diff --git a/Makefile b/Makefile index 4def1d40..88d3bb14 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ PYTHON ?= python3 LOCAL_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills.disabled/yao-meta-skill ACTIVE_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills/yao-meta-skill -.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-kit-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean +.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-kit-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adaptation-safety-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean eval: $(PYTHON) scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt @@ -127,6 +127,9 @@ benchmark-reproducibility-check: feedback-check: $(PYTHON) tests/verify_feedback.py +adaptation-safety-check: + $(PYTHON) tests/verify_adaptation_safety.py + adoption-drift-check: $(PYTHON) tests/verify_adoption_drift.py @@ -238,7 +241,7 @@ sync-local-install: package-check sync-active-install: package-check $(PYTHON) scripts/sync_local_install.py --install-dir "$(ACTIVE_SKILL_INSTALL_DIR)" -test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check +test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adaptation-safety-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check ci-test: $(PYTHON) scripts/ci_test.py diff --git a/README.md b/README.md index c7276e6f..bf1adf19 100644 --- a/README.md +++ b/README.md @@ -42,6 +42,7 @@ It turns rough workflows, transcripts, prompts, notes, and runbooks into reusabl - three high-value next iteration directions after the first package is created - a lightweight feedback log that does not require a full promotion cycle - a local-first metadata-only adoption and drift report that turns real usage signals into next iteration candidates, with optional `yao.py` CLI run capture, external client event emit hooks, hook recipes, and JSONL import that record command names and outcomes without arguments or raw content +- an explicit-source adaptive proposal loop that summarizes redacted repeated user preferences and generates approval-gated adaptation proposals without scanning private logs or writing source files - a Browser/Chrome Native Messaging telemetry host that can receive length-prefixed metadata-only client events and generate a local launcher plus manifest without storing raw content - a Skill Atlas drift layer that reads aggregate adoption reports and surfaces portfolio-level drift signals without packaging raw telemetry logs - a baseline compare report for with-skill vs baseline review @@ -118,6 +119,8 @@ python3 scripts/yao.py artifact-design-profile my-skill python3 scripts/yao.py prompt-quality-profile my-skill python3 scripts/yao.py system-model my-skill python3 scripts/yao.py feedback my-skill --note "Tighten exclusions before adding scripts." --rating 4 --category boundary +python3 scripts/yao.py adapt-scan my-skill --source ./curated-user-signals.jsonl +python3 scripts/yao.py adapt-propose my-skill python3 scripts/yao.py adoption-drift my-skill --record-event skill_activation --activation-type explicit --outcome accepted YAO_CLI_TELEMETRY=1 python3 scripts/yao.py validate my-skill python3 scripts/yao.py telemetry-emit my-skill --event skill_activation --activation-type explicit --outcome accepted --command browser-extension diff --git a/evals/adaptation/user_signals.example.jsonl b/evals/adaptation/user_signals.example.jsonl new file mode 100644 index 00000000..ed06eda9 --- /dev/null +++ b/evals/adaptation/user_signals.example.jsonl @@ -0,0 +1,8 @@ +{"text":"新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"} +{"text":"HTML 报告需要双语能力，但默认内容应该保持中文简体。"} +{"text":"报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。"} +{"text":"Skill 概览报告需要更多图表模块，避免右侧文本挤在一起。"} +{"text":"自适应升级必须先生成提案，不能直接自动修改源文件。"} +{"text":"用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"} +{"text":"每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。"} +{"text":"涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。"} diff --git a/references/autonomous-adaptation.md b/references/autonomous-adaptation.md new file mode 100644 index 00000000..5eaf0ed7 --- /dev/null +++ b/references/autonomous-adaptation.md @@ -0,0 +1,42 @@ +# Autonomous Adaptation Method + +This reference defines the safe foundation for adaptive self-iteration. + +## Scope + +Adaptive iteration is a proposal-only loop until a human explicitly approves a patch application workflow. The current implementation may: + +- read one user-provided local source file; +- redact sensitive text before storing evidence excerpts; +- summarize repeated preferences and operational signals; +- produce adaptation proposals with target files, risks, tests, and rollback plans. + +It must not: + +- scan shell history, browser history, chat logs, mail, or private folders by default; +- infer permanent user memory from a single comment; +- write source files as part of scan or proposal generation; +- count proposals as completed implementation evidence. + +## Flow + +1. `adapt-scan` reads an explicit source path and writes `reports/user_patterns.json` plus `reports/user_patterns.md`. +2. `adapt-propose` reads the pattern report and writes `reports/adaptation_proposals.json` plus `reports/adaptation_proposals.md`. +3. A reviewer decides whether any proposal is worth implementing. +4. Future `adapt-apply` work must require approval evidence, allowlisted targets, regression commands, and rollback metadata before writing files. + +## Evidence Standard + +Each proposal should include: + +- the repeated pattern that triggered it; +- redacted excerpts, never unredacted raw content; +- target files and change intent; +- risk level and boundary; +- verification commands; +- rollback plan; +- a clear `proposal-only` status. + +## Review Boundary + +The adaptive loop improves iteration quality, but it does not replace normal review. Any proposal touching trigger behavior, reports, packaging, telemetry, privacy, or governance must still pass the same tests and release gates as a manually designed change. diff --git a/references/user-memory-policy.md b/references/user-memory-policy.md new file mode 100644 index 00000000..fd363856 --- /dev/null +++ b/references/user-memory-policy.md @@ -0,0 +1,35 @@ +# User Memory Policy + +This skill treats user preference memory as local, explicit, and reviewable. + +## Principles + +- **Explicit source only**: adaptive scans require a user-provided file path. +- **Local first**: no network access is needed for preference extraction. +- **No implicit private logs**: shell history, browser history, mail, and hidden chat logs are blocked by default. +- **Repeated signals only**: one-off statements are recorded as discarded signals unless they meet the configured support threshold. +- **Redacted evidence**: stored excerpts must remove secrets, tokens, email addresses, and local absolute paths. +- **Proposal before patch**: preference memory can generate proposals, not automatic source edits. + +## Allowed Inputs + +Recommended inputs are curated JSONL, Markdown, or text files prepared for review. JSONL records should use a field such as `text`, `message`, `content`, `excerpt`, `prompt`, `note`, or `body`. + +## Blocked By Default + +The scanner refuses common shell history files such as `.zsh_history`, `.bash_history`, and `.fish_history` unless an explicit override is added for a controlled test. Even with an override, the output remains redacted and proposal-only. + +## Retention + +Generated reports store only summarized patterns and short redacted excerpts. They should not be treated as a full transcript, chat archive, or durable personal memory store. + +## Upgrade Path + +A future patch-application stage must add: + +- human approval ledger; +- allowlisted target files; +- dry-run diffs; +- regression command execution; +- rollback artifacts; +- reviewer-visible audit trail. diff --git a/registry/index.json b/registry/index.json index a85b521e..65255181 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index aa01ae3c..d371f99f 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,7 +16,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json new file mode 100644 index 00000000..c1ea0ec9 --- /dev/null +++ b/reports/adaptation_proposals.json @@ -0,0 +1,208 @@ +{ + "schema_version": "1.0", + "ok": true, + "generated_at": "2026-06-15T00:00:00Z", + "skill_dir": ".", + "source_patterns": "reports/user_patterns.json", + "summary": { + "pattern_count": 5, + "proposal_count": 5, + "apply_supported": false, + "failure_count": 0 + }, + "proposal_contract": { + "proposal_only": true, + "approval_required": true, + "writes_repository_files": false, + "allowlisted_targets_required": true, + "rollback_required_for_apply": true, + "apply_command_available": false + }, + "proposals": [ + { + "proposal_id": "adapt-18c7517f3d", + "pattern_id": "language_default", + "title": "Keep reports Chinese-first with optional English", + "change_type": "report-default-language", + "status": "proposal-only", + "requires_approval": true, + "write_allowed_without_approval": false, + "risk_level": "low", + "reason": "2 redacted records matched repeated report-language signals.", + "support_count": 2, + "target_files": [ + "scripts/render_skill_overview.py", + "references/artifact-design-doctrine.md" + ], + "suggested_changes": [ + "Keep user-facing report copy Simplified Chinese by default.", + "Expose English through the existing language switch instead of mixing languages in the default view." + ], + "verification_commands": [ + "python3 tests/verify_skill_overview.py" + ], + "rollback_plan": "Revert report language template changes and rerun the overview verifier.", + "evidence_refs": [ + { + "record_id": "line-1", + "excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。" + }, + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + } + ] + }, + { + "proposal_id": "adapt-fbfe921ba5", + "pattern_id": "report_ui", + "title": "Improve report layout, visual hierarchy, and chart readability", + "change_type": "artifact-ui-polish", + "status": "proposal-only", + "requires_approval": true, + "write_allowed_without_approval": false, + "risk_level": "medium", + "reason": "5 redacted records matched repeated artifact-design signals.", + "support_count": 5, + "target_files": [ + "scripts/render_skill_overview.py", + "references/artifact-design-doctrine.md", + "tests/verify_skill_overview.py" + ], + "suggested_changes": [ + "Prefer vertical narrative sections with limited two-column layouts only when content has enough width.", + "Keep charts inline SVG, with captions and stable responsive constraints." + ], + "verification_commands": [ + "python3 tests/verify_skill_overview.py", + "python3 tests/verify_skill_report_charts.py" + ], + "rollback_plan": "Restore the previous report renderer and regenerate the demo report.", + "evidence_refs": [ + { + "record_id": "line-1", + "excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。" + }, + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + }, + { + "record_id": "line-3", + "excerpt": "报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。" + } + ] + }, + { + "proposal_id": "adapt-59d219a1fb", + "pattern_id": "approval_safety", + "title": "Keep adaptive iteration approval-gated", + "change_type": "privacy-governance", + "status": "proposal-only", + "requires_approval": true, + "write_allowed_without_approval": false, + "risk_level": "low", + "reason": "2 redacted records matched repeated governance signals.", + "support_count": 2, + "target_files": [ + "references/user-memory-policy.md", + "references/autonomous-adaptation.md", + "schemas/adaptation-proposal.schema.json" + ], + "suggested_changes": [ + "Require explicit source paths for memory scans.", + "Generate proposals before any source patching.", + "Reserve automatic apply for a future approval ledger and rollback implementation." + ], + "verification_commands": [ + "python3 tests/verify_adaptation_safety.py" + ], + "rollback_plan": "Remove the adaptive proposal artifacts and keep feedback/adoption drift as the only iteration inputs.", + "evidence_refs": [ + { + "record_id": "line-5", + "excerpt": "自适应升级必须先生成提案，不能直接自动修改源文件。" + }, + { + "record_id": "line-6", + "excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。" + } + ] + }, + { + "proposal_id": "adapt-457baca160", + "pattern_id": "delivery_format", + "title": "Make generated artifact paths explicit in CLI output", + "change_type": "artifact-discoverability", + "status": "proposal-only", + "requires_approval": true, + "write_allowed_without_approval": false, + "risk_level": "low", + "reason": "2 redacted records matched repeated artifact-format signals.", + "support_count": 2, + "target_files": [ + "scripts/yao.py", + "README.md" + ], + "suggested_changes": [ + "Include stable report paths in command output.", + "Document which artifacts are meant for human review." + ], + "verification_commands": [ + "python3 tests/verify_yao_cli.py" + ], + "rollback_plan": "Revert CLI copy/documentation changes and keep artifact paths unchanged.", + "evidence_refs": [ + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + }, + { + "record_id": "line-6", + "excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。" + } + ] + }, + { + "proposal_id": "adapt-abfee25d3a", + "pattern_id": "evidence_testing", + "title": "Attach tests and evidence refresh to each upgrade", + "change_type": "quality-gate", + "status": "proposal-only", + "requires_approval": true, + "write_allowed_without_approval": false, + "risk_level": "medium", + "reason": "2 redacted records matched repeated quality-gate signals.", + "support_count": 2, + "target_files": [ + "tests/verify_adaptation_safety.py", + "scripts/render_skill_os2_coverage.py", + "reports/skill_os2_coverage.json" + ], + "suggested_changes": [ + "Add focused verifier coverage for every new adaptive behavior.", + "Refresh Skill OS 2.0 coverage so planned, partial, and covered states remain visible." + ], + "verification_commands": [ + "python3 tests/verify_adaptation_safety.py", + "python3 tests/verify_skill_os2_coverage.py" + ], + "rollback_plan": "Revert the new verifier and coverage status updates, then regenerate coverage reports.", + "evidence_refs": [ + { + "record_id": "line-7", + "excerpt": "每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。" + }, + { + "record_id": "line-8", + "excerpt": "涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。" + } + ] + } + ], + "failures": [], + "artifacts": { + "json": "reports/adaptation_proposals.json", + "markdown": "reports/adaptation_proposals.md" + } +} diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md new file mode 100644 index 00000000..95aa6b0c --- /dev/null +++ b/reports/adaptation_proposals.md @@ -0,0 +1,119 @@ +# Adaptation Proposals + +- Generated at: `2026-06-15T00:00:00Z` +- Pattern report: `reports/user_patterns.json` +- Proposal only: `true` +- Writes repository files: `false` +- Proposals: `5` + +## Keep reports Chinese-first with optional English + +- ID: `adapt-18c7517f3d` +- Status: `proposal-only` +- Pattern: `language_default` +- Risk: `low` +- Requires approval: `true` +- Reason: 2 redacted records matched repeated report-language signals. +- Target files: + - `scripts/render_skill_overview.py` + - `references/artifact-design-doctrine.md` +- Suggested changes: + - Keep user-facing report copy Simplified Chinese by default. + - Expose English through the existing language switch instead of mixing languages in the default view. +- Verification: + - `python3 tests/verify_skill_overview.py` +- Rollback: Revert report language template changes and rerun the overview verifier. +- Redacted evidence refs: + - `line-1`: 新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。 + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + +## Improve report layout, visual hierarchy, and chart readability + +- ID: `adapt-fbfe921ba5` +- Status: `proposal-only` +- Pattern: `report_ui` +- Risk: `medium` +- Requires approval: `true` +- Reason: 5 redacted records matched repeated artifact-design signals. +- Target files: + - `scripts/render_skill_overview.py` + - `references/artifact-design-doctrine.md` + - `tests/verify_skill_overview.py` +- Suggested changes: + - Prefer vertical narrative sections with limited two-column layouts only when content has enough width. + - Keep charts inline SVG, with captions and stable responsive constraints. +- Verification: + - `python3 tests/verify_skill_overview.py` + - `python3 tests/verify_skill_report_charts.py` +- Rollback: Restore the previous report renderer and regenerate the demo report. +- Redacted evidence refs: + - `line-1`: 新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。 + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + - `line-3`: 报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。 + +## Keep adaptive iteration approval-gated + +- ID: `adapt-59d219a1fb` +- Status: `proposal-only` +- Pattern: `approval_safety` +- Risk: `low` +- Requires approval: `true` +- Reason: 2 redacted records matched repeated governance signals. +- Target files: + - `references/user-memory-policy.md` + - `references/autonomous-adaptation.md` + - `schemas/adaptation-proposal.schema.json` +- Suggested changes: + - Require explicit source paths for memory scans. + - Generate proposals before any source patching. + - Reserve automatic apply for a future approval ledger and rollback implementation. +- Verification: + - `python3 tests/verify_adaptation_safety.py` +- Rollback: Remove the adaptive proposal artifacts and keep feedback/adoption drift as the only iteration inputs. +- Redacted evidence refs: + - `line-5`: 自适应升级必须先生成提案，不能直接自动修改源文件。 + - `line-6`: 用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。 + +## Make generated artifact paths explicit in CLI output + +- ID: `adapt-457baca160` +- Status: `proposal-only` +- Pattern: `delivery_format` +- Risk: `low` +- Requires approval: `true` +- Reason: 2 redacted records matched repeated artifact-format signals. +- Target files: + - `scripts/yao.py` + - `README.md` +- Suggested changes: + - Include stable report paths in command output. + - Document which artifacts are meant for human review. +- Verification: + - `python3 tests/verify_yao_cli.py` +- Rollback: Revert CLI copy/documentation changes and keep artifact paths unchanged. +- Redacted evidence refs: + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + - `line-6`: 用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。 + +## Attach tests and evidence refresh to each upgrade + +- ID: `adapt-abfee25d3a` +- Status: `proposal-only` +- Pattern: `evidence_testing` +- Risk: `medium` +- Requires approval: `true` +- Reason: 2 redacted records matched repeated quality-gate signals. +- Target files: + - `tests/verify_adaptation_safety.py` + - `scripts/render_skill_os2_coverage.py` + - `reports/skill_os2_coverage.json` +- Suggested changes: + - Add focused verifier coverage for every new adaptive behavior. + - Refresh Skill OS 2.0 coverage so planned, partial, and covered states remain visible. +- Verification: + - `python3 tests/verify_adaptation_safety.py` + - `python3 tests/verify_skill_os2_coverage.py` +- Rollback: Revert the new verifier and coverage status updates, then regenerate coverage reports. +- Redacted evidence refs: + - `line-7`: 每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。 + - `line-8`: 涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。 diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index d1ecb926..e3e48ec6 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T11:08:09Z", + "generated_at": "2026-06-15T13:08:50Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 91b31983..206372c9 100644 --- a/reports/adoption_drift_report.md +++ b/reports/adoption_drift_report.md @@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Summary - Events: `1` -- Adoption samples: `0` -- Activation events: `0` -- Adoption rate: `0` +- Adoption samples: `1` +- Activation events: `1` +- Adoption rate: `100.0` - Missed trigger signals: `0` - Bad output signals: `0` - Script error signals: `0` @@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | -| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | +| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` +- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 48db2f50..f2754316 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,18 +1,18 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { - "python_file_count": 162, - "script_file_count": 102, - "test_file_count": 60, - "internal_module_count": 28, - "cli_script_count": 76, + "python_file_count": 166, + "script_file_count": 105, + "test_file_count": 61, + "internal_module_count": 29, + "cli_script_count": 78, "command_handler_count": 34, "warn_line_threshold": 900, "block_line_threshold": 1500, - "largest_file_lines": 891, + "largest_file_lines": 894, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -20,14 +20,14 @@ "largest_files": [ { "path": "tests/verify_yao_cli.py", - "lines": 891, + "lines": 894, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, { "path": "scripts/yao.py", - "lines": 881, + "lines": 882, "kind": "cli-script", "severity": "pass", "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator." @@ -46,20 +46,20 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, - { - "path": "tests/verify_review_studio.py", - "lines": 745, - "kind": "test", - "severity": "pass", - "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." - }, { "path": "scripts/yao_cli_parser.py", - "lines": 741, + "lines": 765, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "tests/verify_review_studio.py", + "lines": 749, + "kind": "test", + "severity": "pass", + "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." + }, { "path": "scripts/compile_skill.py", "lines": 734, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index e9036ba2..4ee0b8c0 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,17 +1,17 @@ # Architecture Maintainability -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary - decision: `pass` -- python files: `162` -- scripts: `102` -- tests: `60` -- internal modules: `28` -- CLI scripts: `76` +- python files: `166` +- scripts: `105` +- tests: `61` +- internal modules: `29` +- CLI scripts: `78` - Yao CLI command handlers: `34` -- largest file lines: `891` +- largest file lines: `894` - hotspots: `0` - blockers: `0` @@ -25,12 +25,12 @@ No file-size hotspots found. | File | Lines | Kind | Severity | | --- | ---: | --- | --- | -| `tests/verify_yao_cli.py` | `891` | `test` | `pass` | -| `scripts/yao.py` | `881` | `cli-script` | `pass` | +| `tests/verify_yao_cli.py` | `894` | `test` | `pass` | +| `scripts/yao.py` | `882` | `cli-script` | `pass` | | `scripts/skill_report_layout.py` | `805` | `internal-module` | `pass` | | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` | -| `tests/verify_review_studio.py` | `745` | `test` | `pass` | -| `scripts/yao_cli_parser.py` | `741` | `internal-module` | `pass` | +| `scripts/yao_cli_parser.py` | `765` | `internal-module` | `pass` | +| `tests/verify_review_studio.py` | `749` | `test` | `pass` | | `scripts/compile_skill.py` | `734` | `cli-script` | `pass` | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` | | `scripts/optimize_description.py` | `723` | `cli-script` | `pass` | diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index e574a581..51f0fabf 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,22 +3,35 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 56, + "sample": [ + " M Makefile", + " M README.md", + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget.md" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb", - "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "evidence_bundle_sha256": "4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c", + "source_contract_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -37,14 +50,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -53,10 +67,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "ready": false, + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -64,7 +78,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb" + "sha256": "4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "e05906fb7e4242e1b4c373285f5bca3283986301f13e08c2d64715efb9f827a4" + "bytes": 7967, + "sha256": "04a5c10af1d342dc15fe42a2b594b71388e3708de3d492f1ea7b91ded2e1fffd" }, { "label": "blind_review", @@ -172,22 +186,22 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 101852, - "sha256": "3cd8c1c2d119e2db480411a9839281e0a9e1b03eb4d9d535c9b0138ef72ba6e4" + "bytes": 104587, + "sha256": "76e40930c175b307145e0632218356ee7e6ca38545d578e527dbf7decda83113" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 21493, - "sha256": "5be76147f3cb9952f8c5f524c8195eb94ea44e5172ab4b34b1b9208f6d8c198a" + "bytes": 21994, + "sha256": "afc31ecb61e58d2f7396a0a069d90aecf9b6312ec0e56f0f1624add940e129d2" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9b8e6521f9455e654850975e3625132fb998ba4e03f7ceebaf4eded9ccd32bb5" + "sha256": "5af907a3c8559dccaf34665815e5d5e6e9189a873bcf4531fe3d6fdbb27c7e1b" }, { "label": "package_verification", @@ -201,14 +215,14 @@ "path": "reports/install_simulation.json", "exists": true, "bytes": 8758, - "sha256": "ee7554d8362d05f2bf6e7389e0524cd6336d42312ab7a05b9c0c6ddacdb0e339" + "sha256": "9c2e297394f92a6b9a8826165ccb32e7eb970ce90b7312f5e125a7f95fe6724f" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "8a7f73832d4da2f63856d7f5be02488db6eac72a3a6149aa26a39c7a15a27053" + "sha256": "47c5859d2a9c22c1a7c49381e363648e7ff09330ba62b2f2b27b0ab8aa4f4071" }, { "label": "world_class_evidence_plan", @@ -263,8 +277,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 8463, - "sha256": "6e718da475b2732695dedf02bbdc15689a7fc23f1ee89d316199f2ab15140102" + "bytes": 8634, + "sha256": "a2e6953e92e667cc0913c08e48b6954ea48420ad3a4056ed15eb19a183825e67" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 0f06141a..a2a4dcb8 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,18 +1,18 @@ # Benchmark Reproducibility Generated at: `2026-06-15` -Commit: `ee2130176fdf69358b9e02cf319329c6aadd841a` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb` +Commit: `180dbf4a41ad242a3e666ff2c542c92b590bdce0` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `fe193ec81d0e` +- source contract sha256: `024e577f4b07` - archive sha256: `6852cf91a74d` - output cases: `5` - disclosed failure cases: `3` @@ -22,8 +22,8 @@ Evidence bundle SHA256: `2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d6061998 - world-class ready: `false` - world-class source checks: `6` pass / `13` total; `7` blocked - public claim ready: `false` -- public claim blockers: `4` -- changed files at generation: `0` +- public claim blockers: `5` +- changed files at generation: `56` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below. @@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | Blocker | | --- | +| release lock is not clean or commit is unavailable | | provider-backed model holdout evidence is incomplete | | human blind-review adjudication is incomplete | | world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) | @@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi ## Release Lock -- ready: `true` -- reason: clean generation-time HEAD +- ready: `false` +- reason: working tree was dirty at generation time - status scope: generation-time status before this report is written ## Evidence Bundle - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb` +- sha256: `4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c` ## Methodology Sections @@ -72,17 +73,17 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `e05906fb7e42` | +| output_execution | `reports/output_execution_runs.json` | present | `04a5c10af1d3` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` | -| trust_report | `reports/security_trust_report.json` | present | `3cd8c1c2d119` | -| python_compatibility | `reports/python_compatibility.json` | present | `5be76147f3cb` | -| registry_audit | `reports/registry_audit.json` | present | `9b8e6521f945` | +| trust_report | `reports/security_trust_report.json` | present | `76e40930c175` | +| python_compatibility | `reports/python_compatibility.json` | present | `afc31ecb61e5` | +| registry_audit | `reports/registry_audit.json` | present | `5af907a3c855` | | package_verification | `reports/package_verification.json` | present | `2476ae8ec9c4` | -| install_simulation | `reports/install_simulation.json` | present | `ee7554d8362d` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `8a7f73832d4d` | +| install_simulation | `reports/install_simulation.json` | present | `9c2e297394f9` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `47c5859d2a9c` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `933cdb002181` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `5407409841eb` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `b10e1ce0a5a1` | @@ -90,7 +91,7 @@ This report proves local benchmark reproducibility only. It keeps external provi | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `d377b8d99831` | | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `9f141f09bf48` | | world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `6e718da475b2` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `a2e6953e92e6` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 8eaaac92..a23e9888 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, @@ -114,6 +114,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -143,7 +144,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -172,6 +174,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -224,8 +227,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -277,7 +279,7 @@ "reports/governance_score.json" ], "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -286,6 +288,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", @@ -322,7 +325,7 @@ ], "baseline": "without_skill", "counts": { - "trigger": 26, + "trigger": 27, "output": 3, "adversarial": 1, "baseline": 1 @@ -384,7 +387,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -404,6 +407,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -445,6 +449,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -488,14 +493,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -517,7 +522,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -537,7 +542,7 @@ "resources": { "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -630,7 +635,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -650,6 +655,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -691,6 +697,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -734,14 +741,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -761,7 +768,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -781,7 +788,7 @@ "resources": { "strategy": "Ship the neutral source tree and expose OpenAI-facing interface metadata as a generated companion file.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -964,6 +971,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -993,7 +1001,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -1022,6 +1031,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -1074,8 +1084,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -1127,7 +1136,7 @@ "reports/governance_score.json" ], "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -1136,6 +1145,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", @@ -1172,7 +1182,7 @@ ], "baseline": "without_skill", "counts": { - "trigger": 26, + "trigger": 27, "output": 3, "adversarial": 1, "baseline": 1 @@ -1234,7 +1244,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1254,6 +1264,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -1295,6 +1306,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -1338,14 +1350,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1367,7 +1379,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -1387,7 +1399,7 @@ "resources": { "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -1480,7 +1492,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1500,6 +1512,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -1541,6 +1554,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -1584,14 +1598,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1611,7 +1625,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -1631,7 +1645,7 @@ "resources": { "strategy": "Preserve the source tree directly; write target notes in targets/claude/README.md.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -1814,6 +1828,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -1843,7 +1858,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -1872,6 +1888,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -1924,8 +1941,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -1977,7 +1993,7 @@ "reports/governance_score.json" ], "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -1986,6 +2002,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", @@ -2022,7 +2039,7 @@ ], "baseline": "without_skill", "counts": { - "trigger": 26, + "trigger": 27, "output": 3, "adversarial": 1, "baseline": 1 @@ -2084,7 +2101,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2104,6 +2121,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -2145,6 +2163,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -2188,14 +2207,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2217,7 +2236,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -2237,7 +2256,7 @@ "resources": { "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -2323,7 +2342,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2343,6 +2362,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -2384,6 +2404,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -2427,14 +2448,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2454,7 +2475,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -2474,7 +2495,7 @@ "resources": { "strategy": "Preserve references, scripts, assets, evals, reports, and adapter metadata as relative package resources.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -2648,6 +2669,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -2677,7 +2699,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -2706,6 +2729,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -2758,8 +2782,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -2811,7 +2834,7 @@ "reports/governance_score.json" ], "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -2820,6 +2843,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", @@ -2856,7 +2880,7 @@ ], "baseline": "without_skill", "counts": { - "trigger": 26, + "trigger": 27, "output": 3, "adversarial": 1, "baseline": 1 @@ -2918,7 +2942,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2938,6 +2962,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -2979,6 +3004,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -3022,14 +3048,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3051,7 +3077,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -3071,7 +3097,7 @@ "resources": { "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -3157,7 +3183,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3177,6 +3203,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -3218,6 +3245,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -3261,14 +3289,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3288,7 +3316,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -3308,7 +3336,7 @@ "resources": { "strategy": "Keep optional directories as relative resources next to SKILL.md.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -3482,6 +3510,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -3511,7 +3540,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -3540,6 +3570,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -3592,8 +3623,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -3645,7 +3675,7 @@ "reports/governance_score.json" ], "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -3654,6 +3684,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", @@ -3690,7 +3721,7 @@ ], "baseline": "without_skill", "counts": { - "trigger": 26, + "trigger": 27, "output": 3, "adversarial": 1, "baseline": 1 @@ -3752,7 +3783,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3772,6 +3803,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -3813,6 +3845,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -3856,14 +3889,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3885,7 +3918,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -3905,7 +3938,7 @@ "resources": { "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 @@ -3995,7 +4028,7 @@ }, "file_write": { "required": true, - "script_count": 64, + "script_count": 66, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -4015,6 +4048,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -4056,6 +4090,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -4099,14 +4134,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 77, + "checked_count": 79, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 64, + "file_write_script_count": 66, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4126,7 +4161,7 @@ ], "capability_counts": { "network": 3, - "file_write": 64, + "file_write": 66, "subprocess": 9, "interactive": 0 }, @@ -4146,7 +4181,7 @@ "resources": { "strategy": "Install as project or user scoped skill source, preserving relative references and scripts.", "counts": { - "references": 32, + "references": 34, "scripts": 80, "assets": 2, "reports": 43 diff --git a/reports/context_budget.json b/reports/context_budget.json index 330fd176..7f1a0f3b 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,21 +6,21 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1265845, + "other_text_tokens": 1283170, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1266612, - "deferred_resource_tokens": 406347, + "estimated_total_text_tokens": 1283937, + "deferred_resource_tokens": 414478, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102 + "estimated_tokens": 365888, + "file_count": 105 }, { "path": "references", - "estimated_tokens": 25901, - "file_count": 32 + "estimated_tokens": 26755, + "file_count": 34 }, { "path": "evals", @@ -31,8 +31,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102 + "estimated_tokens": 365888, + "file_count": 105 } ], "deferred_resource_governance": { @@ -54,14 +54,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102, + "estimated_tokens": 365888, + "file_count": 105, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 525, + "relevant_file_count": 537, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 135.4 diff --git a/reports/context_budget.md b/reports/context_budget.md index 1cc283d5..373065fa 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 960 | 767 | 406347 | `governed` | scripts:358611 | 135.4 | - | ok | +| root | `.` | `production` | 1000 | 960 | 767 | 414478 | `governed` | scripts:365888 | 135.4 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index f969ea4b..53c94ae8 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -8,12 +8,12 @@ "budget_limit": 1000, "initial_tokens": 960, "skill_body_tokens": 767, - "deferred_resource_tokens": 406347, + "deferred_resource_tokens": 414478, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102 + "estimated_tokens": 365888, + "file_count": 105 } ], "deferred_resource_governance": { @@ -35,8 +35,8 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102, + "estimated_tokens": 365888, + "file_count": 105, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], diff --git a/reports/install_simulation.json b/reports/install_simulation.json index ad7559a2..77bda91b 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -8,7 +8,7 @@ "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 586, + "archive_entry_count": 598, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 9de1c887..ca23572d 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.08, + "duration_ms": 58.58, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 46.44, + "duration_ms": 40.49, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.3, + "duration_ms": 39.32, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.96, + "duration_ms": 38.11, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 57.56, + "duration_ms": 50.33, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 43.25, + "duration_ms": 50.85, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 39.31, + "duration_ms": 40.77, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.5, + "duration_ms": 37.9, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.42, + "duration_ms": 36.65, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.66, + "duration_ms": 35.4, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 0c3b5691..715ade7f 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext | Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status | | --- | --- | --- | --- | ---: | ---: | ---: | --- | -| skill-package-contract | baseline | command | local-output-eval-runner | 37.08 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 46.44 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 36.3 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.96 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 57.56 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 43.25 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 39.31 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 38.5 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 38.42 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 37.66 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 58.58 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 40.49 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 39.32 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 38.11 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 50.33 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 50.85 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 40.77 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 37.9 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 36.65 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 35.4 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index 71623276..570615e1 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,11 +1,11 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", - "file_count": 165, + "file_count": 169, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -196,6 +196,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/propose_adaptation.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/provider_output_eval_runner.py", "ok": true, @@ -556,6 +562,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/summarize_user_signals.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/sync_local_install.py", "ok": true, @@ -616,6 +628,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/yao_cli_config.py", "ok": true, @@ -652,6 +670,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_adaptation_safety.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_adapter_snapshots.py", "ok": true, diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 1f33c7bc..963df5ed 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,12 +1,12 @@ # Python Compatibility -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary - decision: `pass` - target python: `3.11` -- files scanned: `165` +- files scanned: `169` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 1795bfe7..41b6aa41 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 4c42ce51..e60add1e 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5` +- Package SHA256: `37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba` - Archive SHA256: `6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index ec24b6f5..4219c017 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,12 +676,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint20/20

2.0 coverage; extensions partial 1, planned 1; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

102 scripts scanned; secrets found

Py Compat0

165 files scanned for Python 3.11

Arch Debt0

891 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

586 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint20/20

2.0 coverage; extensions partial 2, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

105 scripts scanned; secrets found

Py Compat0

169 files scanned for Python 3.11

Arch Debt0

894 largest lines; 34 CLI handlers

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

73 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

586 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 102 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 960/1000; deferred 414470/120000; top deferred scripts 365880; resource governance governed; quality density 135.4

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 105 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 169 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

166 Python files; 0 hotspots; 0 blockers; largest 894 lines; 34 CLI handlers

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

@@ -743,17 +743,17 @@
-

上下文

initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4

+

上下文

initial load 960/1000; deferred 414470/120000; top deferred scripts 365880; resource governance governed; quality density 135.4

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
102
网络脚本
3
Help 失败
0
包体哈希
fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5
+

信任报告

Secret
0
脚本数
105
网络脚本
3
Help 失败
0
包体哈希
7df432cd514ab7be6cad1a7e88210c72dae2348844d38feb1f2dd8a262f14b76

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

-

Python 兼容

目标 Python
3.11
文件数
165
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
169
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。

@@ -801,13 +801,13 @@
-

蓝图覆盖

项目数
20
模块数
8
建议 PR
12
通过数
20
Warn Count
0
缺失数
0
Extension Track Count
2
Extension Partial Count
1
Extension Planned Count
1
Adaptive Extension Ready
否
本地蓝图
是
世界级
否
待补证据
4
+

蓝图覆盖

项目数
20
模块数
8
建议 PR
12
通过数
20
Warn Count
0
缺失数
0
Extension Track Count
2
Extension Partial Count
2
Extension Planned Count
0
Adaptive Extension Ready
否
本地蓝图
是
世界级
否
待补证据
4

覆盖边界

蓝图覆盖只证明 2.0 模块、建议 PR、脚本、报告和测试在本地闭环；public world-class 仍以 world-class evidence ledger 的真人和外部证据为准。

-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

  • 阻断release lock is not clean or commit is unavailable
  • 阻断provider-backed model holdout evidence is incomplete
  • 阻断human blind-review adjudication is incomplete
  • 阻断world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)
  • 阻断world-class source checks are not all accepted (6/13 pass, 7 blocked)
diff --git a/reports/review-studio.json b/reports/review-studio.json index 9a996044..74627d40 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4", + "detail": "initial load 960/1000; deferred 414470/120000; top deferred scripts 365880; resource governance governed; quality density 135.4", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -59,7 +59,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 102 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 105 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -67,7 +67,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 169 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -75,7 +75,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers", + "detail": "166 Python files; 0 hotspots; 0 blockers; largest 894 lines; 34 CLI handlers", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -778,7 +778,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 15566 个词/字。", + "入口约 356 个词/字，references 约 16045 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -882,7 +882,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。" + "上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -1183,13 +1183,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", @@ -1204,7 +1204,7 @@ "file_count": 207 } ], - "file_count": 373, + "file_count": 378, "folder_count": 4, "distribution": [ { @@ -1225,11 +1225,11 @@ }, { "label": "references", - "value": 32 + "value": 34 }, { "label": "scripts", - "value": 102 + "value": 105 }, { "label": "evals", @@ -1353,13 +1353,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", @@ -1672,11 +1672,11 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb", + "evidence_bundle_sha256": "bc6faadfc706df8308850e2a2bd33da8b76ece0aa854d701ef2cef7fde0e2fb4", "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, @@ -1696,11 +1696,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 30 }, - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -4342,7 +4342,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.08, + "duration_ms": 32.7, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4370,7 +4370,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 46.44, + "duration_ms": 31.4, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4393,7 +4393,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 36.3, + "duration_ms": 31.59, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4421,7 +4421,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.96, + "duration_ms": 31.55, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4444,7 +4444,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 57.56, + "duration_ms": 31.61, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4472,7 +4472,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 43.25, + "duration_ms": 32.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4495,7 +4495,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 39.31, + "duration_ms": 34.35, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4522,7 +4522,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.5, + "duration_ms": 58.54, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4545,7 +4545,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.42, + "duration_ms": 39.5, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4574,7 +4574,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 37.66, + "duration_ms": 39.79, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5295,21 +5295,34 @@ "ok": true, "generated_at": "2026-06-15", "skill_dir": ".", - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 30, + "sample": [ + " M README.md", + " M reports/adoption_drift_report.json", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/output_execution_runs.json", + " M reports/output_execution_runs.md", + " M reports/python_compatibility.json" + ], "scope": "generation-time status before this report is written" }, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb", + "evidence_bundle_sha256": "bc6faadfc706df8308850e2a2bd33da8b76ece0aa854d701ef2cef7fde0e2fb4", "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, @@ -5329,14 +5342,15 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 30 }, "public_claim": { "ready": false, "scope": "public benchmark or world-class readiness claim", "blockers": [ + "release lock is not clean or commit is unavailable", "provider-backed model holdout evidence is incomplete", "human blind-review adjudication is incomplete", "world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)", @@ -5345,10 +5359,10 @@ "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "ready": false, + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "status_scope": "generation-time status before this report is written", - "reason": "clean generation-time HEAD" + "reason": "working tree was dirty at generation time" }, "evidence_bundle": { "algorithm": "sha256(path,label,exists,artifact_sha256)", @@ -5356,7 +5370,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb" + "sha256": "bc6faadfc706df8308850e2a2bd33da8b76ece0aa854d701ef2cef7fde0e2fb4" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5429,8 +5443,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "e05906fb7e4242e1b4c373285f5bca3283986301f13e08c2d64715efb9f827a4" + "bytes": 7964, + "sha256": "f98615e61d82c2a935157444ea83931267ebd7ef7b76d296e78205ccb1448ff2" }, { "label": "blind_review", @@ -5471,8 +5485,8 @@ "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 21493, - "sha256": "5be76147f3cb9952f8c5f524c8195eb94ea44e5172ab4b34b1b9208f6d8c198a" + "bytes": 21994, + "sha256": "afc31ecb61e58d2f7396a0a069d90aecf9b6312ec0e56f0f1624add940e129d2" }, { "label": "registry_audit", @@ -5696,8 +5710,8 @@ "warn_count": 0, "missing_count": 0, "extension_track_count": 2, - "extension_partial_count": 1, - "extension_planned_count": 1, + "extension_partial_count": 2, + "extension_planned_count": 0, "extension_covered_count": 0, "adaptive_extension_ready": false, "local_blueprint_ready": true, @@ -5711,8 +5725,7 @@ "missing": 0 }, "extension_status_counts": { - "partial": 1, - "planned": 1 + "partial": 2 }, "modules": [ { @@ -6333,39 +6346,55 @@ { "key": "adaptive-self-iteration", "label": "Adaptive Self-Iteration", - "status": "planned", + "status": "partial", "objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", - "current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + "current": "Proposal-only adapt-scan/adapt-propose foundation exists with policy, schema, and safety tests; approval-gated patch application is not implemented yet.", "target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", "evidence": [ { "path": "references/autonomous-adaptation.md", - "exists": false + "exists": true }, { "path": "references/user-memory-policy.md", - "exists": false + "exists": true }, { "path": "schemas/adaptation-proposal.schema.json", - "exists": false + "exists": true }, { "path": "scripts/summarize_user_signals.py", - "exists": false + "exists": true }, { "path": "scripts/propose_adaptation.py", - "exists": false + "exists": true + }, + { + "path": "tests/verify_adaptation_safety.py", + "exists": true }, { "path": "scripts/apply_adaptation.py", "exists": false }, { - "path": "tests/verify_adaptation_safety.py", + "path": "reports/adaptation_approval_ledger.json", "exists": false }, + { + "path": "reports/adaptation_regression_report.json", + "exists": false + }, + { + "path": "reports/user_patterns.json", + "exists": true + }, + { + "path": "reports/adaptation_proposals.json", + "exists": true + }, { "path": "reports/iteration-directions.md", "exists": true @@ -6375,7 +6404,7 @@ "exists": true } ], - "next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path." + "next_action": "Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed." } ], "next_highest_leverage": [ @@ -11267,9 +11296,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 186, - "script_count": 102, - "internal_module_count": 25, + "scanned_files": 192, + "script_count": 105, + "internal_module_count": 26, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -11277,18 +11306,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 64, + "file_write_script_count": 66, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 77, + "help_smoke_checked_count": 79, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 186, - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_hash_file_count": 192, + "package_sha256": "7df432cd514ab7be6cad1a7e88210c72dae2348844d38feb1f2dd8a262f14b76" }, "failures": [], "warnings": [], @@ -11667,6 +11696,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/propose_adaptation.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Turns redacted repeated preference patterns into proposal-only adaptation plans.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/provider_output_eval_runner.py", "interface": "cli", @@ -12515,6 +12558,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/summarize_user_signals.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Scans an explicit local source file and summarizes redacted repeated user preference signals.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/sync_local_install.py", "interface": "cli", @@ -12655,6 +12712,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by yao.py to keep adaptive scan/proposal command handlers outside the thin CLI orchestrator.", + "has_argparse": true, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/yao_cli_config.py", "interface": "internal-module", @@ -12770,11 +12841,11 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 77, - "checked_count": 77, - "passed_count": 77, + "candidate_count": 79, + "checked_count": 79, + "passed_count": 79, "failed_count": 0, - "skipped_count": 25, + "skipped_count": 26, "failed_scripts": [], "results": [ { @@ -13027,6 +13098,16 @@ "stdout_excerpt": "usage: promotion_checker.py [-h] [--optimization-suite OPTIMIZATION_SUITE]\n [--route-scorecard ROUTE_SCORECARD]\n [--output-json OUTPUT_JSON]\n [--output-md OUTP", "stderr_excerpt": "" }, + { + "path": "scripts/propose_adaptation.py", + "command": "python3 scripts/propose_adaptation.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: propose_adaptation.py [-h] [--patterns-json PATTERNS_JSON]\n [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [--generated-at GENERATED_AT]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/provider_output_eval_runner.py", "command": "python3 scripts/provider_output_eval_runner.py --help", @@ -13467,6 +13548,16 @@ "stdout_excerpt": "usage: simulate_install.py [-h] [--package-dir PACKAGE_DIR]\n [--install-root INSTALL_ROOT]\n [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n [--generated-at G", "stderr_excerpt": "" }, + { + "path": "scripts/summarize_user_signals.py", + "command": "python3 scripts/summarize_user_signals.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: summarize_user_signals.py [-h] --source SOURCE\n [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [--min-support MIN_SUPPORT]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/sync_local_install.py", "command": "python3 scripts/sync_local_install.py --help", @@ -13625,6 +13716,10 @@ "path": "scripts/world_class_source_checks.py", "reason": "internal module" }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "reason": "internal module" + }, { "path": "scripts/yao_cli_config.py", "reason": "internal module" @@ -13721,6 +13816,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -13762,6 +13858,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", @@ -13834,7 +13931,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 165, + "file_count": 169, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -14025,6 +14122,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/propose_adaptation.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/provider_output_eval_runner.py", "ok": true, @@ -14385,6 +14488,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/summarize_user_signals.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/sync_local_install.py", "ok": true, @@ -14445,6 +14554,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/yao_cli_config.py", "ok": true, @@ -14481,6 +14596,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_adaptation_safety.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_adapter_snapshots.py", "ok": true, @@ -14854,15 +14975,15 @@ "generated_at": "2026-06-15", "skill_dir": ".", "summary": { - "python_file_count": 162, - "script_file_count": 102, - "test_file_count": 60, - "internal_module_count": 28, - "cli_script_count": 76, + "python_file_count": 166, + "script_file_count": 105, + "test_file_count": 61, + "internal_module_count": 29, + "cli_script_count": 78, "command_handler_count": 34, "warn_line_threshold": 900, "block_line_threshold": 1500, - "largest_file_lines": 891, + "largest_file_lines": 894, "hotspot_count": 0, "blocker_count": 0, "decision": "pass" @@ -14870,14 +14991,14 @@ "largest_files": [ { "path": "tests/verify_yao_cli.py", - "lines": 891, + "lines": 894, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, { "path": "scripts/yao.py", - "lines": 881, + "lines": 882, "kind": "cli-script", "severity": "pass", "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator." @@ -14896,6 +15017,13 @@ "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." }, + { + "path": "scripts/yao_cli_parser.py", + "lines": 765, + "kind": "internal-module", + "severity": "pass", + "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." + }, { "path": "tests/verify_review_studio.py", "lines": 745, @@ -14903,13 +15031,6 @@ "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, - { - "path": "scripts/yao_cli_parser.py", - "lines": 741, - "kind": "internal-module", - "severity": "pass", - "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." - }, { "path": "scripts/compile_skill.py", "lines": 734, @@ -14968,21 +15089,21 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 767, - "other_text_tokens": 1265845, + "other_text_tokens": 1283182, "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1266612, - "deferred_resource_tokens": 406347, + "estimated_total_text_tokens": 1283949, + "deferred_resource_tokens": 414470, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102 + "estimated_tokens": 365880, + "file_count": 105 }, { "path": "references", - "estimated_tokens": 25901, - "file_count": 32 + "estimated_tokens": 26755, + "file_count": 34 }, { "path": "evals", @@ -14993,8 +15114,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102 + "estimated_tokens": 365880, + "file_count": 105 } ], "deferred_resource_governance": { @@ -15016,14 +15137,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 358611, - "file_count": 102, + "estimated_tokens": 365880, + "file_count": 105, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 525, + "relevant_file_count": 537, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 135.4 @@ -16884,7 +17005,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T11:08:09Z", + "generated_at": "2026-06-15T11:21:49Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/review-viewer.json b/reports/review-viewer.json index a1315986..ad198741 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -101,7 +101,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 15566 个词/字。", + "入口约 356 个词/字，references 约 16045 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -205,7 +205,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。" + "上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -506,28 +506,28 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", "label": "Trigger and quality checks", "kind": "folder", - "file_count": 28 + "file_count": 29 }, { "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 207 + "file_count": 211 } ], - "file_count": 373, + "file_count": 383, "folder_count": 4, "distribution": [ { @@ -548,19 +548,19 @@ }, { "label": "references", - "value": 32 + "value": 34 }, { "label": "scripts", - "value": 102 + "value": 105 }, { "label": "evals", - "value": 28 + "value": 29 }, { "label": "reports", - "value": 207 + "value": 211 } ] }, @@ -676,25 +676,25 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", "label": "Trigger and quality checks", "kind": "folder", - "file_count": 28 + "file_count": 29 }, { "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 207 + "file_count": 211 } ], "strengths": [ @@ -995,12 +995,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb", - "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "evidence_bundle_sha256": "4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c", + "source_contract_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1019,11 +1019,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1107,9 +1107,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 186, - "script_count": 102, - "internal_module_count": 25, + "scanned_files": 192, + "script_count": 105, + "internal_module_count": 26, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1117,18 +1117,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 64, + "file_write_script_count": 66, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 77, + "help_smoke_checked_count": 79, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 186, - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_hash_file_count": 192, + "package_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32" }, "skill_atlas": { "skill_count": 12, @@ -1166,7 +1166,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "package_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1226,7 +1226,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 586, + "archive_entry_count": 598, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1298,7 +1298,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "to": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32" } ] }, diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 76fadc1f..66f2b1d9 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 3acbd17e..07eeccbc 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -52,7 +52,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { diff --git a/reports/review_waivers.md b/reports/review_waivers.md index 2fcb0546..dbc942d1 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -35,7 +35,7 @@ - waiver allowed: `true` - risk: review pending 5; model-executed 0; output failures 0 - evidence: `reports/output_review_adjudication.md` -- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 9097799c..338e8e02 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,9 +2,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 186, - "script_count": 102, - "internal_module_count": 25, + "scanned_files": 192, + "script_count": 105, + "internal_module_count": 26, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -12,18 +12,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 64, + "file_write_script_count": 66, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 77, + "help_smoke_checked_count": 79, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 186, - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_hash_file_count": 192, + "package_sha256": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba" }, "failures": [], "warnings": [], @@ -402,6 +402,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/propose_adaptation.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Turns redacted repeated preference patterns into proposal-only adaptation plans.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/provider_output_eval_runner.py", "interface": "cli", @@ -1250,6 +1264,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/summarize_user_signals.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Scans an explicit local source file and summarizes redacted repeated user preference signals.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/sync_local_install.py", "interface": "cli", @@ -1390,6 +1418,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by yao.py to keep adaptive scan/proposal command handlers outside the thin CLI orchestrator.", + "has_argparse": true, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/yao_cli_config.py", "interface": "internal-module", @@ -1505,11 +1547,11 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 77, - "checked_count": 77, - "passed_count": 77, + "candidate_count": 79, + "checked_count": 79, + "passed_count": 79, "failed_count": 0, - "skipped_count": 25, + "skipped_count": 26, "failed_scripts": [], "results": [ { @@ -1762,6 +1804,16 @@ "stdout_excerpt": "usage: promotion_checker.py [-h] [--optimization-suite OPTIMIZATION_SUITE]\n [--route-scorecard ROUTE_SCORECARD]\n [--output-json OUTPUT_JSON]\n [--output-md OUTP", "stderr_excerpt": "" }, + { + "path": "scripts/propose_adaptation.py", + "command": "python3 scripts/propose_adaptation.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: propose_adaptation.py [-h] [--patterns-json PATTERNS_JSON]\n [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [--generated-at GENERATED_AT]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/provider_output_eval_runner.py", "command": "python3 scripts/provider_output_eval_runner.py --help", @@ -2202,6 +2254,16 @@ "stdout_excerpt": "usage: simulate_install.py [-h] [--package-dir PACKAGE_DIR]\n [--install-root INSTALL_ROOT]\n [--output-json OUTPUT_JSON] [--output-md OUTPUT_MD]\n [--generated-at G", "stderr_excerpt": "" }, + { + "path": "scripts/summarize_user_signals.py", + "command": "python3 scripts/summarize_user_signals.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: summarize_user_signals.py [-h] --source SOURCE\n [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [--min-support MIN_SUPPORT]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/sync_local_install.py", "command": "python3 scripts/sync_local_install.py --help", @@ -2360,6 +2422,10 @@ "path": "scripts/world_class_source_checks.py", "reason": "internal module" }, + { + "path": "scripts/yao_cli_adaptation_commands.py", + "reason": "internal module" + }, { "path": "scripts/yao_cli_config.py", "reason": "internal module" @@ -2456,6 +2522,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", "scripts/render_adoption_drift_report.py", @@ -2497,6 +2564,7 @@ "scripts/run_output_eval.py", "scripts/run_output_execution.py", "scripts/simulate_install.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trust_check.py", diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index bab77b4f..f813033f 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,22 +1,22 @@ # Security Trust Report - OK: `True` -- Scanned files: `186` -- Scripts: `102` -- Internal script modules: `25` +- Scanned files: `192` +- Scripts: `105` +- Internal script modules: `26` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` - Network policy missing scripts: `0` -- File-write scripts: `64` +- File-write scripts: `66` - Permission approvals: `3 / 3` - Permission approval gaps: `0` -- CLI help smoke checked: `77` +- CLI help smoke checked: `79` - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `186` -- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5` +- Package hash files: `192` +- Package SHA256: `37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba` ## Failures @@ -54,8 +54,8 @@ - Enabled: `True` - Timeout seconds: `5.0` -- Checked scripts: `77` -- Passed scripts: `77` +- Checked scripts: `79` +- Passed scripts: `79` - Failed scripts: `none` ## Script Surface @@ -88,6 +88,7 @@ | scripts/prepare_world_class_submission_kit.py | cli | True | True | True | False | False | True | False | Prepares editable world-class evidence intake packets without counting drafts as accepted evidence. | | scripts/probe_runtime_permissions.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/promotion_checker.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | +| scripts/propose_adaptation.py | cli | True | True | True | False | False | True | False | Turns redacted repeated preference patterns into proposal-only adaptation plans. | | scripts/provider_output_eval_runner.py | cli | False | True | True | False | True | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/python_compat_check.py | cli | True | True | True | False | False | True | False | Checks repository Python source for syntax that can pass locally but fail on the supported CI interpreter. | | scripts/registry_audit.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | @@ -148,6 +149,7 @@ | scripts/skill_report_metrics.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to calculate overview report metrics. | | scripts/skill_report_model.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to build the v2 report data model. | | scripts/skill_report_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to summarize world-class evidence readiness and roadmap actions. | +| scripts/summarize_user_signals.py | cli | True | True | True | False | False | True | False | Scans an explicit local source file and summarizes redacted repeated user preference signals. | | scripts/sync_local_install.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/telemetry_native_host.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/trigger_eval.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | @@ -158,6 +160,7 @@ | scripts/world_class_evidence_contract.py | internal-module | True | False | False | False | False | False | False | Imported by world-class evidence reports to share intake validation and artifact integrity checks. | | scripts/world_class_source_checks.py | internal-module | True | False | False | False | False | False | False | Imported by world-class evidence reports to keep source-evidence readiness checks consistent. | | scripts/yao.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | +| scripts/yao_cli_adaptation_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep adaptive scan/proposal command handlers outside the thin CLI orchestrator. | | scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. | | scripts/yao_cli_create_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator. | | scripts/yao_cli_parser.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep CLI parser declarations separate from command orchestration. | diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 4a9d6177..f6ac105d 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -761,7 +761,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。After creation, open reports/skill-overview.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 356 个词/字，references 约 15566 个词/字。Entrypoint is about 356 words/characters; references are about 15566.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 356 个词/字，references 约 16045 个词/字。Entrypoint is about 356 words/characters; references are about 16045.
@@ -797,10 +797,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 356 个词/字，references 约 15566 个词/字。Entrypoint is about 356 words/characters; references are about 15566.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 356 个词/字，references 约 16045 个词/字。Entrypoint is about 356 words/characters; references are about 16045.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 356 个词/字，references 约 15566 个词/字。Entrypoint is about 356 words/characters; references are about 15566.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 356 个词/字，references 约 16045 个词/字。Entrypoint is about 356 words/characters; references are about 16045.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -875,7 +875,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 15566.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 16045.纳入下一轮修复Fix next
@@ -927,7 +927,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution373项373 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution383项383 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 3b7e2a6b..5164beda 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -100,7 +100,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 15566 个词/字。", + "入口约 356 个词/字，references 约 16045 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -204,7 +204,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 15566 个词/字。" + "上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -505,28 +505,28 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", "label": "Trigger and quality checks", "kind": "folder", - "file_count": 28 + "file_count": 29 }, { "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 207 + "file_count": 211 } ], - "file_count": 373, + "file_count": 383, "folder_count": 4, "distribution": [ { @@ -547,19 +547,19 @@ }, { "label": "references", - "value": 32 + "value": 34 }, { "label": "scripts", - "value": 102 + "value": 105 }, { "label": "evals", - "value": 28 + "value": 29 }, { "label": "reports", - "value": 207 + "value": 211 } ] }, @@ -675,25 +675,25 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 32 + "file_count": 34 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 102 + "file_count": 105 }, { "path": "evals", "label": "Trigger and quality checks", "kind": "folder", - "file_count": 28 + "file_count": 29 }, { "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 207 + "file_count": 211 } ], "strengths": [ @@ -994,12 +994,12 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "2885b1100c09f73a4e09c9a210eb41bccfda117c08ffd62d60619987b9ff76eb", - "source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "evidence_bundle_sha256": "4c07bfcbbf601e11c3d8b986c939987ad7ad1aa1a091ea036b8dae40f77e740c", + "source_contract_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1018,11 +1018,11 @@ "world_class_source_pass_count": 6, "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4, - "working_tree_dirty": false, - "changed_file_count": 0 + "public_claim_blocker_count": 5, + "working_tree_dirty": true, + "changed_file_count": 56 }, - "commit": "ee2130176fdf69358b9e02cf319329c6aadd841a", + "commit": "180dbf4a41ad242a3e666ff2c542c92b590bdce0", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -1106,9 +1106,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 186, - "script_count": 102, - "internal_module_count": 25, + "scanned_files": 192, + "script_count": 105, + "internal_module_count": 26, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1116,18 +1116,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 64, + "file_write_script_count": 66, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 77, + "help_smoke_checked_count": 79, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 186, - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "package_hash_file_count": 192, + "package_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32" }, "skill_atlas": { "skill_count": 12, @@ -1165,7 +1165,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5", + "package_sha256": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32", "archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc" }, "compatibility": { @@ -1225,7 +1225,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 586, + "archive_entry_count": 598, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1297,7 +1297,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "to": "024e577f4b07e803e451c9ad1cc034023bc8502c57b3e09a8b6193e12660de32" } ] }, diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index ab1c3de2..6b4b6814 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -90,6 +90,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -150,6 +151,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/skill_report_world_class.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", @@ -160,6 +162,7 @@ "scripts/world_class_evidence_contract.py", "scripts/world_class_source_checks.py", "scripts/yao.py", + "scripts/yao_cli_adaptation_commands.py", "scripts/yao_cli_config.py", "scripts/yao_cli_create_commands.py", "scripts/yao_cli_parser.py", @@ -168,6 +171,7 @@ "scripts/yao_cli_telemetry.py", "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -198,6 +202,7 @@ "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", "references/trust-security-method.md", + "references/user-memory-policy.md", "templates/basic_skill.md.j2", "templates/complex_skill.md.j2" ], diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 49a4d428..60ff43ce 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 102; help failures 0", + "current": "secrets 0; scripts 105; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index a5cb9801..a1a5fc8b 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -23,7 +23,7 @@ Generated at: `2026-06-13` | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. | | Benchmark Reproducibility | pass | artifacts 24; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. | | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. | -| Trust Security | pass | secrets 0; scripts 102; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | +| Trust Security | pass | secrets 0; scripts 105; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index b87347f3..214491ba 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 20, @@ -11,8 +11,8 @@ "warn_count": 0, "missing_count": 0, "extension_track_count": 2, - "extension_partial_count": 1, - "extension_planned_count": 1, + "extension_partial_count": 2, + "extension_planned_count": 0, "extension_covered_count": 0, "adaptive_extension_ready": false, "local_blueprint_ready": true, @@ -26,8 +26,7 @@ "missing": 0 }, "extension_status_counts": { - "partial": 1, - "planned": 1 + "partial": 2 }, "modules": [ { @@ -131,7 +130,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "102 scripts; secrets 0; help failures 0", + "current": "105 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -648,39 +647,55 @@ { "key": "adaptive-self-iteration", "label": "Adaptive Self-Iteration", - "status": "planned", + "status": "partial", "objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", - "current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + "current": "Proposal-only adapt-scan/adapt-propose foundation exists with policy, schema, and safety tests; approval-gated patch application is not implemented yet.", "target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", "evidence": [ { "path": "references/autonomous-adaptation.md", - "exists": false + "exists": true }, { "path": "references/user-memory-policy.md", - "exists": false + "exists": true }, { "path": "schemas/adaptation-proposal.schema.json", - "exists": false + "exists": true }, { "path": "scripts/summarize_user_signals.py", - "exists": false + "exists": true }, { "path": "scripts/propose_adaptation.py", - "exists": false + "exists": true + }, + { + "path": "tests/verify_adaptation_safety.py", + "exists": true }, { "path": "scripts/apply_adaptation.py", "exists": false }, { - "path": "tests/verify_adaptation_safety.py", + "path": "reports/adaptation_approval_ledger.json", "exists": false }, + { + "path": "reports/adaptation_regression_report.json", + "exists": false + }, + { + "path": "reports/user_patterns.json", + "exists": true + }, + { + "path": "reports/adaptation_proposals.json", + "exists": true + }, { "path": "reports/iteration-directions.md", "exists": true @@ -690,7 +705,7 @@ "exists": true } ], - "next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path." + "next_action": "Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed." } ], "next_highest_leverage": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index d12da8b4..9d6827fe 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Blueprint Coverage -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -11,8 +11,8 @@ Generated at: `2026-06-15` - missing: `0` - warn: `0` - reference extensions: `2` -- extension partial: `1` -- extension planned: `1` +- extension partial: `2` +- extension planned: `0` - adaptive extension ready: `false` - world-class evidence pending: `4` @@ -25,7 +25,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` | | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` | | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | -| Trust Security | `pass` | 102 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 105 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` | | Registry Distribution | `pass` | archive entries 586; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` | @@ -53,7 +53,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Track | Status | Current | Target | Next action | | --- | --- | --- | --- | --- | | Skill Interpretation Report | `partial` | Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet. | Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests. | Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests. | -| Adaptive Self-Iteration | `planned` | The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy. | Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan. | Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. | +| Adaptive Self-Iteration | `partial` | Proposal-only adapt-scan/adapt-propose foundation exists with policy, schema, and safety tests; approval-gated patch application is not implemented yet. | Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan. | Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed. | These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution. @@ -217,7 +217,7 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are ### Adaptive Self-Iteration - objective: Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback. -- status: `planned` -- existing evidence: `reports/iteration-directions.md`, `reports/adoption_drift_report.md` -- missing evidence: `references/autonomous-adaptation.md`, `references/user-memory-policy.md`, `schemas/adaptation-proposal.schema.json`, `scripts/summarize_user_signals.py`, `scripts/propose_adaptation.py`, `scripts/apply_adaptation.py`, `tests/verify_adaptation_safety.py` -- next action: Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. +- status: `partial` +- existing evidence: `references/autonomous-adaptation.md`, `references/user-memory-policy.md`, `schemas/adaptation-proposal.schema.json`, `scripts/summarize_user_signals.py`, `scripts/propose_adaptation.py`, `tests/verify_adaptation_safety.py`, `reports/user_patterns.json`, `reports/adaptation_proposals.json`, `reports/iteration-directions.md`, `reports/adoption_drift_report.md` +- missing evidence: `scripts/apply_adaptation.py`, `reports/adaptation_approval_ledger.json`, `reports/adaptation_regression_report.json` +- next action: Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed. diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index c2afb6d4..56d93474 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5" + "to": "37a1ec0f35323886bdae64523b4113f5dc4ba3153117ee4980b8e5cd54b49aba" } ] }, diff --git a/reports/user_patterns.json b/reports/user_patterns.json new file mode 100644 index 00000000..d73a4f86 --- /dev/null +++ b/reports/user_patterns.json @@ -0,0 +1,136 @@ +{ + "ok": true, + "schema_version": "1.0", + "generated_at": "2026-06-15T00:00:00Z", + "skill_dir": ".", + "source": { + "label": "user_signals.example.jsonl", + "path": "evals/adaptation/user_signals.example.jsonl", + "fingerprint_sha256": "48f94a4f3b82f90db29921c13d09c765ec10aabfde1adce65710c137cc6c5abf", + "explicit_source": true, + "record_count": 8 + }, + "privacy_contract": { + "local_only": true, + "explicit_source_required": true, + "implicit_private_log_scan": false, + "raw_content_stored": false, + "redacted_excerpts_only": true, + "redacted_excerpt_limit": 240, + "writes_repository_files": false + }, + "summary": { + "record_count": 8, + "pattern_count": 5, + "discarded_signal_count": 0, + "min_support": 2, + "failure_count": 0 + }, + "patterns": [ + { + "pattern_id": "language_default", + "label": "Default language preference", + "signal_type": "report-language", + "support_count": 2, + "confidence": 0.79, + "reason": "2 redacted records matched repeated report-language signals.", + "recommended_action": "Keep generated reports Chinese-first with an English switch where user-facing.", + "evidence": [ + { + "record_id": "line-1", + "excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。" + }, + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + } + ] + }, + { + "pattern_id": "report_ui", + "label": "Report UI and visualization preference", + "signal_type": "artifact-design", + "support_count": 5, + "confidence": 0.95, + "reason": "5 redacted records matched repeated artifact-design signals.", + "recommended_action": "Prioritize white-background Kami-style reports with readable charts and stable navigation.", + "evidence": [ + { + "record_id": "line-1", + "excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。" + }, + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + }, + { + "record_id": "line-3", + "excerpt": "报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。" + } + ] + }, + { + "pattern_id": "approval_safety", + "label": "Approval and privacy boundary", + "signal_type": "governance", + "support_count": 2, + "confidence": 0.79, + "reason": "2 redacted records matched repeated governance signals.", + "recommended_action": "Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path.", + "evidence": [ + { + "record_id": "line-5", + "excerpt": "自适应升级必须先生成提案，不能直接自动修改源文件。" + }, + { + "record_id": "line-6", + "excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。" + } + ] + }, + { + "pattern_id": "delivery_format", + "label": "Delivery format preference", + "signal_type": "artifact-format", + "support_count": 2, + "confidence": 0.79, + "reason": "2 redacted records matched repeated artifact-format signals.", + "recommended_action": "Surface stable artifact paths and formats in CLI output and generated summaries.", + "evidence": [ + { + "record_id": "line-2", + "excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。" + }, + { + "record_id": "line-6", + "excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。" + } + ] + }, + { + "pattern_id": "evidence_testing", + "label": "Evidence and testing preference", + "signal_type": "quality-gate", + "support_count": 2, + "confidence": 0.79, + "reason": "2 redacted records matched repeated quality-gate signals.", + "recommended_action": "Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade.", + "evidence": [ + { + "record_id": "line-7", + "excerpt": "每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。" + }, + { + "record_id": "line-8", + "excerpt": "涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。" + } + ] + } + ], + "discarded_signals": [], + "failures": [], + "artifacts": { + "json": "reports/user_patterns.json", + "markdown": "reports/user_patterns.md" + } +} diff --git a/reports/user_patterns.md b/reports/user_patterns.md new file mode 100644 index 00000000..855d5ebb --- /dev/null +++ b/reports/user_patterns.md @@ -0,0 +1,72 @@ +# User Pattern Summary + +- Generated at: `2026-06-15T00:00:00Z` +- Local only: `true` +- Explicit source: `evals/adaptation/user_signals.example.jsonl` +- Records: `8` +- Patterns: `5` +- Discarded signals: `0` + +## Privacy Contract + +- No implicit private log scan. +- No unredacted raw content stored. +- Scan and proposal stages do not write source files. + +## Patterns + +### Default language preference + +- Pattern: `language_default` +- Support: `2` +- Confidence: `0.79` +- Reason: 2 redacted records matched repeated report-language signals. +- Recommended action: Keep generated reports Chinese-first with an English switch where user-facing. +- Redacted evidence: + - `line-1`: 新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。 + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + +### Report UI and visualization preference + +- Pattern: `report_ui` +- Support: `5` +- Confidence: `0.95` +- Reason: 5 redacted records matched repeated artifact-design signals. +- Recommended action: Prioritize white-background Kami-style reports with readable charts and stable navigation. +- Redacted evidence: + - `line-1`: 新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。 + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + - `line-3`: 报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。 + +### Approval and privacy boundary + +- Pattern: `approval_safety` +- Support: `2` +- Confidence: `0.79` +- Reason: 2 redacted records matched repeated governance signals. +- Recommended action: Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path. +- Redacted evidence: + - `line-5`: 自适应升级必须先生成提案，不能直接自动修改源文件。 + - `line-6`: 用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。 + +### Delivery format preference + +- Pattern: `delivery_format` +- Support: `2` +- Confidence: `0.79` +- Reason: 2 redacted records matched repeated artifact-format signals. +- Recommended action: Surface stable artifact paths and formats in CLI output and generated summaries. +- Redacted evidence: + - `line-2`: HTML 报告需要双语能力，但默认内容应该保持中文简体。 + - `line-6`: 用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。 + +### Evidence and testing preference + +- Pattern: `evidence_testing` +- Support: `2` +- Confidence: `0.79` +- Reason: 2 redacted records matched repeated quality-gate signals. +- Recommended action: Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade. +- Redacted evidence: + - `line-7`: 每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。 + - `line-8`: 涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。 diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index 29e36b21..f4de42a2 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -1,12 +1,12 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, "ledger_pending_count": 4, - "claim_surface_count": 73, + "claim_surface_count": 75, "violation_count": 0, "overclaim_guard_active": true, "decision": "claim-guard-pass-evidence-pending" @@ -67,6 +67,10 @@ "path": "docs/migration-v2.md", "violation_count": 0 }, + { + "path": "reports/adaptation_proposals.md", + "violation_count": 0 + }, { "path": "reports/adoption_drift_report.md", "violation_count": 0 @@ -303,6 +307,10 @@ "path": "reports/upgrade_check.md", "violation_count": 0 }, + { + "path": "reports/user_patterns.md", + "violation_count": 0 + }, { "path": "reports/world_class_evidence_intake.md", "violation_count": 0 diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index 8c4bc49c..98cc8e66 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -1,13 +1,13 @@ # World-Class Claim Guard -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary - decision: `claim-guard-pass-evidence-pending` - ledger ready to claim world-class: `false` - ledger pending evidence: `4` -- claim surfaces scanned: `73` +- claim surfaces scanned: `75` - violations: `0` - overclaim guard active: `true` diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index c773fa5d..ed002e84 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -307,7 +307,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index bc5fd179..62c2d7ed 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -1,6 +1,6 @@ # World-Class Evidence Intake -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index e245338f..6637eb6e 100644 --- a/reports/world_class_evidence_ledger.json +++ b/reports/world_class_evidence_ledger.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_entry_count": 4, @@ -14,8 +14,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -351,7 +351,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -388,7 +388,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -409,8 +409,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -426,8 +426,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index 1bc98d0c..8ec440ff 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -1,6 +1,6 @@ # World-Class Evidence Ledger -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -8,8 +8,8 @@ Generated at: `2026-06-15` - ready to claim world-class: `false` - entries: `4` - source accepted: `0` -- source checks: `6` pass / `13` total -- source blocked: `7` +- source checks: `7` pass / `13` total +- source blocked: `6` - accepted: `0` - pending: `4` - human pending: `1` @@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source | `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. | | `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. | | `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. | +| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. | ## Provider Holdout @@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` -- source checks: `1` pass / `3` total +- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` +- source checks: `2` pass / `3` total - submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}` ### Provenance Requirements @@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source | Check | Current | Expected | Status | | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | -| Adoption sample | `0` | `>0` | `blocked` | +| Adoption sample | `1` | `>0` | `pass` | | Raw content blocked | `False` | `false` | `pass` | ### Completion Assertions diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index 20b0d4e5..236c40fe 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", @@ -141,7 +141,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -299,7 +299,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index 6af4cf3c..c0db846d 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -1,6 +1,6 @@ # World-Class Evidence Plan -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It | `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 | | `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 | | `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | ## Provider Holdout diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index be9f2679..e239453a 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.

-
Pending4
Awaiting4
Ready0
Source6/13
Blocked7
Invalid0
+
Pending4
Awaiting4
Ready0
Source7/13
Blocked6
Invalid0

Fast Path

  1. Run the real external or human work for one evidence item.
  2. Generate and fill the matching submission draft.
  3. Validate intake and inspect the submission review queue.
  4. Refresh the ledger and run the claim guard before making any completion claim.

Evidence Items

@@ -120,7 +120,7 @@
Owner
Browser/Chrome/IDE/provider client integrator
Ledger
pending
-
Blocked
2
+
Blocked
1
Submission
evidence/world_class/submissions/native-client-telemetry.json

Source Runbook

  • python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  • Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -130,8 +130,8 @@

Success Checks

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

Privacy

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
-

Next Source Actions

  • Import at least one metadata-only event from a real client.
  • Telemetry must include adoption outcome evidence.
-

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
+

Next Source Actions

  • Import at least one metadata-only event from a real client.
+

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 1 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.

Boundary

  • Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.
  • Valid intake means ready for submission review; ledger review still requires passing source evidence.
  • The world-class ledger and claim guard remain the source of truth.
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index dfb90499..eb0e1857 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -12,8 +12,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -394,7 +394,7 @@ "review_state": "awaiting-submission", "source_accepted": false, "objective": "Import production metadata-only events from a real external client into the local drift loop.", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "execution_runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -442,7 +442,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -463,8 +463,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -479,10 +479,9 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 2, + "blocked_source_check_count": 1, "next_source_actions": [ - "Import at least one metadata-only event from a real client.", - "Telemetry must include adoption outcome evidence." + "Import at least one metadata-only event from a real client." ], "submission_state": { "status": "missing", diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index 3abb08c3..bef6278b 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -1,6 +1,6 @@ # World-Class Operator Runbook -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission | `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials | | `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer | | `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator | -| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | +| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator | ## Provider Holdout @@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission - objective: Import production metadata-only events from a real external client into the local drift loop. - blocking reason: No evidence packet has been submitted for review. -- blocked source checks: `2` +- blocked source checks: `1` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -292,14 +292,13 @@ This runbook coordinates evidence collection only. It does not accept submission ### Next Source Actions - Import at least one metadata-only event from a real client. -- Telemetry must include adoption outcome evidence. ### Source Evidence Snapshot | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 5b79d650..cb10f86b 100644 --- a/reports/world_class_submission_review.json +++ b/reports/world_class_submission_review.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-15", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "review_item_count": 4, @@ -13,8 +13,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 6, - "source_blocked_count": 7, + "source_pass_count": 7, + "source_blocked_count": 6, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -265,7 +265,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -286,8 +286,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 0, - "status": "blocked", + "actual": 1, + "status": "pass", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -303,8 +303,8 @@ } ], "source_check_count": 3, - "source_pass_count": 1, - "source_blocked_count": 2, + "source_pass_count": 2, + "source_blocked_count": 1, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index a896c218..7fe1e470 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -1,6 +1,6 @@ # World-Class Submission Review -Generated at: `2026-06-15` +Generated at: `2026-06-13` ## Summary @@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w #### Source Checks - External events: 0 / >0 => blocked -- Adoption sample: 0 / >0 => blocked +- Adoption sample: 1 / >0 => pass - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/schemas/adaptation-proposal.schema.json b/schemas/adaptation-proposal.schema.json new file mode 100644 index 00000000..4e6017d9 --- /dev/null +++ b/schemas/adaptation-proposal.schema.json @@ -0,0 +1,130 @@ +{ + "$schema": "https://json-schema.org/draft/2020-12/schema", + "$id": "https://yao.local/schemas/adaptation-proposal.schema.json", + "title": "Yao Adaptation Proposal Report", + "type": "object", + "required": [ + "schema_version", + "ok", + "generated_at", + "skill_dir", + "summary", + "proposal_contract", + "proposals", + "artifacts" + ], + "properties": { + "schema_version": { + "const": "1.0" + }, + "ok": { + "type": "boolean" + }, + "generated_at": { + "type": "string" + }, + "skill_dir": { + "type": "string" + }, + "summary": { + "type": "object", + "required": ["pattern_count", "proposal_count", "apply_supported"], + "properties": { + "pattern_count": { + "type": "integer", + "minimum": 0 + }, + "proposal_count": { + "type": "integer", + "minimum": 0 + }, + "apply_supported": { + "const": false + } + }, + "additionalProperties": true + }, + "proposal_contract": { + "type": "object", + "required": [ + "proposal_only", + "approval_required", + "writes_repository_files", + "allowlisted_targets_required", + "rollback_required_for_apply" + ], + "properties": { + "proposal_only": { + "const": true + }, + "approval_required": { + "const": true + }, + "writes_repository_files": { + "const": false + }, + "allowlisted_targets_required": { + "const": true + }, + "rollback_required_for_apply": { + "const": true + } + }, + "additionalProperties": true + }, + "proposals": { + "type": "array", + "items": { + "type": "object", + "required": [ + "proposal_id", + "status", + "requires_approval", + "write_allowed_without_approval", + "target_files", + "verification_commands", + "rollback_plan" + ], + "properties": { + "proposal_id": { + "type": "string", + "minLength": 1 + }, + "status": { + "const": "proposal-only" + }, + "requires_approval": { + "const": true + }, + "write_allowed_without_approval": { + "const": false + }, + "risk_level": { + "enum": ["low", "medium", "high"] + }, + "target_files": { + "type": "array", + "items": { + "type": "string" + } + }, + "verification_commands": { + "type": "array", + "items": { + "type": "string" + } + }, + "rollback_plan": { + "type": "string", + "minLength": 1 + } + }, + "additionalProperties": true + } + }, + "artifacts": { + "type": "object" + } + }, + "additionalProperties": true +} diff --git a/scripts/ci_test.py b/scripts/ci_test.py index c4aad45e..6ca8570d 100644 --- a/scripts/ci_test.py +++ b/scripts/ci_test.py @@ -63,6 +63,7 @@ DEFAULT_TARGETS = [ "world-class-claim-guard-check", "benchmark-reproducibility-check", "feedback-check", + "adaptation-safety-check", "adoption-drift-check", "telemetry-import-check", "telemetry-emit-check", diff --git a/scripts/propose_adaptation.py b/scripts/propose_adaptation.py new file mode 100644 index 00000000..b485df04 --- /dev/null +++ b/scripts/propose_adaptation.py @@ -0,0 +1,264 @@ +#!/usr/bin/env python3 +import argparse +import hashlib +import json +from datetime import datetime, timezone +from pathlib import Path +from typing import Any + + +ROOT = Path(__file__).resolve().parent.parent +SCRIPT_INTERFACE = "cli" +SCRIPT_INTERFACE_REASON = "Turns redacted repeated preference patterns into proposal-only adaptation plans." + +PROPOSAL_LIBRARY = { + "language_default": { + "title": "Keep reports Chinese-first with optional English", + "change_type": "report-default-language", + "risk_level": "low", + "target_files": ["scripts/render_skill_overview.py", "references/artifact-design-doctrine.md"], + "suggested_changes": [ + "Keep user-facing report copy Simplified Chinese by default.", + "Expose English through the existing language switch instead of mixing languages in the default view.", + ], + "verification_commands": ["python3 tests/verify_skill_overview.py"], + "rollback_plan": "Revert report language template changes and rerun the overview verifier.", + }, + "report_ui": { + "title": "Improve report layout, visual hierarchy, and chart readability", + "change_type": "artifact-ui-polish", + "risk_level": "medium", + "target_files": ["scripts/render_skill_overview.py", "references/artifact-design-doctrine.md", "tests/verify_skill_overview.py"], + "suggested_changes": [ + "Prefer vertical narrative sections with limited two-column layouts only when content has enough width.", + "Keep charts inline SVG, with captions and stable responsive constraints.", + ], + "verification_commands": ["python3 tests/verify_skill_overview.py", "python3 tests/verify_skill_report_charts.py"], + "rollback_plan": "Restore the previous report renderer and regenerate the demo report.", + }, + "approval_safety": { + "title": "Keep adaptive iteration approval-gated", + "change_type": "privacy-governance", + "risk_level": "low", + "target_files": ["references/user-memory-policy.md", "references/autonomous-adaptation.md", "schemas/adaptation-proposal.schema.json"], + "suggested_changes": [ + "Require explicit source paths for memory scans.", + "Generate proposals before any source patching.", + "Reserve automatic apply for a future approval ledger and rollback implementation.", + ], + "verification_commands": ["python3 tests/verify_adaptation_safety.py"], + "rollback_plan": "Remove the adaptive proposal artifacts and keep feedback/adoption drift as the only iteration inputs.", + }, + "delivery_format": { + "title": "Make generated artifact paths explicit in CLI output", + "change_type": "artifact-discoverability", + "risk_level": "low", + "target_files": ["scripts/yao.py", "README.md"], + "suggested_changes": [ + "Include stable report paths in command output.", + "Document which artifacts are meant for human review.", + ], + "verification_commands": ["python3 tests/verify_yao_cli.py"], + "rollback_plan": "Revert CLI copy/documentation changes and keep artifact paths unchanged.", + }, + "evidence_testing": { + "title": "Attach tests and evidence refresh to each upgrade", + "change_type": "quality-gate", + "risk_level": "medium", + "target_files": ["tests/verify_adaptation_safety.py", "scripts/render_skill_os2_coverage.py", "reports/skill_os2_coverage.json"], + "suggested_changes": [ + "Add focused verifier coverage for every new adaptive behavior.", + "Refresh Skill OS 2.0 coverage so planned, partial, and covered states remain visible.", + ], + "verification_commands": ["python3 tests/verify_adaptation_safety.py", "python3 tests/verify_skill_os2_coverage.py"], + "rollback_plan": "Revert the new verifier and coverage status updates, then regenerate coverage reports.", + }, +} + + +def utc_now() -> str: + return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z") + + +def display_path(path: Path, skill_dir: Path) -> str: + try: + return str(path.resolve().relative_to(skill_dir.resolve())) + except ValueError: + return str(path.resolve()) + + +def resolve_output(skill_dir: Path, value: str) -> Path: + path = Path(value) + return path if path.is_absolute() else skill_dir / path + + +def load_json(path: Path) -> dict[str, Any]: + if not path.exists(): + return {} + try: + payload = json.loads(path.read_text(encoding="utf-8")) + except json.JSONDecodeError: + return {} + return payload if isinstance(payload, dict) else {} + + +def proposal_id(pattern_id: str, support_count: int, target_files: list[str]) -> str: + digest = hashlib.sha1(f"{pattern_id}:{support_count}:{','.join(target_files)}".encode("utf-8")).hexdigest() + return f"adapt-{digest[:10]}" + + +def proposal_from_pattern(pattern: dict[str, Any]) -> dict[str, Any]: + pattern_id = str(pattern.get("pattern_id") or "generic") + spec = PROPOSAL_LIBRARY.get( + pattern_id, + { + "title": "Review repeated preference pattern", + "change_type": "manual-review", + "risk_level": "medium", + "target_files": ["README.md"], + "suggested_changes": ["Review this repeated signal manually before changing skill behavior."], + "verification_commands": ["make ci-test"], + "rollback_plan": "Revert the approved patch and rerun the relevant verifier.", + }, + ) + support_count = int(pattern.get("support_count") or 0) + target_files = list(spec["target_files"]) + return { + "proposal_id": proposal_id(pattern_id, support_count, target_files), + "pattern_id": pattern_id, + "title": spec["title"], + "change_type": spec["change_type"], + "status": "proposal-only", + "requires_approval": True, + "write_allowed_without_approval": False, + "risk_level": spec["risk_level"], + "reason": pattern.get("reason", "Repeated signal detected."), + "support_count": support_count, + "target_files": target_files, + "suggested_changes": spec["suggested_changes"], + "verification_commands": spec["verification_commands"], + "rollback_plan": spec["rollback_plan"], + "evidence_refs": [ + { + "record_id": item.get("record_id", "unknown"), + "excerpt": item.get("excerpt", ""), + } + for item in pattern.get("evidence", [])[:3] + if isinstance(item, dict) + ], + } + + +def build_report(skill_dir: Path, patterns_json: Path, generated_at: str) -> dict[str, Any]: + skill_dir = skill_dir.resolve() + if not patterns_json.is_absolute(): + patterns_json = skill_dir / patterns_json + patterns_payload = load_json(patterns_json) + failures: list[str] = [] + if not patterns_payload: + failures.append(f"Pattern report does not exist or is invalid: {display_path(patterns_json, skill_dir)}") + elif patterns_payload.get("ok") is not True: + failures.append("Pattern report is not ok; fix scan failures before proposal generation.") + patterns = patterns_payload.get("patterns", []) if isinstance(patterns_payload.get("patterns"), list) else [] + proposals = [proposal_from_pattern(pattern) for pattern in patterns if isinstance(pattern, dict)] if not failures else [] + return { + "schema_version": "1.0", + "ok": not failures, + "generated_at": generated_at, + "skill_dir": display_path(skill_dir, skill_dir), + "source_patterns": display_path(patterns_json, skill_dir), + "summary": { + "pattern_count": len(patterns), + "proposal_count": len(proposals), + "apply_supported": False, + "failure_count": len(failures), + }, + "proposal_contract": { + "proposal_only": True, + "approval_required": True, + "writes_repository_files": False, + "allowlisted_targets_required": True, + "rollback_required_for_apply": True, + "apply_command_available": False, + }, + "proposals": proposals, + "failures": failures, + "artifacts": { + "json": "reports/adaptation_proposals.json", + "markdown": "reports/adaptation_proposals.md", + }, + } + + +def render_markdown(report: dict[str, Any]) -> str: + lines = [ + "# Adaptation Proposals", + "", + f"- Generated at: `{report['generated_at']}`", + f"- Pattern report: `{report['source_patterns']}`", + f"- Proposal only: `{str(report['proposal_contract']['proposal_only']).lower()}`", + f"- Writes repository files: `{str(report['proposal_contract']['writes_repository_files']).lower()}`", + f"- Proposals: `{report['summary']['proposal_count']}`", + "", + ] + if not report["proposals"]: + lines.append("No proposals were generated.") + for proposal in report["proposals"]: + lines.extend( + [ + f"## {proposal['title']}", + "", + f"- ID: `{proposal['proposal_id']}`", + f"- Status: `{proposal['status']}`", + f"- Pattern: `{proposal['pattern_id']}`", + f"- Risk: `{proposal['risk_level']}`", + f"- Requires approval: `{str(proposal['requires_approval']).lower()}`", + f"- Reason: {proposal['reason']}", + "- Target files:", + ] + ) + lines.extend(f" - `{path}`" for path in proposal["target_files"]) + lines.append("- Suggested changes:") + lines.extend(f" - {item}" for item in proposal["suggested_changes"]) + lines.append("- Verification:") + lines.extend(f" - `{item}`" for item in proposal["verification_commands"]) + lines.append(f"- Rollback: {proposal['rollback_plan']}") + if proposal["evidence_refs"]: + lines.append("- Redacted evidence refs:") + lines.extend(f" - `{item['record_id']}`: {item['excerpt']}" for item in proposal["evidence_refs"]) + lines.append("") + if report["failures"]: + lines.extend(["## Failures", ""]) + lines.extend(f"- {failure}" for failure in report["failures"]) + return "\n".join(lines).rstrip() + "\n" + + +def main() -> None: + parser = argparse.ArgumentParser(description="Create proposal-only adaptation plans from summarized user signal patterns.") + parser.add_argument("skill_dir", nargs="?", default=".") + parser.add_argument("--patterns-json", default="reports/user_patterns.json") + parser.add_argument("--output-json", default="reports/adaptation_proposals.json") + parser.add_argument("--output-md", default="reports/adaptation_proposals.md") + parser.add_argument("--generated-at", default=utc_now()) + args = parser.parse_args() + + skill_dir = Path(args.skill_dir).resolve() + report = build_report(skill_dir, Path(args.patterns_json), args.generated_at) + if report["ok"]: + output_json = resolve_output(skill_dir, args.output_json) + output_md = resolve_output(skill_dir, args.output_md) + output_json.parent.mkdir(parents=True, exist_ok=True) + output_md.parent.mkdir(parents=True, exist_ok=True) + report["artifacts"] = { + "json": display_path(output_json, skill_dir), + "markdown": display_path(output_md, skill_dir), + } + output_json.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") + output_md.write_text(render_markdown(report), encoding="utf-8") + print(json.dumps(report, ensure_ascii=False, indent=2)) + if not report["ok"]: + raise SystemExit(2) + + +if __name__ == "__main__": + main() diff --git a/scripts/render_skill_os2_coverage.py b/scripts/render_skill_os2_coverage.py index 400d1fbb..efd4b037 100644 --- a/scripts/render_skill_os2_coverage.py +++ b/scripts/render_skill_os2_coverage.py @@ -50,6 +50,10 @@ def all_exist(items: list[dict[str, Any]]) -> bool: return all(item["exists"] for item in items) +def paths_exist(skill_dir: Path, paths: list[str]) -> bool: + return all((skill_dir / item).exists() for item in paths) + + def condition_status(condition: bool, evidence_items: list[dict[str, Any]]) -> str: if not all_exist(evidence_items): return "missing" @@ -316,28 +320,57 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]: next_action="Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests.", skill_dir=skill_dir, ), + ] + adaptive_foundation_paths = [ + "references/autonomous-adaptation.md", + "references/user-memory-policy.md", + "schemas/adaptation-proposal.schema.json", + "scripts/summarize_user_signals.py", + "scripts/propose_adaptation.py", + "tests/verify_adaptation_safety.py", + ] + adaptive_apply_paths = [ + "scripts/apply_adaptation.py", + "reports/adaptation_approval_ledger.json", + "reports/adaptation_regression_report.json", + ] + adaptive_foundation_ready = paths_exist(skill_dir, adaptive_foundation_paths) + adaptive_apply_ready = paths_exist(skill_dir, adaptive_apply_paths) + adaptive_status = "covered" if adaptive_foundation_ready and adaptive_apply_ready else ("partial" if adaptive_foundation_ready else "planned") + adaptive_current = ( + "Proposal-only adapt-scan/adapt-propose foundation exists with policy, schema, and safety tests; approval-gated patch application is not implemented yet." + if adaptive_status == "partial" + else ( + "Full adaptive loop includes proposal, approval, patch application, regression evidence, and rollback metadata." + if adaptive_status == "covered" + else "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy." + ) + ) + adaptive_next_action = ( + "Add adapt-apply only after approval ledger, allowlisted targets, dry-run diffs, regression reports, and rollback artifacts are designed." + if adaptive_status == "partial" + else "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path." + ) + extension_tracks.append( build_extension_track( key="adaptive-self-iteration", label="Adaptive Self-Iteration", - status="planned", + status=adaptive_status, objective="Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.", - current="The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.", + current=adaptive_current, target="Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.", artifact_paths=[ - "references/autonomous-adaptation.md", - "references/user-memory-policy.md", - "schemas/adaptation-proposal.schema.json", - "scripts/summarize_user_signals.py", - "scripts/propose_adaptation.py", - "scripts/apply_adaptation.py", - "tests/verify_adaptation_safety.py", + *adaptive_foundation_paths, + *adaptive_apply_paths, + "reports/user_patterns.json", + "reports/adaptation_proposals.json", "reports/iteration-directions.md", "reports/adoption_drift_report.md", ], - next_action="Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path.", + next_action=adaptive_next_action, skill_dir=skill_dir, - ), - ] + ) + ) extension_counts: dict[str, int] = {} for item in extension_tracks: extension_counts[item["status"]] = extension_counts.get(item["status"], 0) + 1 @@ -360,7 +393,7 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]: "extension_partial_count": extension_counts.get("partial", 0), "extension_planned_count": extension_counts.get("planned", 0), "extension_covered_count": extension_counts.get("covered", 0), - "adaptive_extension_ready": extension_counts.get("planned", 0) == 0, + "adaptive_extension_ready": adaptive_status == "covered", "local_blueprint_ready": local_ready, "public_world_class_ready": public_ready, "world_class_evidence_pending_count": pending_world_class, diff --git a/scripts/summarize_user_signals.py b/scripts/summarize_user_signals.py new file mode 100644 index 00000000..3ce15e4a --- /dev/null +++ b/scripts/summarize_user_signals.py @@ -0,0 +1,321 @@ +#!/usr/bin/env python3 +import argparse +import hashlib +import json +import re +from datetime import datetime, timezone +from pathlib import Path +from typing import Any + + +ROOT = Path(__file__).resolve().parent.parent +SCRIPT_INTERFACE = "cli" +SCRIPT_INTERFACE_REASON = "Scans an explicit local source file and summarizes redacted repeated user preference signals." + +TEXT_FIELDS = ("text", "message", "content", "excerpt", "prompt", "note", "body") +HISTORY_FILENAMES = {".zsh_history", ".bash_history", ".fish_history", "History"} +SECRET_PATTERNS = [ + re.compile(r"sk-[A-Za-z0-9_-]{12,}"), + re.compile(r"AKIA[0-9A-Z]{12,}"), + re.compile(r"(?i)\b(api[_-]?key|token|password|secret)\b\s*[:=]\s*[^\s,;]+"), +] +EMAIL_RE = re.compile(r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b") +LOCAL_PATH_RE = re.compile(r"/Users/[^\s'\"<>]+") + +PATTERN_RULES = [ + { + "pattern_id": "language_default", + "label": "Default language preference", + "signal_type": "report-language", + "keywords": ["中文", "简体", "默认中文", "英文", "双语", "language", "bilingual", "chinese", "english"], + "recommended_action": "Keep generated reports Chinese-first with an English switch where user-facing.", + }, + { + "pattern_id": "report_ui", + "label": "Report UI and visualization preference", + "signal_type": "artifact-design", + "keywords": ["报告", "html", "图表", "排版", "ui", "kami", "白底", "模块", "导航", "report", "chart", "layout"], + "recommended_action": "Prioritize white-background Kami-style reports with readable charts and stable navigation.", + }, + { + "pattern_id": "approval_safety", + "label": "Approval and privacy boundary", + "signal_type": "governance", + "keywords": ["审批", "授权", "不要扫描", "隐私", "私人", "日志", "明确路径", "回滚", "提案", "批准", "approval", "privacy", "private", "proposal", "rollback"], + "recommended_action": "Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path.", + }, + { + "pattern_id": "delivery_format", + "label": "Delivery format preference", + "signal_type": "artifact-format", + "keywords": ["markdown", "pdf", "word", "docx", "html", "地址", "路径", "打开", "输出", "交付"], + "recommended_action": "Surface stable artifact paths and formats in CLI output and generated summaries.", + }, + { + "pattern_id": "evidence_testing", + "label": "Evidence and testing preference", + "signal_type": "quality-gate", + "keywords": ["测试", "验证", "ci", "证据", "覆盖", "github", "push", "evidence", "review"], + "recommended_action": "Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade.", + }, +] + + +def utc_now() -> str: + return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z") + + +def display_path(path: Path, skill_dir: Path) -> str: + try: + return str(path.resolve().relative_to(skill_dir.resolve())) + except ValueError: + return f"[external-explicit-source]/{path.name}" + + +def resolve_output(skill_dir: Path, value: str) -> Path: + path = Path(value) + return path if path.is_absolute() else skill_dir / path + + +def source_fingerprint(path: Path) -> str: + digest = hashlib.sha256() + with path.open("rb") as handle: + for chunk in iter(lambda: handle.read(1024 * 1024), b""): + digest.update(chunk) + return digest.hexdigest() + + +def redact_text(text: str) -> str: + redacted = text + for pattern in SECRET_PATTERNS: + redacted = pattern.sub("[REDACTED_SECRET]", redacted) + redacted = EMAIL_RE.sub("[REDACTED_EMAIL]", redacted) + redacted = LOCAL_PATH_RE.sub("[LOCAL_PATH]", redacted) + redacted = re.sub(r"\s+", " ", redacted).strip() + if len(redacted) > 240: + return redacted[:237].rstrip() + "..." + return redacted + + +def extract_text(raw: Any) -> str: + if isinstance(raw, str): + return raw + if not isinstance(raw, dict): + return "" + for field in TEXT_FIELDS: + value = raw.get(field) + if isinstance(value, str) and value.strip(): + return value + messages = raw.get("messages") + if isinstance(messages, list): + parts = [] + for item in messages: + if isinstance(item, dict): + content = item.get("content") + if isinstance(content, str): + parts.append(content) + elif isinstance(item, str): + parts.append(item) + return "\n".join(parts) + return "" + + +def load_records(source: Path) -> tuple[list[dict[str, str]], list[str]]: + records: list[dict[str, str]] = [] + failures: list[str] = [] + text = source.read_text(encoding="utf-8", errors="replace") + if source.suffix.lower() == ".jsonl": + for index, line in enumerate(text.splitlines(), start=1): + if not line.strip(): + continue + try: + raw = json.loads(line) + except json.JSONDecodeError as exc: + failures.append(f"line {index}: invalid JSONL source: {exc.msg}") + continue + extracted = extract_text(raw) + if not extracted.strip(): + failures.append(f"line {index}: no supported text field found") + continue + records.append({"record_id": f"line-{index}", "excerpt": redact_text(extracted)}) + else: + for index, line in enumerate(text.splitlines(), start=1): + if line.strip(): + records.append({"record_id": f"line-{index}", "excerpt": redact_text(line)}) + return records, failures + + +def classify_patterns(records: list[dict[str, str]], min_support: int) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]: + patterns: list[dict[str, Any]] = [] + discarded: list[dict[str, Any]] = [] + for rule in PATTERN_RULES: + matches = [] + for record in records: + lowered = record["excerpt"].lower() + if any(keyword.lower() in lowered for keyword in rule["keywords"]): + matches.append(record) + if not matches: + continue + item = { + "pattern_id": rule["pattern_id"], + "label": rule["label"], + "signal_type": rule["signal_type"], + "support_count": len(matches), + "confidence": min(0.95, round(0.55 + (0.12 * len(matches)), 2)), + "reason": f"{len(matches)} redacted records matched repeated {rule['signal_type']} signals.", + "recommended_action": rule["recommended_action"], + "evidence": matches[:3], + } + if len(matches) >= min_support: + patterns.append(item) + else: + discarded.append({**item, "discard_reason": f"support_count below min_support {min_support}"}) + return patterns, discarded + + +def build_report( + skill_dir: Path, + source: Path, + min_support: int, + generated_at: str, + allow_history_source: bool, +) -> dict[str, Any]: + skill_dir = skill_dir.resolve() + source = source.resolve() + failures: list[str] = [] + records: list[dict[str, str]] = [] + fingerprint = "" + if not source.exists(): + failures.append(f"Explicit source does not exist: {display_path(source, skill_dir)}") + elif not source.is_file(): + failures.append(f"Explicit source must be a file: {display_path(source, skill_dir)}") + elif source.name in HISTORY_FILENAMES and not allow_history_source: + failures.append(f"Refusing private history source by default: {source.name}") + else: + fingerprint = source_fingerprint(source) + records, load_failures = load_records(source) + failures.extend(load_failures) + patterns, discarded = classify_patterns(records, min_support) if not failures else ([], []) + return { + "ok": not failures, + "schema_version": "1.0", + "generated_at": generated_at, + "skill_dir": display_path(skill_dir, skill_dir), + "source": { + "label": source.name, + "path": display_path(source, skill_dir), + "fingerprint_sha256": fingerprint, + "explicit_source": True, + "record_count": len(records), + }, + "privacy_contract": { + "local_only": True, + "explicit_source_required": True, + "implicit_private_log_scan": False, + "raw_content_stored": False, + "redacted_excerpts_only": True, + "redacted_excerpt_limit": 240, + "writes_repository_files": False, + }, + "summary": { + "record_count": len(records), + "pattern_count": len(patterns), + "discarded_signal_count": len(discarded), + "min_support": min_support, + "failure_count": len(failures), + }, + "patterns": patterns, + "discarded_signals": discarded, + "failures": failures, + "artifacts": { + "json": "reports/user_patterns.json", + "markdown": "reports/user_patterns.md", + }, + } + + +def render_markdown(report: dict[str, Any]) -> str: + lines = [ + "# User Pattern Summary", + "", + f"- Generated at: `{report['generated_at']}`", + f"- Local only: `{str(report['privacy_contract']['local_only']).lower()}`", + f"- Explicit source: `{report['source']['path']}`", + f"- Records: `{report['summary']['record_count']}`", + f"- Patterns: `{report['summary']['pattern_count']}`", + f"- Discarded signals: `{report['summary']['discarded_signal_count']}`", + "", + "## Privacy Contract", + "", + "- No implicit private log scan.", + "- No unredacted raw content stored.", + "- Scan and proposal stages do not write source files.", + "", + "## Patterns", + "", + ] + if not report["patterns"]: + lines.append("- No repeated pattern met the support threshold.") + for pattern in report["patterns"]: + lines.extend( + [ + f"### {pattern['label']}", + "", + f"- Pattern: `{pattern['pattern_id']}`", + f"- Support: `{pattern['support_count']}`", + f"- Confidence: `{pattern['confidence']}`", + f"- Reason: {pattern['reason']}", + f"- Recommended action: {pattern['recommended_action']}", + "- Redacted evidence:", + ] + ) + for item in pattern["evidence"]: + lines.append(f" - `{item['record_id']}`: {item['excerpt']}") + lines.append("") + if report["discarded_signals"]: + lines.extend(["## Discarded Signals", ""]) + for item in report["discarded_signals"]: + lines.append(f"- `{item['pattern_id']}`: {item['discard_reason']}") + if report["failures"]: + lines.extend(["", "## Failures", ""]) + lines.extend(f"- {failure}" for failure in report["failures"]) + return "\n".join(lines).rstrip() + "\n" + + +def main() -> None: + parser = argparse.ArgumentParser(description="Summarize repeated user preference signals from one explicit local source file.") + parser.add_argument("skill_dir", nargs="?", default=".") + parser.add_argument("--source", required=True) + parser.add_argument("--output-json", default="reports/user_patterns.json") + parser.add_argument("--output-md", default="reports/user_patterns.md") + parser.add_argument("--min-support", type=int, default=2) + parser.add_argument("--generated-at", default=utc_now()) + parser.add_argument("--allow-history-source", action="store_true") + args = parser.parse_args() + + skill_dir = Path(args.skill_dir).resolve() + report = build_report( + skill_dir, + Path(args.source), + min_support=max(2, args.min_support), + generated_at=args.generated_at, + allow_history_source=args.allow_history_source, + ) + if report["ok"]: + output_json = resolve_output(skill_dir, args.output_json) + output_md = resolve_output(skill_dir, args.output_md) + output_json.parent.mkdir(parents=True, exist_ok=True) + output_md.parent.mkdir(parents=True, exist_ok=True) + report["artifacts"] = { + "json": display_path(output_json, skill_dir), + "markdown": display_path(output_md, skill_dir), + } + output_json.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") + output_md.write_text(render_markdown(report), encoding="utf-8") + print(json.dumps(report, ensure_ascii=False, indent=2)) + if not report["ok"]: + raise SystemExit(2) + + +if __name__ == "__main__": + main() diff --git a/scripts/yao.py b/scripts/yao.py index dd0585a4..d9cb550d 100644 --- a/scripts/yao.py +++ b/scripts/yao.py @@ -11,6 +11,7 @@ from yao_cli_config import ( resolve_promotion_target, resolve_target, ) +from yao_cli_adaptation_commands import command_adapt_propose, command_adapt_scan from yao_cli_create_commands import command_init, command_quickstart from yao_cli_parser import build_parser as build_cli_parser from yao_cli_report_commands import ( diff --git a/scripts/yao_cli_adaptation_commands.py b/scripts/yao_cli_adaptation_commands.py new file mode 100644 index 00000000..7d830954 --- /dev/null +++ b/scripts/yao_cli_adaptation_commands.py @@ -0,0 +1,45 @@ +"""Adaptive proposal command handlers for the Yao CLI.""" + +import argparse +import json +from pathlib import Path + +from yao_cli_runtime import run_script + + +SCRIPT_INTERFACE = "internal-module" +SCRIPT_INTERFACE_REASON = "Imported by yao.py to keep adaptive scan/proposal command handlers outside the thin CLI orchestrator." + + +def command_adapt_scan(args: argparse.Namespace) -> int: + skill_dir = str(Path(args.skill_dir).resolve()) + cmd = [skill_dir, "--source", args.source] + if args.output_json: + cmd.extend(["--output-json", args.output_json]) + if args.output_md: + cmd.extend(["--output-md", args.output_md]) + if args.min_support is not None: + cmd.extend(["--min-support", str(args.min_support)]) + if args.generated_at: + cmd.extend(["--generated-at", args.generated_at]) + if args.allow_history_source: + cmd.append("--allow-history-source") + result = run_script("summarize_user_signals.py", cmd) + print(json.dumps(result["payload"] if result["payload"] is not None else result, ensure_ascii=False, indent=2)) + return 0 if result["ok"] else 2 + + +def command_adapt_propose(args: argparse.Namespace) -> int: + skill_dir = str(Path(args.skill_dir).resolve()) + cmd = [skill_dir] + if args.patterns_json: + cmd.extend(["--patterns-json", args.patterns_json]) + if args.output_json: + cmd.extend(["--output-json", args.output_json]) + if args.output_md: + cmd.extend(["--output-md", args.output_md]) + if args.generated_at: + cmd.extend(["--generated-at", args.generated_at]) + result = run_script("propose_adaptation.py", cmd) + print(json.dumps(result["payload"] if result["payload"] is not None else result, ensure_ascii=False, indent=2)) + return 0 if result["ok"] else 2 diff --git a/scripts/yao_cli_parser.py b/scripts/yao_cli_parser.py index 80830387..fb9a4174 100644 --- a/scripts/yao_cli_parser.py +++ b/scripts/yao_cli_parser.py @@ -373,6 +373,30 @@ def build_parser(command_handlers: dict[str, Callable[[argparse.Namespace], int] feedback_cmd.add_argument("--recommended-action", default="review") feedback_cmd.set_defaults(func=_handler(command_handlers, "command_feedback")) + adapt_scan_cmd = subparsers.add_parser( + "adapt-scan", + help="Scan one explicit local source file for redacted repeated user preference signals.", + ) + adapt_scan_cmd.add_argument("skill_dir", nargs="?", default=".") + adapt_scan_cmd.add_argument("--source", required=True) + adapt_scan_cmd.add_argument("--output-json") + adapt_scan_cmd.add_argument("--output-md") + adapt_scan_cmd.add_argument("--min-support", type=int, default=2) + adapt_scan_cmd.add_argument("--generated-at") + adapt_scan_cmd.add_argument("--allow-history-source", action="store_true") + adapt_scan_cmd.set_defaults(func=_handler(command_handlers, "command_adapt_scan")) + + adapt_propose_cmd = subparsers.add_parser( + "adapt-propose", + help="Create proposal-only adaptation plans from redacted repeated preference patterns.", + ) + adapt_propose_cmd.add_argument("skill_dir", nargs="?", default=".") + adapt_propose_cmd.add_argument("--patterns-json") + adapt_propose_cmd.add_argument("--output-json") + adapt_propose_cmd.add_argument("--output-md") + adapt_propose_cmd.add_argument("--generated-at") + adapt_propose_cmd.set_defaults(func=_handler(command_handlers, "command_adapt_propose")) + adoption_drift_cmd = subparsers.add_parser( "adoption-drift", help="Render local-first metadata-only adoption and drift telemetry for a skill package.", diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index 37fc649c..9c557e08 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -77,6 +77,7 @@ "references": [ "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -106,7 +107,8 @@ "references/skill-ir-method.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", - "references/trust-security-method.md" + "references/trust-security-method.md", + "references/user-memory-policy.md" ], "scripts": [ "scripts/adjudicate_output_review.py", @@ -135,6 +137,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -187,8 +190,7 @@ "scripts/run_description_optimization_suite.py", "scripts/run_eval_suite.py", "scripts/run_output_eval.py", - "scripts/run_output_execution.py", - "scripts/simulate_install.py" + "scripts/run_output_execution.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -243,6 +245,7 @@ "eval_plan": { "trigger": [ "evals/README.md", + "evals/adaptation/user_signals.example.jsonl", "evals/adversarial/trigger_cases.json", "evals/blind_holdout/trigger_cases.json", "evals/confusion/route_cases.json", diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 50d09246..81283388 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -46,6 +46,7 @@ "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", + "scripts/propose_adaptation.py", "scripts/provider_output_eval_runner.py", "scripts/python_compat_check.py", "scripts/registry_audit.py", @@ -106,6 +107,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/skill_report_world_class.py", + "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", "scripts/trigger_eval.py", @@ -116,6 +118,7 @@ "scripts/world_class_evidence_contract.py", "scripts/world_class_source_checks.py", "scripts/yao.py", + "scripts/yao_cli_adaptation_commands.py", "scripts/yao_cli_config.py", "scripts/yao_cli_create_commands.py", "scripts/yao_cli_parser.py", @@ -124,6 +127,7 @@ "scripts/yao_cli_telemetry.py", "references/artifact-design-doctrine.md", "references/authoring-discipline.md", + "references/autonomous-adaptation.md", "references/distribution-registry-method.md", "references/eval-playbook.md", "references/gate-selection.md", @@ -154,6 +158,7 @@ "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", "references/trust-security-method.md", + "references/user-memory-policy.md", "templates/basic_skill.md.j2", "templates/complex_skill.md.j2" ], diff --git a/tests/verify_adaptation_safety.py b/tests/verify_adaptation_safety.py new file mode 100644 index 00000000..233299b7 --- /dev/null +++ b/tests/verify_adaptation_safety.py @@ -0,0 +1,157 @@ +#!/usr/bin/env python3 +import json +import shutil +import subprocess +import sys +from pathlib import Path + + +ROOT = Path(__file__).resolve().parent.parent +CLI = ROOT / "scripts" / "yao.py" +SCAN_SCRIPT = ROOT / "scripts" / "summarize_user_signals.py" +PROPOSE_SCRIPT = ROOT / "scripts" / "propose_adaptation.py" +TMP = ROOT / "tests" / "tmp_adaptation_safety" + + +def run_script(*args: str) -> subprocess.CompletedProcess[str]: + return subprocess.run( + [sys.executable, *args], + cwd=ROOT, + capture_output=True, + text=True, + ) + + +def main() -> None: + shutil.rmtree(TMP, ignore_errors=True) + skill_dir = TMP / "adaptive-demo-skill" + reports_dir = skill_dir / "reports" + reports_dir.mkdir(parents=True, exist_ok=True) + source = TMP / "curated-user-signals.jsonl" + source.write_text( + "\n".join( + [ + json.dumps({"text": "报告默认中文简体，同时右上角提供英文切换。"}, ensure_ascii=False), + json.dumps({"message": "新的 HTML 报告要双语，但默认中文简体。"}, ensure_ascii=False), + json.dumps({"content": "报告 UI 需要 Kami 白底排版、图表模块和清晰导航。"}, ensure_ascii=False), + json.dumps({"excerpt": "HTML 报告还是白底 Kami 风格，图表不要挤在一起。"}, ensure_ascii=False), + json.dumps({"note": "不要自动扫描私人日志；必须由用户提供明确路径。"}, ensure_ascii=False), + json.dumps({"body": "自适应升级需要先输出提案，授权后再修改，并能回滚。"}, ensure_ascii=False), + json.dumps({"text": "隐私证据里也要保护 token=abc123456789、sk-1234567890abcdef 和 /Users/laoyao/private/path。"}, ensure_ascii=False), + json.dumps({"text": "PDF 只提过一次，不能当作稳定偏好。"}, ensure_ascii=False), + ] + ) + + "\n", + encoding="utf-8", + ) + + scan_proc = run_script( + str(SCAN_SCRIPT), + str(skill_dir), + "--source", + str(source), + "--generated-at", + "2026-06-15T00:00:00Z", + ) + assert scan_proc.returncode == 0, scan_proc.stderr + scan_payload = json.loads(scan_proc.stdout) + assert scan_payload["ok"], scan_payload + assert scan_payload["privacy_contract"]["local_only"] is True, scan_payload + assert scan_payload["privacy_contract"]["implicit_private_log_scan"] is False, scan_payload + assert scan_payload["privacy_contract"]["raw_content_stored"] is False, scan_payload + assert scan_payload["privacy_contract"]["writes_repository_files"] is False, scan_payload + assert scan_payload["source"]["path"].startswith("[external-explicit-source]/"), scan_payload + pattern_ids = {item["pattern_id"] for item in scan_payload["patterns"]} + assert {"language_default", "report_ui", "approval_safety"} <= pattern_ids, scan_payload + serialized = json.dumps(scan_payload, ensure_ascii=False) + assert "sk-1234567890abcdef" not in serialized, serialized + assert "token=abc123456789" not in serialized, serialized + assert "/Users/laoyao/private" not in serialized, serialized + assert "[REDACTED_SECRET]" in serialized, serialized + assert "[LOCAL_PATH]" in serialized, serialized + assert (reports_dir / "user_patterns.json").exists(), reports_dir + assert (reports_dir / "user_patterns.md").exists(), reports_dir + + propose_proc = run_script( + str(PROPOSE_SCRIPT), + str(skill_dir), + "--generated-at", + "2026-06-15T00:00:00Z", + ) + assert propose_proc.returncode == 0, propose_proc.stderr + proposal_payload = json.loads(propose_proc.stdout) + assert proposal_payload["ok"], proposal_payload + assert proposal_payload["summary"]["apply_supported"] is False, proposal_payload + assert proposal_payload["proposal_contract"]["proposal_only"] is True, proposal_payload + assert proposal_payload["proposal_contract"]["writes_repository_files"] is False, proposal_payload + assert proposal_payload["summary"]["proposal_count"] >= 3, proposal_payload + assert all(item["status"] == "proposal-only" for item in proposal_payload["proposals"]), proposal_payload + assert all(item["requires_approval"] is True for item in proposal_payload["proposals"]), proposal_payload + assert all(item["write_allowed_without_approval"] is False for item in proposal_payload["proposals"]), proposal_payload + assert any( + any("tests/verify_adaptation_safety.py" in command for command in item["verification_commands"]) + for item in proposal_payload["proposals"] + ), proposal_payload + assert not (skill_dir / "scripts" / "apply_adaptation.py").exists(), skill_dir + assert (reports_dir / "adaptation_proposals.json").exists(), reports_dir + assert (reports_dir / "adaptation_proposals.md").exists(), reports_dir + + missing_source_proc = run_script(str(SCAN_SCRIPT), str(skill_dir)) + assert missing_source_proc.returncode != 0, missing_source_proc + + history_source = TMP / ".zsh_history" + history_source.write_text("报告默认中文\n报告默认中文\n", encoding="utf-8") + history_proc = run_script(str(SCAN_SCRIPT), str(skill_dir), "--source", str(history_source)) + assert history_proc.returncode == 2, history_proc.stdout + history_payload = json.loads(history_proc.stdout) + assert history_payload["ok"] is False, history_payload + assert any("Refusing private history source" in item for item in history_payload["failures"]), history_payload + + cli_skill_dir = TMP / "cli-adaptive-demo-skill" + cli_skill_dir.mkdir(parents=True, exist_ok=True) + cli_source = TMP / "cli-user-signals.jsonl" + cli_source.write_text( + "\n".join( + [ + json.dumps({"text": "报告默认中文简体，同时提供英文切换。"}, ensure_ascii=False), + json.dumps({"text": "新的 HTML 报告还是默认中文简体，并保留英文版。"}, ensure_ascii=False), + json.dumps({"text": "报告 UI 要保持 Kami 白底排版和图表模块。"}, ensure_ascii=False), + json.dumps({"text": "HTML 报告的图表和白底 Kami 排版都要清晰。"}, ensure_ascii=False), + json.dumps({"text": "自适应升级必须先生成提案，授权后再修改。"}, ensure_ascii=False), + json.dumps({"text": "不要默认扫描私人日志，要由用户提供明确路径。"}, ensure_ascii=False), + ] + ) + + "\n", + encoding="utf-8", + ) + cli_scan = run_script( + str(CLI), + "adapt-scan", + str(cli_skill_dir), + "--source", + str(cli_source), + "--generated-at", + "2026-06-15T00:00:00Z", + ) + assert cli_scan.returncode == 0, cli_scan.stderr + cli_scan_payload = json.loads(cli_scan.stdout) + assert cli_scan_payload["summary"]["pattern_count"] >= 3, cli_scan_payload + assert cli_scan_payload["privacy_contract"]["writes_repository_files"] is False, cli_scan_payload + assert (cli_skill_dir / "reports" / "user_patterns.json").exists(), cli_skill_dir + cli_propose = run_script( + str(CLI), + "adapt-propose", + str(cli_skill_dir), + "--generated-at", + "2026-06-15T00:00:00Z", + ) + assert cli_propose.returncode == 0, cli_propose.stderr + cli_proposal_payload = json.loads(cli_propose.stdout) + assert cli_proposal_payload["summary"]["proposal_count"] >= 3, cli_proposal_payload + assert cli_proposal_payload["proposal_contract"]["proposal_only"] is True, cli_proposal_payload + assert cli_proposal_payload["proposal_contract"]["writes_repository_files"] is False, cli_proposal_payload + print(json.dumps({"ok": True}, ensure_ascii=False, indent=2)) + + +if __name__ == "__main__": + main() diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py index a7f0a442..4735bb30 100644 --- a/tests/verify_review_studio.py +++ b/tests/verify_review_studio.py @@ -538,13 +538,15 @@ def main() -> None: assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"] assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_track_count"] == 2, full_payload["data"]["skill_os2_coverage"] - assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_planned_count"] == 1, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_partial_count"] == 2, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_planned_count"] == 0, full_payload["data"]["skill_os2_coverage"] + assert full_payload["data"]["skill_os2_coverage"]["summary"]["adaptive_extension_ready"] is False, full_payload["data"]["skill_os2_coverage"] extension_tracks = { item["key"]: item for item in full_payload["data"]["skill_os2_coverage"]["reference_extension_tracks"] } assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks - assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks + assert extension_tracks["adaptive-self-iteration"]["status"] == "partial", extension_tracks world_class_entries = full_payload["data"]["world_class_evidence_ledger"]["entries"] assert len(world_class_entries) == 4, world_class_entries assert {item["key"] for item in world_class_entries} == { @@ -654,7 +656,9 @@ def main() -> None: assert "蓝图覆盖" in html, html assert "Extension Track Count" in html, html assert "Adaptive Extension Ready" in html, html - assert "extensions partial 1, planned 1" in html, html + assert "
Extension Partial Count
2
" in html, html + assert "
Extension Planned Count
0
" in html, html + assert "Adaptive Extension Ready" in html, html assert "本地蓝图" in html, html assert "public world-class 仍以 world-class evidence ledger" in html, html assert "公开声明" in html, html diff --git a/tests/verify_skill_os2_coverage.py b/tests/verify_skill_os2_coverage.py index 14883c28..961803dc 100644 --- a/tests/verify_skill_os2_coverage.py +++ b/tests/verify_skill_os2_coverage.py @@ -45,8 +45,8 @@ def main() -> None: assert summary["warn_count"] == 0, summary assert summary["missing_count"] == 0, summary assert summary["extension_track_count"] == 2, summary - assert summary["extension_partial_count"] == 1, summary - assert summary["extension_planned_count"] == 1, summary + assert summary["extension_partial_count"] == 2, summary + assert summary["extension_planned_count"] == 0, summary assert summary["adaptive_extension_ready"] is False, summary assert summary["local_blueprint_ready"] is True, summary assert summary["public_world_class_ready"] is False, summary @@ -88,13 +88,17 @@ def main() -> None: assert payload["source_blueprint"]["reference_extension_count"] == 2, payload extension_tracks = {item["key"]: item for item in payload["reference_extension_tracks"]} assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks - assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks + assert extension_tracks["adaptive-self-iteration"]["status"] == "partial", extension_tracks assert any( entry["path"] == "reports/skill-overview.html" and entry["exists"] for entry in extension_tracks["skill-interpretation-report"]["evidence"] ), extension_tracks["skill-interpretation-report"] assert any( - entry["path"] == "scripts/summarize_user_signals.py" and not entry["exists"] + entry["path"] == "scripts/summarize_user_signals.py" and entry["exists"] + for entry in extension_tracks["adaptive-self-iteration"]["evidence"] + ), extension_tracks["adaptive-self-iteration"] + assert any( + entry["path"] == "scripts/apply_adaptation.py" and not entry["exists"] for entry in extension_tracks["adaptive-self-iteration"]["evidence"] ), extension_tracks["adaptive-self-iteration"] assert "Close the four world-class evidence ledger entries" in payload["next_highest_leverage"][0], payload diff --git a/tests/verify_yao_cli.py b/tests/verify_yao_cli.py index cd238423..820ff9fe 100644 --- a/tests/verify_yao_cli.py +++ b/tests/verify_yao_cli.py @@ -11,6 +11,7 @@ CLI = ROOT / "scripts" / "yao.py" BENCHMARK_FIXTURE_DIR = ROOT / "tests" / "fixtures" / "github_benchmark_scan" sys.path.insert(0, str(ROOT / "scripts")) import yao as yao_cli_module # noqa: E402 +import yao_cli_adaptation_commands # noqa: E402 import yao_cli_config # noqa: E402 import yao_cli_parser # noqa: E402 import yao_cli_report_commands # noqa: E402 @@ -73,6 +74,7 @@ def main() -> None: assert "--allow-custom-base-url" in yao_cli_config.provider_output_runner_command("openai", allow_custom_base_url=True) assert yao_cli_parser.SCRIPT_INTERFACE == "internal-module" assert yao_cli_runtime.SCRIPT_INTERFACE == "internal-module" + assert yao_cli_adaptation_commands.SCRIPT_INTERFACE == "internal-module" assert yao_cli_report_commands.SCRIPT_INTERFACE == "internal-module" assert callable(yao_cli_module.command_review_studio) parser_help = yao_cli_module.build_parser().format_help() @@ -80,7 +82,8 @@ def main() -> None: "quickstart review-studio python-compat architecture-audit skill-os2-audit skill-os2-coverage " "world-class-evidence world-class-ledger world-class-intake world-class-submission-kit " "world-class-submission-review world-class-runbook world-class-claim-guard " - "benchmark-reproducibility output-review-kit telemetry-import telemetry-emit telemetry-hooks --record-cli-telemetry" + "benchmark-reproducibility output-review-kit adapt-scan adapt-propose " + "telemetry-import telemetry-emit telemetry-hooks --record-cli-telemetry" ).split() assert all(item in parser_help for item in expected_help), parser_help @@ -211,7 +214,7 @@ def main() -> None: assert architecture_result["ok"], architecture_result assert architecture_result["payload"]["summary"]["hotspot_count"] == 0, architecture_result assert architecture_result["payload"]["summary"]["blocker_count"] == 0, architecture_result - assert 30 <= architecture_result["payload"]["summary"]["command_handler_count"] < 50, architecture_result + assert 30 <= architecture_result["payload"]["summary"]["command_handler_count"] < 55, architecture_result world_class_evidence_result = run( "world-class-evidence",
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder