Commit Graph

17 Commits

Author SHA1 Message Date
boshu 4823077621 refactor: cut AgentOps to a single-pass evidence loop 2026-07-14 22:01:50 -04:00
Bo 1d4c003e05 Cut plan: gate registry diet, legacy bash gate removal, CI collapse, pawl warm-service removal (#906)
## Summary
- **Wave 1** — remove the `always.wiring-closure` meta-gate, demote
`docs.skill-refs` to Full tier, delete 8 orphan scripts.
- **Wave 2** — delete the legacy bash pre-push gate (`pre-push-gate.sh`,
2,279 lines) and its parity machinery; collapse `validate.yml` from 18
jobs to 5.
- **Wave 3** — remove the pawl warm NTM standing service; the cold
review spine (pawl-review / pawl-verdict / pre-push check) is untouched.
- **Wave 4** — gate registry diet: cut 24 doctrine/meta check IDs and
~70 backing scripts/workflows/bats; trim nightly knowledge-cycle job.

Net: gate registry 112 → 83 checks (incl. main's additions), ~24k lines
of scripts/CI/bats deleted. Routine one-file fast gate now runs in ~19s.

## Test plan
- [x] `go build` / `go vet` / gates+goals+ports package tests green
- [x] `ao gate check --fast --scope range:origin/main..HEAD` — 66
passed, 0 failed, 1 skipped (199 changed files)
- [x] `validate-ci-policy-parity.sh` PASS; validate.yml / nightly.yml
parse
- [x] `regen-changed-scope --check` green; registry.json regenerated
- [x] Grepped tree for dangling references to every deleted script/check
ID

Made with [Cursor](https://cursor.com)

---------

Co-authored-by: boshu <241868352+boshu2@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-13 14:45:20 -04:00
boshu 4e584f2297 feat(cli): deliver truthful executable CLI spine (age-cli-truthful-spine-2f5n.19) 2026-07-10 19:30:53 -04:00
boshu 46c802d7ab fix(pawl): tip-coherence guard + canonical evidence/catch rooting (age-pawl-bead-tip-coherence-wckn, age-pawl-evidence-worktree-loss-np1e)
Two guards for the 2026-07-09 wrong-tree/evidence-loss incident:

wckn: pawl_tip_coherence refuses (exit 3, fix-and-re-run) when the review
target commit cites bead ids sharing the reviewed bead's prefix and none is
the bead or a dotted relative - a verdict can no longer bind a tree that
belongs to a different bead. Positive-mismatch only; PAWL_ALLOW_TIP_MISMATCH=1
opts out. 7 bats.

np1e: evidence transcripts and membrane catches now root at the CANONICAL
checkout (git-common-dir parent) via pawl_evidence_dir/pawl_canonical_root,
so reviews run in disposable land worktrees no longer write artifacts that
die with 'git worktree remove', and ledger evidence_path never dangles.
5 bats. Both libs registered in validate-embedded-sync + embedded copies synced.

Claude-Session: https://claude.ai/code/session_01BkgdP88SiccCSyYdi8GHNa
2026-07-10 09:38:54 -04:00
boshu 74aefa8312 feat(economics): amend-into-#trivial-bind trap guard (age-verification-economics-ebec.11)
Kills the operator-error class that fired ~4x on 2026-07-07, each costing a wasted
review round: after the pawl auto-binds a #trivial provenance commit on the feat, a
'git commit --amend' folds the fix INTO the bind — HEAD becomes a #trivial commit
carrying code, the reviewer's trivial-waiver walk steps PAST it to review the STALE
original feat, and the verdict binds the wrong tree (surfacing only as an opaque
'hidden non-trivial commit' gate failure at push).

scripts/lib/pawl-amend-guard.sh (new, sourceable, unit-tested): pawl_amend_guard
returns 2 when HEAD is a trailing-#trivial commit changing non-provenance files,
printing the diagnosis + the rebuild-don't-amend recovery. Wired EARLY into
pawl-review.sh (scope=head, before the review — where it saves the round) and as a
land-time backstop in pawl-land.sh; embedded pawl bundle + Makefile + embed validator
updated. Safe: provenance-only #trivial binds, plain feats, and mid-subject #trivial
mentions all pass; opt out PAWL_NO_AMEND_GUARD=1. bats 5/5; guard proven to fire on
the trap and stay silent on legitimate binds; race suite green.
2026-07-07 19:10:45 -04:00
boshu 69d5e7c392 feat(economics): pre-flight gate — run the deterministic battery BEFORE the model reviewer (age-verification-economics-ebec.9)
THE bottleneck fix. On 2026-07-07, closing skill-doc changes took 4-7 model-review
rounds each because ~90% of the defects were DETERMINISTIC (format/link/twin/
gate-hint) — but the expensive cross-family verdict was requested BEFORE the local
deterministic checks were green, so the membrane re-discovered them serially, each
round a full re-review + re-land.

scripts/lib/pawl-preflight.sh (new, sourceable, unit-tested): pawl_preflight <scope>
<repo> runs the reviewed repo's deterministic battery before the reviewer and fails
fast (exit 3, same fix-and-re-run disposition as the --smoke/REFUTED path) on a
CONFIRMED-red battery — WITHOUT spending a reviewer round (0 tokens). Command:
PAWL_PREFLIGHT_CMD if set (operator owns exit semantics), else the default
'ao gate check --fast --scope head' (ao resolved AO_BIN -> repo cli/bin/ao -> PATH,
mirroring check-pawl-pre-push.sh). Wired into pawl-review.sh after the HEAD snapshot,
before packet assembly + the meter clock.

SAFETY — pure ACCELERATOR, never a false blocker: a nonzero that cannot be CONFIRMED
as a real gate run (RCE trust-guard, missing/stale ao, build error — distinguished by
the absence of the gate's 'checks —' summary marker) is SKIP-and-proceed, not RED.
Worst case it no-ops and behavior is byte-identical to today (the pre-push gate still
backstops). Disabled for PAWL_UNTRUSTED_REPO=1 (never run a repo's own battery over an
untrusted checkout) and scope != head (no committed HEAD). Opt out: PAWL_NO_PREFLIGHT=1.

Converts the inert prose lesson 'run the battery before the verdict' into MECHANISM
(the skills audit proved prose lessons are inert). bats 9/9; embedded pawl bundle +
Makefile sync + embed-sync validator updated; Go embed test green.
2026-07-07 18:46:27 -04:00
boshu 9a23ba9cc5 refactor(skills): execute the audit retire wave — 8 skills retired/merged, 66 -> 58, spine 15 -> 13 (age-skills-audit-fable-l6ic.12)
Executes the age-e3zk decision (fresh disposition pass: docs/audits/
skills-audit-2026-07-06.md; council 2026-07-06 parked this behind age-p2c7,
which landed as d7f950ca8; operator directive 2026-07-07 authorized finishing
all filed work).

RETIRED: red-team (validate --debate absorbs), perf (frontier-generic, zero
repo bindings), flywheel (ao flywheel status CLI is the surface).
MERGED: eval-outcomes -> validate (--mode=pre-impl --target=scenario),
review -> validate (--mode=pr), compile + curate -> post-mortem (mining half;
mechanical surfaces stay ao compile / ao lookup), recover -> status
(--recover mode; deep playbook preserved at status/references/
recovery-playbook.md; delivers l6ic.7 and the l6ic.13 row reconcile).

Mechanics: ao skills retire x8 (trees incl. images/*/skills, terminal ledger
rows via --into, .agy-plugin review bundle removed); absorption tombstones in
docs/SKILLS.md + SKILL-TIERS.md (56 user-facing + 2 internal = 58, counted);
spine gate re-anchored 15 -> 13 (l6ic.11 minimal consistency: review +
red-team leave; membrane 7 + bookkeeper 6); bespoke twins post-mortem/status
hand-mirrored per AGENTS-CODEX; manifest pruned of orphan twin rows (62 -> 57);
overrides catalog pruned of 8 retired rows; gemini verify core_skills +
claude/codex image manifests updated; retired-subject eval
red-team-adversarial-validation.json removed (not canary-listed).

Gates: spine-integrity 13 PASS; wiring-closure PASS; skill-frontmatter 58/58;
codex manifest+artifacts+parity PASS; regen-check ALL GREEN; SKILL-TIERS also
fixed Opus 4.6 -> 4.8, GOALS.yaml -> GOALS.md, flywheel diagram to CLI truth
(l6ic.6 pre-work). Residual prose mentions in non-gated docs are the l6ic.2
debris sweep's scope.
2026-07-07 11:06:35 -04:00
boshu fe1d8fee8c feat(pawl): patch-id REBOUND verdicts — authorize a byte-identical rebase without a full re-review, gate-green + lineage required (age-rk3r.9)
# Conflicts:
#	skills/catalog.json
2026-07-02 18:24:24 -04:00
boshu 3c4e4d6d54 feat(pawl): source per-repo verify config once at pawl-review entry (age-rk3r.17) 2026-07-02 01:30:44 -04:00
boshu bc9fb32709 feat(verify): ao verify receipts — portable proof page from the embedded bundle (age-rk3r.12)
Ship gen-membrane-receipts.sh + check-membrane-receipts-freshness.sh in the
embedded pawl bundle (make sync-hooks + //go:embed all:pawl) so a stranger repo
can render its own membrane-receipts proof page with no AgentOps checkout.

ao verify receipts mirrors the pawl review trust split: in-checkout dogfood runs
the live repo generator; anywhere else it extracts the EMBEDDED generator and
runs it against the user's OWN git repo under the sanitized cold env
(pawlReviewColdEnv) with AO_BIN pinned to the running binary — no ao-on-PATH
needed, no repo-local script trusted. The generator refuses the build-from-cli/
fallback when PAWL_UNTRUSTED_REPO=1 (compiling+running an untrusted repo's
cmd/ao would be RCE); the in-repo path keeps its fallback. Fail-closed
chain-verify-before-render and the count-parity check are unchanged.

Byte-identical to the current generator on this repo's ledger (behavior lock).
Bats acceptance in a throwaway repo with a production-writer-built ledger:
render + tamper-refusal + embedded==in-repo parity.

# Conflicts:
#	docs/cli-surface.json
#	docs/cli-surface.md
2026-07-02 00:46:05 -04:00
boshu 07571c3fe3 refactor(pawl): delegate cold codex invocation to codex-exec lib — single source of truth for stall/echo defenses (age-gate-the-ungated-egwt.13) 2026-07-01 20:08:46 -04:00
boshu e1d2d74be8 feat(pawl): run ao pawl review zero-config on a stranger's repo (age-a9iv.4)
S2 — decouple the guaranteed cross-family verb from the AgentOps source checkout
so a fresh external user can run the catch on their OWN non-AgentOps repo.

Before: ao pawl review died on a stranger's repo with 'locating AgentOps repo root'
before ever reaching codex (S0). Now: a GENUINE in-checkout run (the running ao binary
lives inside the resolved checkout — aoBinaryInside) uses the live scripts (EDGE 1);
everyone else (installed ao, or forged markers) extracts the embedded pawl bundle
(go:embed cli/embedded/pawl/, sibling scripts/+schemas/ for EDGE 2) and runs it against
the user's own git repo via AGENTOPS_REPO_ROOT + PAWL_NO_SERVICE. cwd stays the user's
repo so the read-only codex refuter can READ the changed files for large diffs.

SECURITY — the cross-family pawl caught a sequence of real defects on this commit:
  - TRUSTED PATH: the stranger run's PATH drops every entry the repo could control — '',
    '.', any relative entry, AND any absolute dir INSIDE the repo (e.g. $PWD/bin on PATH).
    So a bare codex/git/jq/timeout can never resolve a repo-planted binary. Go-side bash
    resolves on the same trusted PATH; repo-root discovery is PURE Go (.git walk, no binary)
    so no planted git runs during discovery.
  - resolve_ao no longer searches $REPO_ROOT/cli/bin/ao; live path gated on aoBinaryInside
    (forged markers can't trigger it); pawl-verdict.sh emits + resolve_ao use ONLY the
    absolute pinned AO_BIN when untrusted. In-checkout behavior unchanged (flags unset).
  - INTEGRITY: the refuter runs codex with project_doc_max_bytes=0 so a repo-planted
    AGENTS.md cannot hijack the reviewer into a fail-open VERDICT: CONFIRMED; the cold env
    neutralizes BASH_ENV/ENV so non-interactive bash cannot source a repo file.

  - ROOT PRE-RUN: ao's root PersistentPreRunE runs git in the cwd (RepairSharedCore
    WorktreeConfig) before any command; that git is now resolved via worktreeconfig.
    trustedGitBin — absolute, excluding '.'/relative/repo-internal PATH dirs — so a
    repo-planted git can't run at startup on the stranger path (CLI-wide).

  - GIT DIFF HELPERS: rendering an untrusted-repo diff (git show/diff) is hardened with
    --no-ext-diff --no-textconv -c core.fsmonitor= (+ GIT_EXTERNAL_DIFF= in the cold env)
    so a repo's diff.external / .gitattributes textconv driver can't run code pre-review.

Packaging/resolution + resolution-safety only — no review LOGIC/gate/daemon change.

Tests: embed-parity gate (+ validate-embedded-sync.sh extended); extract-layout (schema
sibling, EDGE 2); cold-env seam contract; trustedPATH unit test; gitToplevel-no-exec test;
an L2 e2e running the verb in a throwaway non-AgentOps repo with codex stubbed (no
resolveAgentsRepoRoot error, commit-bound verdict written into the USER's repo, schema-
validated check passes); RCE regression tests — planted cli/bin/ao + cli/ao + ./ao + ./codex
(with '.' first in PATH) + BASH_ENV that must never run, and a forged-markers repo that must
route to embedded. Verified on the real binary against a fresh stranger repo: CONFIRMED +
verdict written + merge authorized, exit 0.
2026-06-27 17:16:18 -04:00
Boden Fuller 94db743181 feat(skills)!: skill-corpus prune phase 2 — fold 39 sources into 21 targets + cut reverse-engineer-rpi (105→65) (ag-s43tg #single-writer-final-pass)
21 trigger-graft augments (aug/* branches) merged; 40 skill dirs removed across
skills/, skills-codex/, images/*; dispositions ledger flipped to terminal
historical rows (42, rows never deleted); all factory surfaces regenerated
(registry, domain map, context map, codex twins+hashes, overrides catalog,
SKILL-TIERS, count diagrams); embedded using-agentops retired (BC5 carve-out);
validators/canaries repointed to fold targets (bd-era + Lane-A pre-existing
reds fixed honestly: mkdocs strict, beads canary, council verdict schema,
finding-registry rows, prompt catalog); vibe reference library + ship-loop
anti-patterns + brainstorm ideation refs rescued into fold targets.

Also clears the account-rotation factory-parity debt (3384f5638).

Closes-scenario: ag-s43tg#single-writer-final-pass
Bounded-context: BC4-Factory
Evidence: docs/plans/ag-s43tg-trigger-manifest.md (pinned-phrase contract)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-12 09:49:02 -04:00
Bo a999bcbe62 fix(embedded): restore emptied standards embeds — main hotfix (ag-arpk follow-up) (#799)
## Main is red — hotfix

`cli/embedded/skills/standards/references/{go,test-pyramid}.md` were
**empty (0 bytes)** on main HEAD; #776's merge truncated them.
`contracts-sync` / `correctness` run the full embedded-sync check on
main-push (changed-files-scoped on PRs, so it slipped through during the
batch drain) → main Validate failed (run on 3df599df, def8fc9b).

## Fix
- Re-synced both embedded files from their sources via the
`cli/Makefile` recipe (`cp ../skills/standards/references/*`).
`scripts/validate-embedded-sync.sh` now reports **All embedded files are
in sync**.
- Corrected that script's stale fix hint: `make sync-embedded` (no such
target) → `make sync-hooks` (the real recipe).

## Evidence
`bash scripts/validate-embedded-sync.sh` → "All embedded files are in
sync."

Bounded-context: BC5-Runtime
Evidence: cli/embedded/skills/standards/references/go.md
2026-06-06 10:51:59 -04:00
Bo 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
2026-05-24 11:19:37 -04:00
Boden Fuller f67ed156d8 fix(gates): ignore agent runtime dirt 2026-04-29 12:33:49 -04:00
Boden Fuller 37d4b5b2ae Merge branch 'codex/rpi-supervisor-cli' into main 2026-02-21 19:41:50 -05:00