example` tags become tool
+> descriptions, so the agent has enough context to choose `task.Create` and
+> `task.List` correctly.
+
+## 2. Run the service and agent
+
+From the same directory:
+
+```sh
+micro run
+```
+
+The local harness starts the service, gateway, dashboard, MCP tool surface, and
+agent playground. You can also verify the service directly before involving the
+agent:
+
+```sh
+micro call task TaskService.Create '{"title":"Ship the walkthrough"}'
+micro call task TaskService.List '{}'
+```
+
+## 3. Chat with the agent
+
+In another terminal, ask the agent to use the service:
+
+```sh
+micro chat assistant
+```
+
+Try:
+
+```text
+Create a task called "Review the first-agent walkthrough", then show me all tasks.
+```
+
+A healthy run shows the agent calling the task service and then summarizing the
+result. If the model refuses to call tools, tighten the prompt so it explicitly
+uses the `task` service before answering.
+
+## 4. Know what just happened
+
+- The service registered typed RPC endpoints.
+- Go Micro derived tool descriptions from the endpoint names, comments, request
+  fields, and examples.
+- The agent registered as another service with an `Agent.Chat` endpoint.
+- `micro chat` sent your message to the agent.
+- The agent selected the scoped `task` tools, called them over the same runtime,
+  and stored conversation history in memory.
+
+That is the core lifecycle: services provide capability, agents use the
+capability, and the same runtime can later put the interaction behind a flow.
+
+## 5. Make it a workflow when the path is event-driven
+
+Once the prompt should run because something happened rather than because a
+human typed a message, move the handoff into a flow:
+
+```go
+flow := micro.NewFlow("task-triage",
+	micro.FlowTrigger("tasks.created"),
+	micro.FlowPrompt("Review this new task and decide the next action: {{.Data}}"),
+	micro.FlowProvider("anthropic"),
+	micro.FlowAPIKey(os.Getenv("ANTHROPIC_API_KEY")),
+)
+```
+
+Use flows for deterministic triggers and long-running orchestration; keep the
+agent for judgment, tool use, and handoffs when the path is not known up front.
+
+## Troubleshooting
+
+| Symptom | Check |
+| --- | --- |
+| The agent says it cannot access tasks. | Confirm the agent was created with `micro.AgentServices("task")` and that `micro agent list` shows `assistant`. |
+| Tool calls use the wrong fields. | Add or improve doc comments and `@example` tags on the service methods. |
+| Plain service calls work but chat fails. | Check that your provider key is exported in the shell that runs `micro run`. |
+| You need a no-secret reference path. | Run `make harness` from the Go Micro repository; it exercises the services → agents → workflows lifecycle with a mock provider. |
+
+## Next steps
+
+- Read the [0→hero reference path](zero-to-hero.html) for the CI-verified
+  lifecycle contract.
+- Run [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support) for the no-secret 0→hero support-desk lifecycle.
+- Run [`examples/agent-plan-delegate`](https://github.com/micro/go-micro/tree/master/examples/agent-plan-delegate)
+  to see planning and delegation across agents.
+- Read [Debugging your agent](debugging-agents.html) when a chat turn does not call the tool you expected, loops, refuses a call, loses memory, or fails after a flow handoff.
+- Read [Agents and Workflows](agents-and-workflows.html) when you are ready to
+  compose agents behind durable flows.
@@ -0,0 +1,99 @@
+---
+layout: default
+---
+
+# 0→hero reference path
+
+The 0→hero path is the maintained, no-secret reference for the Go Micro
+services → agents → workflows lifecycle. It ties the CLI inner loop and the
+runtime harness together so a contributor can prove the framework still works as
+one system, not as separate demos.
+
+Use it when you want to answer: "Can I scaffold a service, run it locally, talk
+to an agent, inspect durable work, and reach the deployment boundary without
+cloud credentials?"
+
+## What the contract covers
+
+| Boundary | Contract | CI check |
+| --- | --- | --- |
+| Scaffold | `micro new` generates a runnable service with and without MCP support. | `go test ./cmd/micro/cli/new -run TestZeroToOne -count=1` |
+| Run | `micro run` remains the local development entry point. | `go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1` |
+| Chat | `micro chat` remains the interactive agent entry point. | `go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1` |
+| Inspect | `micro inspect agent`, `micro inspect flow`, and `micro flow runs` remain discoverable for run history. | `go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1` |
+| Deploy | `micro deploy --dry-run` resolves deploy targets without touching remote infrastructure. | `go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1` |
+| Runtime | Real services, agents, durable flows, store-backed history, delegation, and A2A run with only the model mocked. | `./internal/harness/zero-to-hero-ci/run.sh` and `make provider-conformance-mock` |
+
+## Run the runnable example
+
+From the repository root, start with the support-desk example when you want to see the full lifecycle in one terminal:
+
+```sh
+go run ./examples/support
+```
+
+It starts typed services, a support agent, an event-driven intake flow, and an approval gate with a deterministic mock model. Change one service method, agent prompt, or guardrail decision and run it again to learn the system by modifying a working path.
+
+## Run the whole no-secret path
+
+From the repository root:
+
+```sh
+make harness
+```
+
+That target runs the scaffold contract, the CLI boundary smoke tests, the
+0→hero runtime harnesses, the event-driven agent-flow harness, and mock provider
+conformance. It is intentionally deterministic: no provider key, cloud account,
+SSH access, or remote service is required.
+
+## Run focused checks while iterating
+
+Use the smaller checks when you are working on one seam:
+
+```sh
+# Scaffold → run/call contract.
+go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
+
+# CLI inner-loop commands: run, chat, inspect, flow runs, deploy --dry-run.
+go test ./cmd/micro -run TestZeroToHeroCLIBoundaries -count=1
+go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
+
+# Durable services → agents → workflows reference scenarios.
+./internal/harness/zero-to-hero-ci/run.sh
+
+# Event-as-prompt agent flow.
+go run ./internal/harness/agent-flow
+
+# Cross-provider semantics with the deterministic mock provider.
+make provider-conformance-mock
+```
+
+## Reference scenarios
+
+- [`examples/support`](https://github.com/micro/go-micro/tree/master/examples/support)
+  is the runnable support-desk story: customers, tickets, notify, a support
+  agent, an intake flow, and an approval gate in one no-secret example.
+- [`examples/agent-plan-delegate`](https://github.com/micro/go-micro/tree/master/examples/agent-plan-delegate)
+  is the smallest runnable planning/delegation example for multiple agents.
+- [`internal/harness/plan-delegate`](https://github.com/micro/go-micro/tree/master/internal/harness/plan-delegate)
+  is the compact 0→hero scenario: real task and notify services, a conductor
+  agent, a comms agent, plan persistence, delegation, and a workflow handoff.
+- [`internal/harness/universe`](https://github.com/micro/go-micro/tree/master/internal/harness/universe)
+  boots a larger mini-world: inventory, payment, order confirmation, a concierge
+  agent, durable checkpoint/resume, agent run history, flow run history, and A2A
+  reachability.
+- [`internal/harness/agent-flow`](https://github.com/micro/go-micro/tree/master/internal/harness/agent-flow)
+  shows the event-driven path where a `user.created` event prompts an agent to
+  call services and complete onboarding.
+
+Together these scenarios keep the North Star executable: services expose typed
+capabilities, agents use those capabilities with memory and guardrails, and
+workflows compose the work over time.
+
+## Keeping the guide honest
+
+If you change the CLI inner loop, durable flow APIs, agent run history, or the
+provider/tool semantics, update this guide and the harness in the same PR. The
+point of 0→hero is not a polished sample app that drifts from reality; it is a
+CI-verifiable contract that the documented lifecycle still works.
@@ -23,6 +23,7 @@ about the framework.
 ## Contents

 - [Getting Started](getting-started.html)
+- [Your First Agent](guides/your-first-agent.html) - Build a service-backed agent end to end
 - [MCP & AI Agents](mcp.html) - Turn services into AI-callable tools with the Model Context Protocol
 - [CLI & Gateway Guide](guides/cli-gateway.html) - Development vs Production modes
 - [Quick Start](quickstart.html)
@@ -44,6 +45,7 @@ about the framework.

 ## AI & Agents

+- [Your First Agent](guides/your-first-agent.html) - Build a service-backed agent end to end
 - [Building AI-Native Services](guides/ai-native-services.html) - End-to-end tutorial for MCP-enabled services
 - [MCP Security Guide](guides/mcp-security.html) - Auth, scopes, rate limiting, and audit logging
 - [Tool Description Best Practices](guides/tool-descriptions.html) - Writing docs that make agents effective
@@ -13,11 +13,9 @@ curl -fsSL https://go-micro.dev/install.sh | sh
 Or, if you have Go and prefer to build from source:

 ```bash
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

-> **Note:** Use `@v6` (not `@latest`) — it resolves to the newest `v6.x.x` release. Plain `@latest` can currently resolve to a stale pre-rename tag through the public module proxy and fail with a "version constraints conflict"; `@v6` avoids that. To pin an exact version use e.g. `@v6.2.0` (see [releases](https://github.com/micro/go-micro/releases)).
-
 ## Create Your First Service

 ```bash
@@ -95,7 +93,7 @@ publisher.Publish(ctx, &UserCreatedEvent{

 ## Get Help

- **[Discord Community](https://discord.gg/WeMU5AGxD)** - Chat with other users
+- **[Discord Community](https://discord.gg/G8Gk5j3uXr)** - Chat with other users
 - **[GitHub Issues](https://github.com/micro/go-micro/issues)** - Report bugs or request features
 - **[Documentation](https://go-micro.dev/docs/)** - Complete docs

@@ -58,4 +58,4 @@ The framework is the product. It's funded by **sponsorship** from the people and

 ## Feedback

-Open an issue or start a discussion on [GitHub](https://github.com/micro/go-micro), or join the [Discord](https://discord.gg/WeMU5AGxD).
+Open an issue or start a discussion on [GitHub](https://github.com/micro/go-micro), or join the [Discord](https://discord.gg/G8Gk5j3uXr).
@@ -28,11 +28,9 @@ For local development, use [`micro run`](guides/micro-run.html) instead.
 Install the CLI which includes the server command:

 ```bash
-go install go-micro.dev/v6/cmd/micro@v6
+go install go-micro.dev/v6/cmd/micro@latest
 ```

-> **Note:** Use a specific version instead of `@latest` to avoid module path conflicts. See [releases](https://github.com/micro/go-micro/releases) for the latest version.
-
 ## Run

 Start the server:
@@ -271,7 +271,7 @@
      </div>
      <p class="subtitle" style="margin-top: 2.25rem;">Want to support Go Micro and put your logo here? Or running it in production and need a hand?</p>
      <div class="hero-buttons">
-        <a href="https://discord.gg/WeMU5AGxD" class="btn btn-secondary">Become a sponsor</a>
+        <a href="https://discord.gg/G8Gk5j3uXr" class="btn btn-secondary">Become a sponsor</a>
        <a href="/support" class="btn btn-primary">Commercial support</a>
      </div>
    </section>
@@ -283,6 +283,7 @@
        <div class="hero-buttons">
          <a href="/docs/getting-started.html" class="btn btn-primary">Get Started</a>
          <a href="/docs/" class="btn btn-secondary">Read the Docs</a>
+          <a href="https://discord.gg/G8Gk5j3uXr" class="btn btn-secondary">Join Discord</a>
          <a href="/blog/" class="btn btn-secondary">Blog</a>
        </div>
      </div>
@@ -116,6 +116,24 @@ func AgentLoopLimit(n int) AgentOption { return agent.LoopLimit(n) }
 // each action the agent takes.
 func AgentApproveTool(fn ApproveFunc) AgentOption { return agent.ApproveTool(fn) }

+// AgentModelCallTimeout sets the timeout for each provider Generate call.
+func AgentModelCallTimeout(d time.Duration) AgentOption { return agent.ModelCallTimeout(d) }
+
+// AgentModelRetry sets the provider retry budget and backoff for transient failures.
+func AgentModelRetry(maxAttempts int, backoff time.Duration) AgentOption {
+	return agent.ModelRetry(maxAttempts, backoff)
+}
+
+// AgentToolCallTimeout sets the timeout for each agent tool execution.
+func AgentToolCallTimeout(d time.Duration) AgentOption { return agent.ToolCallTimeout(d) }
+
+// AgentToolRetry sets the tool retry budget and backoff for transient failures.
+// Attempts include the first call. Retries are opt-in because tools can have
+// side effects; keep handlers idempotent before enabling this.
+func AgentToolRetry(maxAttempts int, backoff time.Duration) AgentOption {
+	return agent.ToolRetry(maxAttempts, backoff)
+}
+
 // Memory is an agent's pluggable conversation memory.
 type Memory = agent.Memory

@@ -128,6 +146,12 @@ type ToolFunc = agent.ToolFunc
 // NewMemory returns the default store-backed agent memory.
 func NewMemory(s store.Store, key string, limit int) Memory { return agent.NewMemory(s, key, limit) }

+// NewRetrievalMemory returns store-backed memory with bounded active context
+// and durable retrieval over every prior turn.
+func NewRetrievalMemory(s store.Store, key string, activeLimit int) Memory {
+	return agent.NewRetrievalMemory(s, key, activeLimit)
+}
+
 // NewCompactingMemory returns store-backed memory with deterministic
 // summarization and retrieval controls.
 func NewCompactingMemory(s store.Store, key string, maxMessages, keepRecent int) Memory {
@@ -140,6 +164,10 @@ func NewInMemory(limit int) Memory { return agent.NewInMemory(limit) }
 // AgentMemory sets the agent's conversation memory (default: store-backed).
 func AgentMemory(m Memory) AgentOption { return agent.WithMemory(m) }

+// AgentRetrievalMemory enables deterministic default-memory retrieval without
+// compaction; activeLimit bounds active context while every turn is archived.
+func AgentRetrievalMemory(activeLimit int) AgentOption { return agent.RetrievalMemory(activeLimit) }
+
 // AgentCompactMemory enables deterministic default-memory compaction and
 // retrieval for long-running agents.
 func AgentCompactMemory(maxMessages, keepRecent int) AgentOption {
Author	SHA1	Message	Date
Codex	6b8b97f8a2	docs(priorities): refresh architect adoption queue Harness (E2E) / Harnesses (mock LLM) (push) Waiting to run Details Harness (E2E) / Provider harnesses (live LLM conformance) (push) Waiting to run Details Lint / golangci-lint (push) Waiting to run Details Run Tests / Unit Tests (push) Waiting to run Details Run Tests / Etcd Integration Tests (push) Waiting to run Details	2026-07-01 21:41:39 +00:00
Asim Aslam	9c66455d2a	docs: add agent debugging guide (#3596 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 22:13:48 +01:00
Asim Aslam	2215065a2e	docs(priorities): refresh architect queue (#3593 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 21:45:21 +01:00
Asim Aslam	f8b8b90a3b	docs: lead guides nav with hands-on path (#3591 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 21:21:39 +01:00
Asim Aslam	1bcf0e1ae9	docs(priorities): drop completed examples task (#3587 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 20:41:31 +01:00
Asim Aslam	b49f5072b1	loop: have DevRel maintain CHANGELOG.md and draft a changelog blog post (#3584 ) The DevRel pass now keeps the changelog living instead of letting it drift: each daily run reconciles a Keep-a-Changelog `[Unreleased]` section against the PRs that actually merged (user-facing entries only; internal loop/CI churn skipped) and rolls it into a dated version heading whenever loop-release cuts a new v6.MINOR.PATCH tag. When enough user-facing work has accumulated (roughly a week's worth, not a near-empty post every day) it also drafts a "what's new" changelog blog post narrating what shipped. Autonomy boundary preserved: CHANGELOG.md upkeep is a safe factual change and rides the auto-merged DevRel PR; the changelog blog post is opened as its own PR but left for the human to review/merge, since blog voice stays with the human. Also fix the CHANGELOG preamble: it claimed calendar versions (YYYY.MM) while tags are semver (v6.MINOR.PATCH). Correct it, add an `[Unreleased]` section seeded from real recent work, and note the historical 2026.0x headings. Claude-Session: https://claude.ai/code/session_01CmdEY7pYmV5zzwCjNJ4ykL Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 20:29:53 +01:00
Asim Aslam	63ebe6ab9c	docs: surface runnable lifecycle examples (#3585 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 20:25:33 +01:00
Asim Aslam	f192c4947c	docs(priorities): drop completed install task (#3581 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 19:46:45 +01:00
Asim Aslam	7fd749b475	docs: lead v6 installs with latest (#3579 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 19:24:10 +01:00
Asim Aslam	dfe9e436e8	docs(priorities): remove completed first-agent task (#3576 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 18:42:38 +01:00
Asim Aslam	72902ee6fb	docs: add your first agent walkthrough (#3574 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 18:27:36 +01:00
Asim Aslam	819403e940	docs(priorities): prioritize adoption on-ramp (#3571 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 17:58:27 +01:00
Asim Aslam	58284c6230	harness: extend live provider deadlines (#3569 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 17:33:29 +01:00
Asim Aslam	66ce68a93f	community: add Discord to nav/footer/README/landing; fix stale invite code (#3567 ) There was no working, prominent Discord link. Update the stale invite code (WeMU5AGxD → G8Gk5j3uXr) everywhere it appeared (README, docs, blog, landing, SECURITY, issue templates, contrib), and add the link prominently: the site nav and footer includes (so it shows on every landing/docs/blog page), a Discord badge + a Community line in the README, and a "Join Discord" button on the landing. Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 17:01:29 +01:00
Asim Aslam	4bd181fc21	loop: point the architect at adoption + add a daily release action (#3566 ) The framework's depth is strong but the on-ramp is the adoption gap, and the architect queue had filled entirely with internal hardening. Steer the architect to weight the developer on-ramp/DX (first-agent tutorial, discoverable examples, docs wayfinding, install friction, debugging) at least as highly as internal work — a developer succeeding on their first agent matters more than another conformance/observability increment. Adoption issues filed: #3561-#3565. Also add loop-release.yml: a daily patch release that tags v6.MINOR.PATCH+1 when master has new commits (pushed with the PAT so goreleaser fires), so the installable framework tracks the loop's daily improvements instead of lapsing. Minor/major bumps stay with the human. Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 16:38:28 +01:00
Asim Aslam	3143767d78	docs(priorities): refresh architect queue (#3557 ) goreleaser / goreleaser (push) Waiting to run Details Co-authored-by: Codex <codex@openai.com>	2026-07-01 16:05:37 +01:00
Asim Aslam	666fc4b794	ci+docs: name the loop workflows by role (planner/generator/evaluator) (#3556 ) Rename the autonomous-loop workflows so the Actions list maps to the long-running-agent harness pattern (planner → generator → evaluator): architecture-review.yml -> loop-architect.yml "Loop: Architect (Planner)" continuous-improvement.yml -> loop-builder.yml "Loop: Builder (Generator)" devrel-review.yml -> loop-devrel.yml "Loop: DevRel" harness-triage.yml -> loop-triage.yml "Loop: Triage (Evaluator feedback)" harness.yml stays the shared Evaluator/CI gate (triage still matches it by the "Harness (E2E)" name). Document the pipeline + role mapping in CONTINUOUS_IMPROVEMENT.md, and point to it from CONTRIBUTING so the development process is discoverable. No behavior change — schedules, gates, and required checks are unaffected. Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 15:59:46 +01:00
Asim Aslam	7af73b06d7	ci: auto-triage harness failures into fix issues (hill-climbing loop) (#3549 ) Close the loop's feedback path: when the live provider-conformance harness fails, harness-triage.yml dispatches Codex to triage the failing run — read logs, root-cause, dedupe against open issues, and file scoped codex/enhancement issues that the hourly increment loop then fixes and the next harness run verifies. Transient flakes are ignored; breaking/architectural fixes are escalated as needs-human rather than auto-built. No human in the middle short of a genuine judgment call. Documented in CONTINUOUS_IMPROVEMENT.md. Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 15:51:55 +01:00
Asim Aslam	0811234f3e	agent: execute text tool call fallbacks (#3554 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 15:27:14 +01:00
Asim Aslam	b64a7d248d	docs(priorities): refresh architect queue (#3551 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 14:55:43 +01:00
Asim Aslam	e7b08d914f	docs(priorities): refresh architect queue (#3545 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 14:03:04 +01:00
Asim Aslam	3a9455f28c	harness: label provider conformance phases (#3542 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 12:46:11 +01:00
Asim Aslam	05e53ec38c	ci: run the live provider-conformance harness hourly, not daily (#3540 ) Match the real-model conformance cadence to the dev/loop velocity so live regressions and provider drift surface within the hour instead of up to 24h. The mock harness already runs on every push/PR; this only changes the live (credentialed) schedule. Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 12:35:36 +01:00
Asim Aslam	dbdd0e1d6f	atlascloud: run provider conformance on a stronger (env-selectable) model (#3538 ) * atlascloud: env-selectable chat model; run conformance on a stronger model The daily provider-conformance harness fails 4/5 harnesses on Atlas Cloud — its default chat model answers agent/tool-use conformance prompts conversationally instead of performing the task. Atlas is currently the only provider with a key configured, so the whole live run is red. Make the Atlas Cloud provider honor an ATLASCLOUD_MODEL env override (falling back to the existing default), and set it in the harness workflow to a stronger tool-use model (Qwen3, overridable via an Actions variable). No change to the default for normal use. * atlascloud: use minimaxai/minimax-m3 for conformance model --------- Co-authored-by: Claude <noreply@anthropic.com>	2026-07-01 12:17:12 +01:00
Asim Aslam	8146e29f7e	docs(priorities): refresh architect queue (#3539 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 12:10:17 +01:00
Asim Aslam	c110774dc7	Add opt-in retries for agent tool calls (#3535 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 10:57:33 +01:00
Asim Aslam	c0a5775fb5	docs(priorities): refresh architect queue (#3533 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 10:12:45 +01:00
Asim Aslam	f844a23bb2	docs: align public AI harness facts (#3531 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 09:40:28 +01:00
Asim Aslam	04e8759d41	test agent checkpoint resume after restart (#3529 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 09:06:46 +01:00
Asim Aslam	78725135aa	docs(priorities): refresh architect queue (#3527 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 08:33:01 +01:00
Asim Aslam	2ff64ff0b2	Document canonical 0-to-hero reference path (#3522 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 07:12:17 +01:00
Asim Aslam	7a8e7cd9ae	docs(priorities): advance queue to 0-to-hero reference (#3520 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 06:37:15 +01:00
Asim Aslam	b58eed1698	Add retrieval-backed agent memory (#3518 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 04:59:16 +01:00
Asim Aslam	c92c9cc244	docs(priorities): refresh architect queue (#3516 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 04:06:59 +01:00
Asim Aslam	a2bf43e9ef	test: broaden stream provider conformance (#3512 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 03:37:26 +01:00
Asim Aslam	49bac7e4a8	trace scheduled flow dispatch metadata (#3510 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 02:42:31 +01:00
Asim Aslam	5aac7e3ca0	docs(priorities): refresh architect queue after scheduling (#3507 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 01:51:21 +01:00
Asim Aslam	d86585bf5c	Add scheduled flow agent harness (#3505 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 01:02:29 +01:00
Asim Aslam	88e2b58711	docs(priorities): refresh architect queue (#3503 ) Co-authored-by: Codex <codex@openai.com>	2026-07-01 00:38:51 +01:00