mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
ao-pre-reduction@5b334a13f
19 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
efc2609682 |
docs(architecture): formalize the L0-L4 autonomy ladder (ag-wrom #autonomy-ladder) (#787)
## What Closes the partial in Google-SRE convergence **point #8** (`ag-wrom`): AgentOps already ran work at several autonomy levels (human-in-loop in-session → substrate dispatch → bounded `autodev`) but the progression was *implicit* — nothing named the rungs, stated what each may mutate, or defined the evidence that earns a promotion. Implicit autonomy is how a probabilistic agent quietly acquires more authority than its track record justifies. Adds `docs/architecture/autonomy-ladder.md`: - **The invariant every rung obeys** — non-deterministic reasoning core wrapped by a deterministic enforcement boundary (CI gates + ports-and-adapters + ratchet) the agent can't bypass. The ladder moves the *leash*, never relaxes the *boundary*. L4 code passes the same CI as L0 code. - **L0–L4 rungs** mapped to AgentOps' real dispatch vocabulary, with human posture / acts-before-review / may-merge per rung. - **Promotion gates** — per-lane, revocable, gated on statistically-significant success vs Golden data at the Bronze/Silver/Gold tier. - **Demotion** — auto-downgrade on risk (the L3→L2 analog of Google's de-escalation) + the unconditional Red Button. - **Hard ceilings** — no rung confers authority over external/secrets/schema/deletion/strategic-fork/merge-beyond-contract; those stay draft-and-queue at every level. - Honest divergence stated: AgentOps autonomy is **build-time** (code + `.agents/` corpus), not run-time production ops — which is why L4 is delegated to a substrate, not shipped (ADR-0009). Wires it into the architecture index card grid + `mkdocs.yml` nav, and flips convergence point #8 from ⚠️ partial to ✅ encoded (tally 9/1/1). ## Evidence Closes-scenario: ag-wrom#autonomy-ladder Bounded-context: BC1-Corpus Evidence: markdownlint-cli2 PASS on all 3 changed docs; all cross-links verified to resolve (operating-loop, canonical-loop-model, fungibility-charter, google-sre, ADR-0009 in-docs relative; CLAUDE.md + skills/autodev as GitHub URLs per repo convention for out-of-docs targets); new page registered in mkdocs nav for `mkdocs build --strict`. |
||
|
|
cfee2b078a |
docs(convergence): first-class Convergence section — The Reading + Ledger + Google SRE map (ag-4hf7 #google-sre-convergence) (#650)
## What Establishes a first-class **`docs/convergence/`** section: the record of the industry independently arriving at the structure AgentOps already runs — kept distinct from the competitor map. Three surfaces: 1. **`the-reading.md`** — the *living thesis*. The argument (with mechanism, firm-vs-forming consensus table, honest moat-risk, and a "how to read a new signal" rubric) that the industry is converging and **why**. 2. **`ledger.md`** — the dated *receipts* table (who/when/which invariant). Seeded with Google SRE 2026. 3. **`google-sre.md`** — the per-party *encoding map*: 11 convergence points → real AgentOps loci (8 encoded · 2 partial · 1 gap). 4. **`index.md`** — section hub framing the three. ## Why first-class, not under comparisons/ A vindication record is the *inverse* of a competitor grid — wrong to parent it under "vs the competition." Radar = competitors in our lane; Convergence = independents arriving from outside it. Promoted to its own top-level nav section (`git mv`, history preserved; permalinks updated; cross-links rewired both ways). ## Gaps surfaced (filed as beads) | Bead | Point | Work | |---|---|---| | `ag-fjbu` | #3 | Adopt Bronze/Silver/Gold eval-tiering + True-vs-Observed-Precision naming | | `ag-wrom` | #8 | Formalize an L0–L4-style autonomy ladder for AgentOps dispatch | | `ag-7278` | #11 | Council: does coherent-arc need a fix-forward escape hatch? (Google is ahead) | ## Verification - All relative links across the convergence section + comparisons pointers resolve. - mkdocs nav + documentation-index updated; renames preserve history. Closes-scenario: ag-4hf7#google-sre-convergence Bounded-context: BC1-Corpus Evidence: docs/convergence/the-reading.md |
||
|
|
f4a91f97a6 |
docs(fungibility): AgentOps 3.0 Fungibility Charter — 6 commitments (soc-vuu6.29 #fungibility-charter) (#644)
Codifies the AgentOps 3.0 fungibility doctrine — implicit in the primitives but contradicted by 2.x surfaces — into a single charter at `docs/architecture/fungibility-charter.md`. ## The six commitments 1. **Default RPI mode is single-model** — the session's model runs every phase; multi-model is opt-in. 2. **Any agent can claim any bead** — no role gating; `bd ready`/`--claim` already enforce this. 3. **Stateless agent assumption** — agents are interchangeable consumers of the `.agents/` corpus; no agent owns a domain or carries irreplaceable state. 4. **Universal init prompt is standard** — every spawn runs `ao session bootstrap` (shipped, vuu6.25). 5. **Death is normal; recovery is automatic** — `ao beads stale-claims` + `ao beads resume` (shipped) make dead-agent recovery operational. 6. **Specialization is opt-in** — `--mixed`/`--pool=N`/`--diverse`/`--codex` exist but are never the default. Each commitment names the shipped primitive that implements it, so the doctrine is honest (the risk-gate from the bead: do not land doctrine ahead of primitives — vuu6.25 closed, the stale-claims primitive lives in `cli/cmd/ao/beads_stale.go`/`beads_resume.go` on main). ## Cross-references / discoverability - `docs/architecture/operating-loop.md` — See also (acceptance: charter referenced from the spine) - `docs/architecture/index.md` — card - `docs/documentation-index.md` — catalogue line - `mkdocs.yml` — added to nav under Architecture Docs-only, no code, scope-only diff (5 files, +105 / -0). README/PRODUCT.md positioning rewrite is out of scope here (separate slice soc-vuu6.30 + the CI citation gate); this PR lands the charter artifact itself. Closes-scenario: soc-vuu6.29#fungibility-charter Bounded-context: BC5-Runtime Evidence: docs/architecture/fungibility-charter.md |
||
|
|
dde214825b |
docs(3.0): ag-p7j W1 — delete daemon contracts, regen generated docs, reframe skills (ag-p7j) (#529)
W1 (structural) of the 3-way ag-p7j doc-sweep. Owns shared/generated/structural artifacts + skills + contracts. Disjoint from W2 (#527, core narrative) and W3 (#528, peripheral docs), both already merged; this branch is rebased on top of them. ## Deleted (deleted-surface docs) - `docs/contracts/{agentops-daemon,ao-watch,daemon-idempotency,dream-run-contract,agent-worker,ao-outcomes,openclaw-consumer-api,gascity-integration}.md` - `docs/code-map/agentopsd-codebase-map.md` - `gascity-integration.md` deleted because it described the OLD daemon↔GasCity adapter (`ao daemon run --executor-policy=gascity`, daemon ledger, OpenClaw consumer endpoints). The current GC story is the using-gc skill + the reference City. - Removed every deleted doc's row from `docs/documentation-index.md`, `docs/contracts/index.md`, and `mkdocs.yml` nav. ## Regenerated (generators, not hand-edited) - `docs/cli-surface.{md,json}` via `check-cmdao-surface-parity.sh --write-surface` — daemon/schedule/overnight/plans/watch/factory rows gone (live `ao` binary no longer registers them; the docs were stale). - `registry.json`, `skills/catalog.json`, SKU catalog, codex `.agentops-generated.json` hashes + manifest. - Skill counts verified in sync (81 skills). ## Reframed to in-session / GC / hookless - Skills: `dream` (+codex twin, neutralized literal `agentopsd`/`ao schedule`/`ao overnight`/`ao watch`/`ao plans` while keeping the retirement message), `compile` (+codex), `scaffold/recommended-reading` (+codex), `discovery/best-practices`, `validation/best-practices`. - Generated narrative: `docs/SKILLS.md` /dream block, `docs/ARCHITECTURE.md` dream paragraph, `skills/SKILL-TIERS.md` dream row. - Contracts prose: `docs/contracts/ubiquitous-language.md`, `docs/contracts/agents-write-surfaces.md` (kept catalog rows for surviving load-bearing-lane subdirs; dropped deleted-command references in descriptions). ## 3.0.md:150 Restored the strong claim: "...gone from the CLI **and from live doc prose** (only historical surfaces — ADRs, the CHANGELOG, release notes, and the 3.0 migration record — still name them, by design)"; kept the `validate-sku-catalog-drift` linkage-gate mention. ## Collateral (minimal dead-link repairs to my deleted targets) - `docs/daemon-migration.md` (gascity-integration link → dependencies.md), `cli/README.md` (dropped dream-run-contract link). The comparisons-file dead link was resolved by W3's merge. ## Gates (all green locally) doc-release (2765 links, 0 broken) · contract-compatibility (0 failures) · structural-floor · agents-write-surfaces · registry --check · validate-sku-catalog-drift · validate-ci-policy-parity · validate-skill-cli-snippets · validate-codex-runtime-sections · codex parity (5 skills) + regen-codex-hashes --check · skill-catalog drift · cli-skills-map · markdownlint (changed files) · mkdocs --strict · `cd cli && go build ./...` Closes-scenario: ag-p7j#w1-structural Bounded-context: BC1-Corpus Evidence: docs/3.0.md |
||
|
|
46ed7fee5a |
docs(3.0): sweep remaining daemon/schedule/hook prose + MIGRATION-3.0 (ag-qbw) (#520)
## What
Wave 2 of the AgentOps 3.0 honest-docs sweep (post-#518 audit, bead
ag-qbw). Makes the `docs/` prose match the shipped code: the daemon,
scheduler, factory, and all hooks were **DELETED** (not deprecated).
AgentOps is the in-session loop + context compiler; out-of-session
orchestration is delegated to a substrate (Gas City reference City /
Olympus). Mirrors the already-correct `docs/3.0.md`.
This makes `docs/3.0.md:150` ("the standalone
daemon/scheduler/overnight-runner surfaces are gone from ... live doc
prose") true for the enumerated wave-2 surfaces.
## Deleted (whole docs about deleted commands)
- `docs/scheduling.md` — entire `ao schedule` + `ao daemon` guide
-
`docs/contracts/{agentopsd-control-plane,agentopsd-schedule,routing-policy}.md`
- `docs/contracts/jobspec-openapi-v0.yaml`
- `docs/templates/dark-factory-schedule.yaml.example`
- `docs/design/olympus-v4-specs/*.md` — v4-port reference for the dead
Olympus → agentopsd extraction
## Reframed (prose → in-session + Gas City)
- Daemon/schedule/overnight: `agentops-3-youtube-starter-series.md`,
`agentops-3-pmf-evidence-loop.md`, `wiki-for-agents.md`,
`activation-profiles.md` (+ `profiles/README.md` profile rename),
`CI-CD.md` (overnight lane)
- Hooks → hookless + CI-as-authoritative-gate (hooks removed #511):
`knowledge-flywheel.md`, `troubleshooting.md`, `reference.md`,
`CI-CD.md`, `release-e2e-checklist.md`, `seed-definition.md`
## Catalog + cross-link cleanup (no broken links)
- `documentation-index.md` — removed deleted-doc rows + the v4 section
- `contracts/index.md` — removed deleted-contract cards
- `rfcs/0002-jobspec-openapi-v0.md` marked superseded; `SCHEMAS.md`,
`templates/README.md` cross-links fixed
## Created
- `docs/MIGRATION-3.0.md` (from the approved draft) + catalog row +
mkdocs nav entry
## Gates (green for this PR's surfaces)
- Link check: **2723 links, 0 broken**
- Contracts structural floor: **PASS (45 contracts)**
- Contract compatibility (orphans): **PASS**
- markdownlint (all changed/new files): **clean**
- `heal.sh --strict`: **All clean**
- mkdocs-strict: my new doc + nav entry build cleanly. The strict build
is **red on main for pre-existing reasons outside this scope** —
`docs/_hooks/gen_cli_reference.py` FATALs on missing `cli/docs/HOOKS.md`
(hooks removed #511, generator not updated; release-mechanics domain)
and `docs/3.0.md:172` links `../PRODUCT.md`/`../GOALS.md` (root files
outside the docs tree). Both confirmed present on `origin/main`; filed
for wave 3.
## Scope notes
- Did **not** touch `CHANGELOG.md`, `cli/`, or version files (parallel
worker owns release mechanics).
- The audit grep still matches ~40 more out-of-scope `docs/` files
(contracts/*, code-map, comparisons, narrative pages, runbooks). Filed
as **wave 3 (ag-p7j)**.
Closes-scenario: ag-qbw#doc-sweep-2
Bounded-context: BC1-Corpus
Evidence: docs/3.0.md
|
||
|
|
e431339c40 |
feat(hookless)!: remove all hooks — skills + CLI only (soc-57b7f #remove-all-hooks) (#511)
## What AgentOps 3.0 goes **fully hookless**. This removes the entire hook product surface — the product is now skills + the `ao` CLI with **zero hooks**. CI is the authoritative gate. ## Deleted - `hooks/` — 46 hook scripts + `hooks.json` + examples (whole directory) - `cli/embedded/hooks/` + embedded `hooks.json` + `embedded/lib/hook-helpers.sh` - `lib/hook-helpers.sh` - `ao hooks` CLI command: `cli/cmd/ao/hooks.go`, `hooks_run.go` + 5 hook test files; `cli/internal/bridge/hooks.go`; `cli/internal/doctor/fix_hooks.go` + test - Codex hook manifest (`hooks/codex-hooks.json`) + handler/audit scripts (`scripts/audit-codex-hooks.sh`, `install-dev-hooks.sh`, `test-hooks-output.sh`, `test-codex-hookless-lifecycle.sh`, `test-hookless-rpi-phased.sh`) - Hook lease surface: `docs/contracts/hook-lease-*`, `schemas/hook-lease.v1.schema.json`, `scripts/check-hook-lease-inventory.sh`, `check-hook-port-replacements.sh`, `generate-hook-lease-inventory.py` - Hook docs: `docs/HOOKS.md`, `cli/docs/HOOKS.md`, `docs/architecture/hook-noise-audit.md`, `docs/contracts/hook-runtime-contract.md` - `tests/hooks/` (whole dir) + hook test scripts; 5 hook eval suites + fixtures ## CI gates removed `hook-preflight`, `validate-hooks-doc-parity`, `hook-output-schema-lint` (+ scripts/bats), the hook eval suites, the `test-runtime-codex-smoke` / `test-codex-native-install` / `test-codex-plugin-install` hook-handler assertions, the cli-integration hook-lifecycle steps, the bats `tests/hooks/*` glob + orphan-hooks audit, and the `--with-hooks` install path. `embedded-sync` now validates only lib/skills. Both summary `needs:` lists + the summary echo + `docs/contracts/ci-jobs.yaml` updated; `validate-ci-policy-parity` passes (66 rows). `.codex-plugin/plugin.json` drops the "Hooks" capability. ## Load-bearing PRESERVED (reported, not forced) - **`cli/cmd/ao/codex_runtime.go`** — the codex runtime *lifecycle profile* (`HookCapable`/`HookConfigured` detection) is a runtime-capability abstraction used by 6 `validate-codex-*` CI gates, distinct from the hook product. Deleting it is a separate refactor. - **`hooks-authoring` skill** + `schemas/hooks-manifest.v1.schema.json` — reframed as an opt-in "author your own hooks" guide. Deleting the skill cascades into catalog/domain-map/dispositions/context-map golden files (skill-count sync), out of scope for the hook-product removal. - **`scripts/pre-push-gate.sh`** — retired local gate (not in CI); self-skips deleted hook scripts via `[[ -x ]]` guards; its 55 bats tests still pass. - Domain-enforcement audit keeps the `enforced`-mode schema for backward-compatible JSON readers, but the hookless resolver only returns `audited`/`unavailable`. ## Verification `go build` / `go vet` clean; `go test ./...` = **11849 passed, 0 failed** (68 pkgs). gofmt clean on all touched files. Green: registry `--check` (0 hooks), `regen-codex-hashes --check`, `validate-ci-policy-parity`, `check-wiring-closure`, `validate-embedded-sync`, `validate-manifests`, `validate-agents-split`, `doc-release` (0 broken links), `generate-cli-reference --check`, `heal.sh --strict`, codex/claude/plugin smoke tests, baseline-audit (0 stale). Diff: 231 files, +354 / −39803. Closes-scenario: soc-57b7f#remove-all-hooks Bounded-context: BC5-Runtime Evidence: .github/workflows/validate.yml |
||
|
|
b8aa715fa8 |
docs(roadmap): move aspirational claims into docs/ROADMAP.md (soc-icvff #w1b-roadmap) (#470)
W1b of the 3.0 reconciliation (match reality). Designed-but-unbuilt features were scattered through live docs; consolidated into one roadmap so live docs describe only what exists. - **docs/ROADMAP.md (NEW)**: gt convoy / bd mol / bd cook, curation later stages, hookless default-install (ADR-0002 S2–S5), legacy-RPI removal (soc-1gbpz) — non-committed framing - troubleshooting.md / brownian-ratchet.md / curation-pipeline.md: removed inline unbuilt-command examples → ROADMAP pointers - documentation-index.md + mkdocs nav: cataloged No code. grep confirms no unbuilt-as-available language left in live docs. NOTE: claude-review infra-red (weekly limit, resets May 25) — operator-authorized bypass when sole red. Closes-scenario: soc-icvff#w1b-roadmap Bounded-context: BC1-Corpus Evidence: docs/ROADMAP.md |
||
|
|
4dd53dffa3 |
docs(3.0): canonical 3.0 north star + weave into sources of truth (soc-25sgs #3.0-north-star) (#468)
W0 of the 3.0 reconciliation (operator-ratified). Grounds the repo before reconciliation work. - **docs/3.0.md (NEW)** — single source of truth: the SDLC↔CDLC loop (BDD/Gherkin planning → tests → bounded build through ports → both-ends behavior+contract validation → feedback → ratchet), the BDD/DDD/Hexagonal/TDD waist, context density, and a precise hookless-first explanation (hooks = quiet adapters, not noise-injectors). + 3.0-ready acceptance + non-goals. - Woven into README, PRODUCT.md, GOALS.md, CLAUDE.md, docs/documentation-index.md, mkdocs.yml nav. Pure grounding: no code, no bead closes, no features. Links verified; additions-only. NOTE: claude-review infra-red (weekly limit, resets May 25) — operator-authorized bypass when sole red. Closes-scenario: soc-25sgs#3.0-north-star Bounded-context: BC1-Corpus Evidence: docs/3.0.md |
||
|
|
9a92652d4d |
docs(architecture): behavior-shaping-environment doctrine — the ABC spine (soc-loqc #behavior-shaping-doctrine) (#414)
Operator product thesis (2026-05-22): AgentOps is the environment that arranges antecedents + reinforcement so agents reliably perform agreed-upon behaviors. This names the operant-conditioning model (Antecedent → Behavior → Consequence) AgentOps already embodies — the *why* beneath the loop. - docs/architecture/behavior-shaping-environment.md (NEW): ABC model + surface→mechanism mapping (antecedent=context arrangement, behavior=.feature, consequence=gates/ratchet reward + hooks/STOP/reverts stop), why-it-works, 5 governing principles, propagation map - catalogued in documentation-index + architecture/index; added to mkdocs nav Anchor for epic **soc-tk1d**. The other 3 surfaces (domain vocab, positioning, GOALS contract) cite this doc. Sibling pattern: mirrors docs/architecture/operating-loop.md doctrine shape. Fitness: behavior-science surfaces 0/4 → 1/4. NOTE: claude-review will be infra-red (weekly limit, resets May 25) — operator-authorized bypass when sole red. Closes-scenario: soc-loqc#behavior-shaping-doctrine Bounded-context: BC1-Corpus Evidence: docs/architecture/behavior-shaping-environment.md |
||
|
|
81fe2d5ae8 |
feat(docs): sovereignty-proof page — F6/F7 + RPI-leanness case studies (soc-vuu6.32 #sovereignty-proof) (#386)
## Summary New \`docs/sovereignty-proof/\` surface with two committed case studies showing where independent-vendor review caught what same-vendor review missed: - **2026-05-15 RPI-leanness council** — Codex (gpt-5.5) independently reframed "RPI is waterfall" to "plan.md is an artifact-boundary bug", turning a multi-week methodology rewrite into a single-port surgical change (PR #275 was already in-flight implementing this). - **2026-05-16 CDLC research council** — Two Codex judges independently flagged the F6 session-misjoin bug in \`cli/cmd/ao/flywheel_citation_feedback.go\` and the F7 \`hooks/citation-tracker.sh\` wiring gap. No Claude judge surfaced either. ## Why Council non-negotiable #2 (.agents/council/2026-05-18-validate-agentops-3.0-doctrine.md). Mixed-model capability must be visible as load-bearing proof of the sovereignty thesis, not buried as opt-in obscurity. The page is what makes the sovereignty claim falsifiable + linkable from the README hero (unblocks soc-vuu6.30). ## Mechanical guarantees - \`scripts/validate-sovereignty-proof-citations.sh\` scans every \`.md\` under \`docs/sovereignty-proof/\` for \`file:line\` citations (\`path/to/file:NN\` or \`path/to/file:NN-MM\`) and verifies each resolves at HEAD. Currently 16 citations across 3 pages. - New CI job \`validate-sovereignty-proof-citations\` (required) wires the script into \`validate.yml\` with broad triggers so any referenced-surface change re-runs the gate. Added to merge-gate \`needs:\` arrays + summary echo. - 8-case bats regression suite at \`tests/scripts/validate-sovereignty-proof-citations.bats\` (pass / file-missing / line-overflow / fenced-code-block / backtick / multi-page / no-dir / no-markdown). - mkdocs nav entry under Concepts → Sovereignty Proof. - \`docs/documentation-index.md\` Concepts entry. ## Acceptance (BDD) Given a visitor wants to verify the sovereignty claim is real, When they click "Sovereignty proof" from README hero (slice 1, blocked on this), Then they land on \`docs/sovereignty-proof/index.md\` showing real \`/council --mixed\` output from the 2026-05-15 reframe AND 2026-05-16 F6+F7 findings with \`file:line\` citations and verdict file links. ## Verification \`\`\`bash bash scripts/validate-sovereignty-proof-citations.sh # validate-sovereignty-proof-citations: scanned 3 pages, 16 citations # PASS — all citations resolve. bats tests/scripts/validate-sovereignty-proof-citations.bats # 1..8 (all pass) \`\`\` Closes-scenario: soc-vuu6.32#sovereignty-proof Bounded-context: BC1-Corpus Evidence: docs/sovereignty-proof/index.md Evidence: scripts/validate-sovereignty-proof-citations.sh Evidence: tests/scripts/validate-sovereignty-proof-citations.bats Evidence: .github/workflows/validate.yml |
||
|
|
d69f9f0c13 |
feat(architecture): intent-to-loop hexagon doc + BDD skill scaffolding (soc-4d0r) (#321)
## What
Foundation slice for the **soc-qk4b** epic ('TDD-crank all skills into
intent-to-loop hexagons'). The epic description listed these artifacts
as 'What already exists' — but they were never committed to main.
Without them, the 6 sub-issues (`soc-qk4b.1` through `.6`) cannot start.
## New
`docs/architecture/intent-to-loop-hexagon.md` — process-level hexagon
connecting [Ports and
Adapters](../blob/main/docs/architecture/ports-and-adapters.md)
(structure) to [Operating
Loop](../blob/main/docs/architecture/operating-loop.md) (execution).
Defines the 8-port chain with driving/driven/guard adapters and
done-state rules:
```
Intent
-> shape_intent -> AcceptanceExample
-> persist_intent -> WorkItem / Bead
-> plan_slices -> Slice
-> execute_slice -> implementation
-> execute_wave -> wave packet
-> validate_acceptance -> CriterionVerdict
-> record_evidence -> Evidence
-> steer_goal -> LearningDisposition
```
## Skill changes
Source-of-truth in `skills/`, mirrored to `skills-codex/` (re-hashed via
`scripts/regen-codex-hashes.sh`):
| Skill | Change |
|---|---|
| `plan` | Require Gherkin block or upstream-scenario link for
feature/bug/product-facing behavior issues; `hexagon:` boundary block
for non-trivial plans and beads. |
| `discovery`, `rpi`, `validate`, `validation`, `beads`,
`shared/validation-contract` | Reference the intent-to-loop hexagon as
the boundary contract. |
## Doc plumbing
- `docs/architecture/{index,operating-loop,ports-and-adapters}.md` +
`docs/contracts/skill-ports-and-adapters.md`: cross-link to new hexagon.
- `docs/templates/{intent-issue,slice-validation}.md`: carry hexagon
block into intent issues and slice validation plans.
- `mkdocs.yml`, `docs/documentation-index.md`: register new doc in nav.
## AGENTS.md
- bd integration block regenerated (`v:1 profile:full hash:f65d5d33`).
- Session Completion section added with **conditional** `bd dolt push`
wording — passes `scripts/validate-bd-closeout-contract.sh`.
## Validation
- ✅ `scripts/pre-push-gate.sh --fast`: passed (1 pre-existing warn on
`scenarios/trace` executable-spec link integrity, unrelated)
- ✅ `scripts/validate-bd-closeout-contract.sh`: passes
- ✅ `scripts/regen-codex-hashes.sh`: 7 manifest hashes updated for
parity
- ✅ All 8 codex JSON files: syntactically valid
- ✅ Self-review per pre-commit hook: no removed error handling, no
changed defaults, no silent data loss
## Origin
Discovered during analysis of merged branch
`refactor/council-mode-taxonomy-soc-ml4l` (PR #293) on 2026-05-18 — the
BDD/hexagon scaffolding sat uncommitted in the worktree after #293
merged. Filed as `soc-4d0r` with `discovered-from: soc-qk4b`. This PR
lands the work cleanly off fresh `main`.
## Unblocks
- soc-qk4b (epic)
- soc-qk4b.1 — Control ledger for 77-skill hexagon crank
- soc-qk4b.2 — Loop priority skills (hexagon/TDD crank)
- soc-qk4b.3 — Factory priority skills
- soc-qk4b.4 — Corpus priority skills
- soc-qk4b.5 — Validation priority skills
- soc-qk4b.6 — Runtime priority skills
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Codex <codex@example.invalid>
|
||
|
|
a427dcce6d |
docs(positioning): assurance profile + goals as reconcile setpoints (soc-sx99) (#257)
* docs(positioning): add assurance profile for agent factory rigor * docs(positioning): frame goals as reconcile setpoints * chore(scripts): suppress SC2034 on bd_out — set by run_capture via name-ref Drive-by fix needed to push crank/soc-sx99 — pre-push shellcheck flagged bd_out as unused in test-rpi-surface-smoke.sh, but it is set indirectly by run_capture's name-ref pattern. Adds a targeted shellcheck disable comment. |
||
|
|
d535db3e29 |
docs(cdlc): add Context Development Life Cycle concept page
Map the DevOps SDLC to CDLC — seven phases (Generate, Compile, Test, Distribute, Deliver, Observe, Adapt) with AgentOps implementation for each. Added to Concepts nav between The Science and Brownian Ratchet. Also updates mkdocs site_description to context-compiler framing. Ref: Debois CDLC talk (AI Engineer 2026), soc-hsef |
||
|
|
d54eba7aaa | docs: add local compute routing policy draft | ||
|
|
6e7ed526a9 | feat(daemon): ship AgentOps daemon runtime | ||
|
|
c4166a5c51 |
docs: fix broken CLI links, add HOOKS/SCHEMAS/UPGRADING pages, expand GLOSSARY
Addresses a batch of documentation improvements identified in a full-docs audit. The goal is to reduce newcomer friction from dead links and missing canonical references, and to give skill/plugin authors explicit pages for hooks, schemas, and version migration that were previously implied only by source code. Navigation fixes: - docs/INDEX.md and docs/newcomer-guide.md pointed to the wrong path for the CLI reference (cli/commands.md vs. the real cli/docs/COMMANDS.md). Replace with the canonical github URL so both mkdocs and raw-GitHub readers land on the file. - INDEX.md Getting Started section now opens with a "pick your path" router so evaluators, installers, contributors, and upgraders don't have to triangulate across three overlapping entry points. - Link docs/getting-started/index.md from INDEX.md (was previously orphaned) and add an "Install verification" block pointing at ao doctor. New pages: - docs/HOOKS.md: user-facing orientation covering lifecycle events, install/uninstall, customization env vars, and common failure modes, pointing to cli/docs/HOOKS.md for the deep technical reference. - docs/SCHEMAS.md: catalog of every JSON Schema under schemas/ and lib/schemas/, grouped by manifest vs. runtime artifact vs. internal contract, with validation commands. - docs/UPGRADING.md: action-required version migration guide. Seeds Unreleased (2.38.x) and 2.37.x sections covering strict delegation, --no-lifecycle -> --no-scaffold rename, Olympus bridge removal, swarm-evidence schema enforcement, and pre-mortem gate tightening. Reference quality: - GLOSSARY.md: 11 new terms (.agents/, MEMORY.md, Compact/PreCompact, Compile, Context Window, Discovery, Dream/Overnight Run alias, Flywheel Health, Harvest, Holdout, RPI Phase, Session Lifecycle). - troubleshooting.md: three new failure-mode sections (pre-mortem gate, go-test-precommit block, context-window compaction recovery). - CONTRIBUTING.md: escalates the sync-skill-counts.sh requirement from an easily-missed sentence to a bold callout with CI-failure rationale. mkdocs.yml: registers the three new pages in nav so they're reachable from the published site and pass strict build. Validation: - tests/docs/validate-links.sh: 1553 links checked, 0 broken. - tests/docs/validate-doc-release.sh: PASS. - scripts/docs-build.sh --check: new docs introduce 0 warnings (the single remaining preexisting warning about index.md is out of scope). |
||
|
|
1e073d8363 |
chore: purge archived AO↔Olympus bridge integration + prefer local Go in precommit hook
Olympus (ol) was the power-user daemon predecessor to AgentOps, archived in strategic-direction.md. The bridge contracts (SPEC_ONLY, never enforced), MemRL policy surface, OL quarantine constraints collector, and supporting scripts/tests all referenced a now-dead integration. Purging them removes ~2400 lines of stale surface area. ## Deleted files - docs/ol-bridge-contracts.md - docs/architecture/ao-olympus-ownership-matrix.md - docs/plans/2026-02-13-ao-olympus-bridge-next-steps.md - docs/contracts/memrl-policy-integration.md - docs/contracts/memrl-policy.schema.json - docs/contracts/memrl-policy.profile.example.json - cli/cmd/ao/inject_ol_test.go - skills/vibe/scripts/ol-validate.sh + codex mirror - skills-codex/swarm/scripts/ol-ratchet.sh, ol-wave-loader.sh - tests/ol-integration/ (entire directory) ## CLI code stripped - internal/search/types.go: OLConstraint struct + InjectedKnowledge.OLConstraints field - internal/search/inject_run.go: CollectOLConstraints, WriteConstraintsSection, quarantineRelPath const, all related trim/render logic - cmd/ao/inject.go: gatherOLConstraints, collectOLConstraints wrapper, olConstraint type alias, init-time call site - Package comments in provenance/storage/types/formatter updated "olympus" → "agentops" - formatter/markdown.go: session tag "olympus" → "agentops" (+ test update) - Tests: deleted TestCollectOLConstraints + TestInject_collectOLConstraints, stripped OL subtests from TestFormatKnowledgeMarkdown and TestInject_*, renamed "olympus" literal test data to "other-repo" - rpi_phased_context.go: stripped "matches Olympus DefaultTimeout" and "Modeled on Olympus internal/git/worktree.go" comments ## Docs + skills stripped - mkdocs.yml nav: 3 entries removed (AO-Olympus Matrix, MemRL Policy, OL-AO Bridge) - docs/INDEX.md, contracts/index.md, architecture/index.md, index.md: cross-refs removed - strategic-direction.md: retirement rationale compressed to one paragraph - docs/context-packet.md, positioning/devops-for-vibe-coding.md, plans/README.md: OL-specific content removed - skills/vibe/SKILL.md + codex mirror, swarm/SKILL.md: OL script refs removed - skills/vibe/references/deep-checks.md, plan/references/planning-rules.md (+ codex), pre-mortem/references/council-fail-patterns.md (+ codex): OL rule/pattern entries removed - skills-codex hashes regenerated (plan, pre-mortem, swarm, vibe) ## Precommit hook fix - hooks/go-test-precommit.sh: prefer ~/.local/go/bin/go when present. Hooks don't inherit interactive-shell PATH, so apt-provided go-1.22 would otherwise override a user-local 1.26 install. Mirrors the zshrc pattern. ## Retained (historical / useful) - strategic-direction.md: 1-paragraph archival note - Historical release notes (docs/releases/*.md) — immutable past-release record - cli/testdata/transcripts/real-2.4mb.jsonl — captured test fixture - docs/brownian-ratchet.md ol-rg3p bead-ID refs — internal bead prefix, not Olympus ## Verification - go build ./... && go vet ./... clean - go test ./... clean except pre-existing TestGCBridgeVersion_Live panic - scripts/docs-build.sh --check (mkdocs strict) clean - scripts/check-contract-compatibility.sh passes - scripts/regen-codex-hashes.sh run — 4 skills updated |
||
|
|
57527e3fd2 |
docs(theme): match agentops-showcase palette — warm terracotta on near-black
Source of truth: boshu2/agentops-showcase (12factoragentops.com). Tokens copied from its tailwind.config.ts + globals.css. ## Palette - Primary: #d97757 (hsl(15 55% 60%)) — warm clay / terracotta - Accent: #fbcfb2 — soft peach - Background: #0a0a0a (neutral-950, warm matte) - Card bg: #111110 / #171512 (warm-tinted ladder) - Foreground: #dea78c / #c79073 (warm tan on dark) - Selection: rgba(217,119,87,0.3) with peach text ## Fonts - Code: Space Mono (replaces JetBrains Mono) to match showcase - Text: Inter (unchanged) ## Updated - mkdocs.yml palette: primary/accent → "custom" so the theme defers to our CSS variables - docs/assets/stylesheets/extra.css: full rewrite — header gradient, announce bar, buttons, grid cards, code blocks, tables, admonitions, nav, search, scrollbars, selection all retuned to the warm palette - docs/assets/logo.svg + favicon.svg: gradient swapped from indigo→pink to terracotta→peach to match - Hero landing H1 gradient: now clay→peach→amber - Preserved the .landing-hero scoping so inner-page H1s stay solid, not gradient Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
|
cc6750c4e8 |
feat(docs,skills): rebuild Pages site with MkDocs Material + harden RPI orchestrator delegation contract
## Docs site — boshu2.github.io/agentops
- Replace Jekyll minima with MkDocs Material (slate dark palette default)
- Landing hero scoped to .landing-hero (no gradient bleed on inner pages)
- Section landings (getting-started, architecture, reference, contracts, levels) with narrative ledes
- Generate skill catalog + per-skill pages from skills/*/SKILL.md at build
- Generate CLI reference from cli/docs/ at build (fails build on missing source)
- Fix every internal link via one-shot migration (scripts/migrations/2026-04-19-fix-docs-links.py)
- Wire mkdocs build --strict into pre-push gate (Check 25a)
- Replace .github/workflows/pages.yml with .github/workflows/docs.yml (actions/deploy-pages)
- README + docs/CONTRIBUTING updated with docs-build toolchain on-ramp
- tests/docs/validate-links.sh patched to understand mkdocs-generated paths
## RPI orchestrator strict-delegation contract
- Strict sub-skill delegation is now the default for /rpi, /discovery, /validation. No --full flag — always on.
- Canonical contract in skills/shared/references/strict-delegation-contract.md (plus Codex mirror)
- Forged learning with detection phrases + corrective actions (ao-inject-ready)
- Rename --no-lifecycle -> --no-scaffold in /discovery (Claude + Codex) with deprecation alias through v2.40.0
- Harden inline-work hotspots with orchestrator-owned markers in /crank STEPS 3a.3, 6.5, 8.7 + Inline Work Policy footer
- Flag consistency: --auto and --interactive scopes documented; --complexity syntax formalized
- CHANGELOG [Unreleased] documents + scaffolds; runtime hook enforcement explicitly deferred
## fix(hooks): go-test-precommit skips when no Go files staged
- Previously ran go vet + go build unconditionally, blocking non-Go commits when Go toolchain was missing or at a different version
- Now checks staged diff and exits cleanly if no *.go or go.{mod,sum,work} files are staged
- Applied to both hooks/ (source) and cli/embedded/hooks/ (synced)
Provenance: full RPI lifecycle with strict delegation at every phase boundary (Phase 1 Skill(discovery) -> Phase 2 Skill(crank) -> Phase 3 Skill(validation) -> Skill(vibe), Skill(post-mortem), Skill(retro)).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|