@open-agent-toolkit/cli 0.2.23 → 0.2.25

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (39) hide show
  1. package/assets/agents/oat-reviewer.md +12 -1
  2. package/assets/docs/cli-utilities/configuration.md +2 -4
  3. package/assets/docs/cli-utilities/workflow-gates.md +27 -3
  4. package/assets/docs/reference/cli-reference.md +1 -1
  5. package/assets/docs/workflows/projects/reviews.md +19 -10
  6. package/assets/public-package-versions.json +4 -4
  7. package/assets/skills/oat-project-autonomous/references/gate-inventory.md +3 -3
  8. package/assets/skills/oat-project-document/references/docs/autonomy-contract.md +3 -3
  9. package/assets/skills/oat-project-implement/SKILL.md +1 -1
  10. package/assets/skills/oat-project-implement/references/docs/autonomy-contract.md +3 -3
  11. package/assets/skills/oat-project-implement/references/phase-execution.md +29 -0
  12. package/assets/skills/oat-project-pr-final/references/docs/autonomy-contract.md +3 -3
  13. package/assets/skills/oat-project-quick-start/references/docs/autonomy-contract.md +3 -3
  14. package/assets/skills/oat-project-review-provide/SKILL.md +124 -26
  15. package/assets/skills/oat-project-review-provide-remote/SKILL.md +64 -15
  16. package/assets/skills/oat-project-review-receive/SKILL.md +21 -1
  17. package/assets/skills/oat-project-review-receive-remote/SKILL.md +39 -2
  18. package/assets/skills/oat-review-provide-remote/SKILL.md +55 -12
  19. package/assets/templates/plan.md +13 -7
  20. package/dist/commands/config/index.js +8 -8
  21. package/dist/commands/gate/child-process.d.ts +32 -0
  22. package/dist/commands/gate/child-process.d.ts.map +1 -0
  23. package/dist/commands/gate/child-process.js +210 -0
  24. package/dist/commands/gate/index.d.ts +2 -31
  25. package/dist/commands/gate/index.d.ts.map +1 -1
  26. package/dist/commands/gate/index.js +24 -150
  27. package/dist/commands/review/latest.d.ts.map +1 -1
  28. package/dist/commands/review/latest.js +22 -9
  29. package/dist/config/resolve.js +1 -1
  30. package/dist/review-remote/body-builder.d.ts +12 -3
  31. package/dist/review-remote/body-builder.d.ts.map +1 -1
  32. package/dist/review-remote/body-builder.js +11 -0
  33. package/dist/review-remote/marker-parser.d.ts +8 -3
  34. package/dist/review-remote/marker-parser.d.ts.map +1 -1
  35. package/dist/review-remote/marker-parser.js +13 -2
  36. package/dist/review-remote/narrowing.d.ts +44 -8
  37. package/dist/review-remote/narrowing.d.ts.map +1 -1
  38. package/dist/review-remote/narrowing.js +106 -10
  39. package/package.json +2 -2
package/assets/agents/oat-reviewer.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: oat-reviewer
3
- version: 1.1.9
3
+ version: 1.2.0
4
4
  description: Unified reviewer for OAT projects - mode-aware verification of requirements/design alignment and code quality. Writes a review artifact to disk by default, or returns structured findings in-memory when dispatched in structured-output mode.
5
5
  tools: Read, Bash, Grep, Glob, Write, Task
6
6
  color: yellow
@@ -55,6 +55,7 @@ You will be given a "Review Scope" block including:
55
55
  - **tasks_in_scope**: Task IDs being reviewed (if task/phase scope)
56
56
  - **oat_output_mode**: Optional output-sink selector. Absent (or any value other than `structured`) means **artifact mode** — write the review artifact to disk per Step 8. `structured` means **structured-output mode** — return a `StructuredFindings` object in-memory and write NO artifact file (see **Structured-Output Mode**). This key parallels the existing `oat_review_invocation` dispatch-payload naming.
57
57
  - **oat_review_invocation**: Optional provenance selector for artifact-mode reviews. Use `manual`, `auto`, or `gate`; default to `manual` when absent.
58
+ - **Code-review provenance**: For artifact-mode code reviews, resolve the authoritative range head with `git rev-parse <authoritative-range-head>^{commit}` and record the resulting full 40-character commit SHA as `oat_review_head_sha`. If the review is narrowed, also record the resolved range, prior artifact path, and prior reviewed head supplied by the caller.
58
59
  - **Gate invocation fields**: For `oat_review_invocation: gate`, the prompt supplies exact `oat_gate_run_id`, `oat_gate_target`, `oat_gate_runtime`, `oat_invocation_model`, `oat_invocation_reasoning_effort`, and `oat_invocation_source` values. Copy them verbatim into artifact frontmatter. They describe OAT's configured invocation, not model self-identification.
59
60
  - **model_axis**: Optional model dispatch state selected by the orchestrator (`selected:<value>`, `inherited`, `not-applicable`, or `host-auto`)
60
61
  - **effort_axis**: Optional effort dispatch state selected by the orchestrator (`selected:<value>`, `provider-default`, `inherited`, `not-applicable`, or `host-auto`)
@@ -357,6 +358,12 @@ oat_review_scope: { scope }
357
358
  oat_review_type: { code|artifact|analysis }
358
359
  oat_review_invocation: { manual|auto|gate }
359
360
  oat_project: { project-path }
361
+ # Code-review only: required full 40-character SHA.
362
+ oat_review_head_sha: { authoritative range head commit SHA }
363
+ # Narrowed code-review only: copy the complete resolved provenance chain.
364
+ oat_review_range: { prior reviewed head }..{ authoritative range head }
365
+ oat_prior_review_artifact: { prior artifact path }
366
+ oat_prior_review_head_sha: { prior artifact's full reviewed head commit SHA }
360
367
  # Gate-only: copy the exact prompt-provided fields below.
361
368
  oat_gate_run_id: { gate run id }
362
369
  oat_gate_target: { configured target id }
@@ -458,6 +465,10 @@ Run the `oat-project-review-receive` skill to convert findings into plan tasks.
458
465
 
459
466
  Gate parsing contract: artifact-mode reviews, including reviews spawned by `oat gate review`, MUST include either the complete `Findings: {N} critical, {N} important, {N} medium, {N} minor` count line or the standard `## Findings` sections shown above with every severity subsection present.
460
467
 
468
+ For every artifact-mode code review, `oat_review_head_sha` is required and must be the full 40-character commit SHA at the head of the authoritative review range. Resolve it with `git rev-parse <authoritative-range-head>^{commit}`. An abbreviated SHA, symbolic ref, or range string is invalid. When the review narrowed, `oat_review_range`, `oat_prior_review_artifact`, and `oat_prior_review_head_sha` are also required; the prior head must likewise be a full 40-character SHA. These code-review fields are independent of the gate-only block and do not apply to artifact, analysis, or structured-output reviews.
469
+
470
+ For a narrowed review, do not restate requirements-coverage claims that this pass did not itself verify. Reference the prior artifact's coverage or mark inherited coverage rows as inherited so the union of passes remains auditable.
471
+
461
472
  For gate-originated artifacts, all six gate-only fields are required when the prompt supplies gate context. Copy the values exactly. Do not parse the provider command, infer values from the target id, or replace configured values with observed/self-reported identity. Any optional self-report belongs in review prose and is non-authoritative; the gate validates the copied frontmatter against its immutable configured invocation record before applying severity thresholds.
462
473
 
463
474
 
package/assets/docs/cli-utilities/configuration.md CHANGED
@@ -540,7 +540,7 @@ Workflow preference keys live under the `workflow.*` namespace:
540
540
  - `workflow.postImplementSequence` — legacy `wait`, `summary`, `pr`, or `docs-pr`, or `{ "preApproval": [...], "postApproval": [...] }`. Legacy values remain strings; structured arrays contain ordered, globally unique `summary`, `document`, and `pr` steps. Pre-approval steps run after final review and before final HiLL approval; post-approval steps run only after that approval. Plain retrieval keeps legacy strings and prints structured values as compact JSON; `--json` returns the raw value.
541
541
  - `workflow.reviewExecutionModel` — `subagent`, `inline`, or `fresh-session`. Default final-review execution model in `oat-project-implement`. `subagent` and `inline` run automatically. `fresh-session` is a soft preference: the skill prints guidance to run the review in another session but still offers escape hatches to `subagent` or `inline` if you change your mind. When unset, the skill prompts.
542
542
  - `workflow.autoReviewAtHillCheckpoints` — boolean. Automatically run the extra lifecycle review when a HiLL checkpoint is reached. This does not control Tier 1 per-phase `oat-reviewer` gates, which run after each phase in Tier 1 regardless of this setting. When unset, the skill prompts.
543
- - `workflow.autoNarrowReReviewScope` — boolean. Auto-narrow re-review scope to fix-task commits only in `oat-project-review-provide`. When unset, the skill prompts.
543
+ - `workflow.autoNarrowReReviewScope` — boolean, default `true`. Re-reviews automatically use the guarded range after the prior matching review's recorded head. Unset and `true` enable narrowing without a prompt; set `false` to opt out and use the nominal full scope.
544
544
  - `workflow.autoArtifactReview.plan` — boolean, default `true`. Automatically run the bounded artifact-review loop for generated `plan.md` files before implementation handoff. Set to `false` only when you intentionally want to skip the plan artifact review.
545
545
  - `workflow.autoArtifactReview.analysis` — boolean, default `true`. Automatically run the bounded accuracy-review loop for generated docs and agent-instructions analysis artifacts before the matching apply workflow consumes them.
546
546
  - `workflow.projectLog` — `auto`, `true`, or `false`; default `auto`. `auto` creates the append-only `project-log.md` on the first lifecycle append, `true` also enables scaffold-time creation, and `false` skips appends when no log exists. An existing artifact remains enabled regardless of the current setting.
@@ -617,7 +617,6 @@ oat config set workflow.createPrOnComplete true --user
617
617
  oat config set workflow.postImplementSequence pr --user
618
618
  oat config set workflow.reviewExecutionModel subagent --user
619
619
  oat config set workflow.autoReviewAtHillCheckpoints true --user
620
- oat config set workflow.autoNarrowReReviewScope true --user
621
620
  oat config set workflow.designMode selective --user
622
621
  oat config set workflow.dispatchCeiling.preset balanced --user
623
622
  oat config adopt dispatch-matrix --user
@@ -668,11 +667,10 @@ Other preferences **depend on per-repo configuration** to be safe. These should
668
667
  **Recommended split for most users:**
669
668
 
670
669
  ```bash
671
- # Personal defaults (apply everywhere)
670
+ # Personal preferences that differ from built-in defaults (apply everywhere)
672
671
  oat config set workflow.hillCheckpointDefault final --user
673
672
  oat config set workflow.reviewExecutionModel subagent --user
674
673
  oat config set workflow.autoReviewAtHillCheckpoints true --user
675
- oat config set workflow.autoNarrowReReviewScope true --user
676
674
 
677
675
  # Per-repo team decisions (set in each repo where they apply)
678
676
  oat config set workflow.archiveOnComplete true --shared
package/assets/docs/cli-utilities/workflow-gates.md CHANGED
@@ -717,8 +717,21 @@ Each liveness tick keeps stdout-idle time and also reports `processAlive` plus
717
717
  the latest metadata-only transcript activity as `lastActivityEvidence` when
718
718
  available. The probe performs bounded depth-two traversal and compares newest
719
719
  mtime plus total size with its spawn baseline. It never reads transcript
720
- contents, never extends a budget, and never changes pass/fail or receive
721
- eligibility.
720
+ contents and never changes pass/fail or receive eligibility.
721
+
722
+ When the hard timeout fires, OAT stops periodic liveness ticks, sends `SIGTERM`,
723
+ schedules the existing `SIGKILL` fallback, and then starts one final transcript
724
+ observation with the timeout timestamp. Once the child closes, result resolution
725
+ waits no longer than the one-second observation grace and does not delay either
726
+ signal. A final sample available before result resolution supersedes older
727
+ in-flight periodic work; otherwise OAT retains the latest valid periodic
728
+ evidence.
729
+
730
+ On a normal child close, OAT waits within the same one-second grace only when a
731
+ periodic transcript observation is already in flight. This preserves late
732
+ evidence but can add up to one second to an otherwise successful execution. The
733
+ one-second observation grace and five-second force-kill fallback are fixed
734
+ safety bounds, not environment-tunable settings.
722
735
 
723
736
  Claude and Cursor evidence has `scope: project-dir`. Codex's date-sharded
724
737
  sessions directory is shared across the runtime, so its evidence has
@@ -726,7 +739,18 @@ sessions directory is shared across the runtime, so its evidence has
726
739
  attributable to this gate child).” Probe errors fail soft to process and stdout
727
740
  telemetry.
728
741
 
729
- Timeout and child-failure envelopes include the latest `activityEvidence`.
742
+ Timeout and child-failure JSON envelopes include the latest `activityEvidence`.
743
+ For human timeout and non-refusal child-failure output, OAT prints a second line
744
+ with this shape:
745
+
746
+ ```text
747
+ Activity evidence: <runtime> <project|ambient> transcript metadata <changed|did not change> since baseline; observed <milliseconds>ms ago; latest transcript change was <milliseconds>ms before observation.
748
+ ```
749
+
750
+ When the evidence scope is ambient, the line ends with `This activity is not
751
+ attributable to this gate child.` Structured refusals omit the extra human
752
+ diagnostic because the refusal itself explains why execution stopped.
753
+
730
754
  Before spawn, the gate also writes a transient marker under the system temp
731
755
  directory at `oat-gate-runs/<runId>.json`; startup diagnostics print its path.
732
756
  The marker records target, runtime, project, review type/scope, start time,
package/assets/docs/reference/cli-reference.md CHANGED
@@ -99,7 +99,7 @@ The `workflow.*` namespace holds user-facing workflow preferences that let you a
99
99
  - `workflow.postImplementSequence` (legacy `wait` | `summary` | `pr` | `docs-pr`, or structured `{preApproval, postApproval}` arrays) — approval-aware post-implementation chaining
100
100
  - `workflow.reviewExecutionModel` (`subagent` | `inline` | `fresh-session`) — default final-review execution model
101
101
  - `workflow.autoReviewAtHillCheckpoints` (`boolean`) — auto-run the extra lifecycle review at HiLL checkpoints
102
- - `workflow.autoNarrowReReviewScope` (`boolean`) — auto-narrow re-review scope to fix-task commits
102
+ - `workflow.autoNarrowReReviewScope` (`boolean`, default `true`) — automatically narrow re-reviews to the guarded range after the prior matching review's recorded head; set `false` to use the nominal full scope
103
103
  - `workflow.autoArtifactReview.plan` (`boolean`, default `true`) — auto-run the bounded `plan.md` artifact-review loop before implementation handoff
104
104
  - `workflow.autoArtifactReview.analysis` (`boolean`, default `true`) — auto-run the bounded accuracy-review loop for generated analysis artifacts before apply workflows consume them
105
105
  - `workflow.gateTimeouts.code` / `workflow.gateTimeouts.artifact` (integer milliseconds from 1,000–14,400,000) — review-type budget defaults below CLI and target overrides
package/assets/docs/workflows/projects/reviews.md CHANGED
@@ -188,21 +188,30 @@ Only an explicit `false` skips a loop. The retry bound comes from `oat_orchestra
188
188
 
189
189
  ## Re-review scope narrowing
190
190
 
191
- When re-reviewing after fix tasks have been applied, `oat-project-review-provide` detects completed `(review)` fix tasks and offers to narrow the re-review scope to just the fix-task commits. This avoids re-examining already-approved code.
191
+ Re-reviews narrow by default to the commits after the prior matching review's recorded head. Set `workflow.autoNarrowReReviewScope` to `false` to opt out and use the nominal full scope. An unset value and an explicit `true` both enable narrowing; the re-review path does not prompt for this decision.
192
192
 
193
- The behavior can be set as a default via `workflow.autoNarrowReReviewScope`:
193
+ Initial reviews have no prior reviewed head and therefore use the nominal full scope. A follow-up review narrows only from a completed review in the same lineage:
194
194
 
195
- - `true` — automatically narrow to fix commits, no prompt
196
- - `false` — always use the full scope, no prompt
197
- - unset (default) — prompt the user on each re-review
195
+ - Lifecycle reviews (`manual` and `auto`) can build only on prior lifecycle reviews for the same project and exact scope.
196
+ - A configured gate can build only on its own prior run for the same exact gate target and scope. It never inherits a lifecycle review or another gate's coverage.
197
+ - Project remote and ad-hoc remote reviews use their own GitHub review-marker lineages. No rail borrows another rail's reviewed head merely because the commit exists.
198
198
 
199
- Typically set at user scope since it's a personal workflow preference:
199
+ Each rail owns its provenance:
200
200
 
201
- ```bash
202
- oat config set workflow.autoNarrowReReviewScope true --user
203
- ```
201
+ - The local project rail checks the matching review artifact and the lineage-qualified tracked Reviews row. The artifact is primary while present; the row preserves the reviewed head after receive, archival, cleanup, or a worktree hand-off. If both sources exist, they must agree.
202
+ - The project remote rail reads same-project, same-scope, same-lineage GitHub review marker blocks.
203
+ - The ad-hoc remote rail reads ad-hoc GitHub review marker blocks and has no project-plan fallback.
204
+ - A configured gate reads its target-qualified gate-owned state and artifacts.
205
+
206
+ A candidate reviewed head must be a full 40-character hexadecimal commit SHA. OAT verifies that the commit exists and is an ancestor of the current review head before accepting the exact `<prior-reviewed-head>..<current-head>` range. An explicit `base_sha=<sha>` or `<sha1>..<sha2>` input overrides automatic narrowing. On the project remote rail, `--narrow` forces narrowing even when the configured preference is `false`, while `--no-narrow` forces the nominal full scope. Nominal scope tokens such as `pNN`, `pNN-tNN`, `pNN-pMM`, and `final` still participate in automatic narrowing; they identify the review subject rather than overriding its range.
207
+
208
+ Automatic narrowing fails open to the nominal full scope and reports why when there is no matching prior review, a legacy artifact or Reviews row has no usable lineage, a reviewed head is missing or invalid, local provenance sources disagree, the commit does not exist, ancestry fails, or remote prior-review discovery is unavailable. A forced remote `--narrow` request instead treats discovery or guard failure as an error. These guards intentionally make narrowing opportunistic: rebases, integration merges, force pushes, shallow history, and worktree consolidation can invalidate the prior commit relationship and cause a full-scope review.
209
+
210
+ Every re-review reports one resolution line naming the selected range, the reason narrowing applied or fell back, and an `empty`, `bookkeeping-only`, or `substantive` classification. Explicit range overrides are classified too. `empty` means the resolved diff has no changed paths. Classification is informational only; every classification still dispatches the review over the complete resolved range.
211
+
212
+ A narrowed artifact names the prior artifact and reviewed head it builds on. It must not restate requirements-coverage claims that the narrowed pass did not verify; it references the prior artifact's coverage or marks inherited rows as inherited so the union of passes remains auditable.
204
213
 
205
- The preference only applies when there are completed fix tasks to narrow to. Initial reviews (before any fix tasks exist) always use the full scope regardless of the preference. See [Workflow preferences in the Configuration guide](../../cli-utilities/configuration.md#workflow-preferences-workflow) for the full list of preference keys.
214
+ See [Workflow preferences in the Configuration guide](../../cli-utilities/configuration.md#workflow-preferences-workflow) for config scopes and the full list of preference keys.
206
215
 
207
216
  ## Phase and final review
208
217
 
package/assets/public-package-versions.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
- "cli": "0.2.23",
3
- "docs-config": "0.2.23",
4
- "docs-theme": "0.2.23",
5
- "docs-transforms": "0.2.23"
2
+ "cli": "0.2.25",
3
+ "docs-config": "0.2.25",
4
+ "docs-theme": "0.2.25",
5
+ "docs-transforms": "0.2.25"
6
6
  }
package/assets/skills/oat-project-autonomous/references/gate-inventory.md CHANGED
@@ -187,7 +187,7 @@ remains.
187
187
  | REVIEWPROVIDE-02 | `oat-project-review-provide` | Missing type or scope | Infer then ask for confirmation | Use caller-provided scope or deterministic project-state inference; ambiguity stops | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
188
188
  | REVIEWPROVIDE-03 | `oat-project-review-provide` | Detached branch | Ask which branch to review | Resolve only from authoritative worktree metadata; otherwise stop | `boundary:repository-policy-approval` | Branch-resolution diagnostic |
189
189
  | REVIEWPROVIDE-04 | `oat-project-review-provide` | Different branch without worktree | Switch, inline-only, or cancel | Do not switch branches or discard context autonomously; stop for a correct checkout/worktree | `boundary:repository-policy-approval` | Branch/worktree diagnostic |
190
- | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow to fixes or review full scope | Use configured preference; when unset, narrow to completed fix commits | `auto-resolve` | Review Scope metadata |
190
+ | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow automatically or use full scope | Use configured preference without prompting: unset or `true` narrows from a guarded prior same-lineage reviewed head, `false` uses full scope; fail open to full scope when provenance or Git guards fail | `auto-resolve` | Review Scope metadata |
191
191
  | REVIEWPROVIDE-06 | `oat-project-review-provide` | Commit-range fallback | Supply a range or accept merge-base | Use a verified merge-base-to-HEAD range when it covers the declared scope; otherwise stop | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
192
192
  | REVIEWPROVIDE-07 | `oat-project-review-provide` | Reviewer delegation authorization | Authorize `oat-reviewer` | Approve once for the exact bounded review scope | `auto-resolve` | Dispatch authorization and record |
193
193
  | REVIEWPROVIDE-08 | `oat-project-review-provide` | Fresh-session or inline fallback | Choose execution route | Use the pre-launch-selected target-preserving route; a blocking review with no adequate route stops | `auto-resolve` / `boundary:missing-credentials` | Dispatch record |
@@ -245,7 +245,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
245
245
  | `oat-project-pr-final/SKILL.md` | `601ac2b890f2 -> NG`; `5eb3949f32e1 -> NG`; `9efcbcee42ea -> NG`; `655d61df0a8f -> NG`; `cf317c17c586 -> PRFINAL-01`; `2de348a391c0 -> PRFINAL-03` |
246
246
  | `oat-project-pr-final/references/docs/autonomy-contract.md` | `* -> NG` |
247
247
  | `oat-project-complete/SKILL.md` | `6ed459f9e462 -> NG`; `a167d03559fa -> NG`; `79c2eeed668c -> COMPLETE-01`; `2c1514b9d9af -> COMPLETE-01`; `31c750b4fea7 -> COMPLETE-01`; `cfba413b1293 -> COMPLETE-01`; `ffcdc9d576c0 -> COMPLETE-01`; `7fcfce0423ac -> COMPLETE-01`; `9497d9f94eed -> COMPLETE-01`; `7b59c728d3fb -> COMPLETE-01`; `48e10a9636fe -> COMPLETE-01`; `c0dad37fc166 -> COMPLETE-01`; `aa9a36243ec1 -> COMPLETE-01`; `7bcbf58b54e9 -> NG`; `4c7f88a7f942 -> COMPLETE-02`; `6a1a95acc8cc -> COMPLETE-02`; `3b559956b3eb -> COMPLETE-03`; `14d161cdf99b -> COMPLETE-03`; `12f7c30a54c8 -> NG`; `fffe5eea5ebd -> NG` |
248
- | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `fab62c510bd0 -> REVIEWPROVIDE-05`; `a9f30853c867 -> REVIEWPROVIDE-05`; `0929c916fc20 -> REVIEWPROVIDE-05`; `f9a37c63afab -> REVIEWPROVIDE-05`; `687bb9368f92 -> REVIEWPROVIDE-05`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
248
+ | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
249
249
  | `oat-project-review-receive/SKILL.md` | `9b8a3743d626 -> NG`; `df49c8c6f192 -> NG`; `4ee8730382d3 -> NG`; `655d61df0a8f -> NG`; `765f897d67ac -> NG`; `53b58d16dd32 -> NG`; `fb8755a3bdf4 -> NG`; `c8ab5dd90075 -> NG`; `1f7dd98dff2f -> NG`; `56f78c6740e6 -> NG`; `76f5fb5a88cd -> NG`; `085abfa3599f -> REVIEWRECEIVE-01`; `3ad3aadb8c60 -> NG`; `a7d114059bb6 -> NG`; `ac88cfaa83d9 -> NG`; `3f758313fedb -> REVIEWRECEIVE-08`; `f31f07284718 -> REVIEWRECEIVE-02`; `aba178a21441 -> REVIEWRECEIVE-04`; `a37e601cd731 -> REVIEWRECEIVE-05`; `20e05e1a4381 -> REVIEWRECEIVE-06`; `90001dadf75f -> REVIEWRECEIVE-07`; `f8fd58180ecf -> NG`; `c3abcdc02d9f -> NG`; `f2ebdd6abb9b -> NG` |
250
250
  | `oat-project-review-provide/SKILL.md` | `2e794bf4fc4a -> REVIEWPROVIDE-08`; `5441ab977b46 -> REVIEWPROVIDE-08` |
251
251
  | `oat-project-review-provide/SKILL.md` | `f4238ebb1887 -> NG`; `0360fa2db9a5 -> NG` |
@@ -297,7 +297,7 @@ inventory`). The file-and-line mappings below were captured against that commit.
297
297
  | `oat-project-summary/SKILL.md` | `4,7,30 -> NG`; `86 -> SUMMARY-01`; `201,203,209-210,249,257,297 -> NG` |
298
298
  | `oat-project-pr-final/SKILL.md` | `4,7,26,43 -> NG`; `104 -> PRFINAL-01` |
299
299
  | `oat-project-complete/SKILL.md` | `7,16 -> NG`; `57,61,63,80,89,92,95,103,105,114,124 -> COMPLETE-01`; `140 -> NG`; `205,214 -> COMPLETE-02`; `219,223 -> COMPLETE-03`; `283,468 -> NG` |
300
- | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `911,927 -> NG` |
300
+ | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `915,931 -> NG` |
301
301
  | `oat-project-review-receive/SKILL.md` | `4,7,26,40,71,128,178,211,215,252,259 -> NG`; `267 -> REVIEWRECEIVE-01`; `273-274,278 -> NG`; `482 -> REVIEWRECEIVE-08`; `517 -> REVIEWRECEIVE-02`; `548 -> REVIEWRECEIVE-04`; `590 -> REVIEWRECEIVE-05`; `614 -> REVIEWRECEIVE-06`; `647 -> REVIEWRECEIVE-07`; `721,724 -> NG` |
302
302
  | `oat-dispatch-subagents/SKILL.md` | `94,98 -> DISPATCH-01`; `110 -> PDISPATCH-01`; `117,123 -> DISPATCH-02`; `126 -> PDISPATCH-01` |
303
303
  | `oat-dispatch-subagents/references/provider-cursor.md` | `40,49 -> NG` |
package/assets/skills/oat-project-document/references/docs/autonomy-contract.md CHANGED
@@ -187,7 +187,7 @@ remains.
187
187
  | REVIEWPROVIDE-02 | `oat-project-review-provide` | Missing type or scope | Infer then ask for confirmation | Use caller-provided scope or deterministic project-state inference; ambiguity stops | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
188
188
  | REVIEWPROVIDE-03 | `oat-project-review-provide` | Detached branch | Ask which branch to review | Resolve only from authoritative worktree metadata; otherwise stop | `boundary:repository-policy-approval` | Branch-resolution diagnostic |
189
189
  | REVIEWPROVIDE-04 | `oat-project-review-provide` | Different branch without worktree | Switch, inline-only, or cancel | Do not switch branches or discard context autonomously; stop for a correct checkout/worktree | `boundary:repository-policy-approval` | Branch/worktree diagnostic |
190
- | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow to fixes or review full scope | Use configured preference; when unset, narrow to completed fix commits | `auto-resolve` | Review Scope metadata |
190
+ | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow automatically or use full scope | Use configured preference without prompting: unset or `true` narrows from a guarded prior same-lineage reviewed head, `false` uses full scope; fail open to full scope when provenance or Git guards fail | `auto-resolve` | Review Scope metadata |
191
191
  | REVIEWPROVIDE-06 | `oat-project-review-provide` | Commit-range fallback | Supply a range or accept merge-base | Use a verified merge-base-to-HEAD range when it covers the declared scope; otherwise stop | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
192
192
  | REVIEWPROVIDE-07 | `oat-project-review-provide` | Reviewer delegation authorization | Authorize `oat-reviewer` | Approve once for the exact bounded review scope | `auto-resolve` | Dispatch authorization and record |
193
193
  | REVIEWPROVIDE-08 | `oat-project-review-provide` | Fresh-session or inline fallback | Choose execution route | Use the pre-launch-selected target-preserving route; a blocking review with no adequate route stops | `auto-resolve` / `boundary:missing-credentials` | Dispatch record |
@@ -245,7 +245,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
245
245
  | `oat-project-pr-final/SKILL.md` | `601ac2b890f2 -> NG`; `5eb3949f32e1 -> NG`; `9efcbcee42ea -> NG`; `655d61df0a8f -> NG`; `cf317c17c586 -> PRFINAL-01`; `2de348a391c0 -> PRFINAL-03` |
246
246
  | `oat-project-pr-final/references/docs/autonomy-contract.md` | `* -> NG` |
247
247
  | `oat-project-complete/SKILL.md` | `6ed459f9e462 -> NG`; `a167d03559fa -> NG`; `79c2eeed668c -> COMPLETE-01`; `2c1514b9d9af -> COMPLETE-01`; `31c750b4fea7 -> COMPLETE-01`; `cfba413b1293 -> COMPLETE-01`; `ffcdc9d576c0 -> COMPLETE-01`; `7fcfce0423ac -> COMPLETE-01`; `9497d9f94eed -> COMPLETE-01`; `7b59c728d3fb -> COMPLETE-01`; `48e10a9636fe -> COMPLETE-01`; `c0dad37fc166 -> COMPLETE-01`; `aa9a36243ec1 -> COMPLETE-01`; `7bcbf58b54e9 -> NG`; `4c7f88a7f942 -> COMPLETE-02`; `6a1a95acc8cc -> COMPLETE-02`; `3b559956b3eb -> COMPLETE-03`; `14d161cdf99b -> COMPLETE-03`; `12f7c30a54c8 -> NG`; `fffe5eea5ebd -> NG` |
248
- | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `fab62c510bd0 -> REVIEWPROVIDE-05`; `a9f30853c867 -> REVIEWPROVIDE-05`; `0929c916fc20 -> REVIEWPROVIDE-05`; `f9a37c63afab -> REVIEWPROVIDE-05`; `687bb9368f92 -> REVIEWPROVIDE-05`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
248
+ | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
249
249
  | `oat-project-review-receive/SKILL.md` | `9b8a3743d626 -> NG`; `df49c8c6f192 -> NG`; `4ee8730382d3 -> NG`; `655d61df0a8f -> NG`; `765f897d67ac -> NG`; `53b58d16dd32 -> NG`; `fb8755a3bdf4 -> NG`; `c8ab5dd90075 -> NG`; `1f7dd98dff2f -> NG`; `56f78c6740e6 -> NG`; `76f5fb5a88cd -> NG`; `085abfa3599f -> REVIEWRECEIVE-01`; `3ad3aadb8c60 -> NG`; `a7d114059bb6 -> NG`; `ac88cfaa83d9 -> NG`; `3f758313fedb -> REVIEWRECEIVE-08`; `f31f07284718 -> REVIEWRECEIVE-02`; `aba178a21441 -> REVIEWRECEIVE-04`; `a37e601cd731 -> REVIEWRECEIVE-05`; `20e05e1a4381 -> REVIEWRECEIVE-06`; `90001dadf75f -> REVIEWRECEIVE-07`; `f8fd58180ecf -> NG`; `c3abcdc02d9f -> NG`; `f2ebdd6abb9b -> NG` |
250
250
  | `oat-project-review-provide/SKILL.md` | `2e794bf4fc4a -> REVIEWPROVIDE-08`; `5441ab977b46 -> REVIEWPROVIDE-08` |
251
251
  | `oat-project-review-provide/SKILL.md` | `f4238ebb1887 -> NG`; `0360fa2db9a5 -> NG` |
@@ -297,7 +297,7 @@ inventory`). The file-and-line mappings below were captured against that commit.
297
297
  | `oat-project-summary/SKILL.md` | `4,7,30 -> NG`; `86 -> SUMMARY-01`; `201,203,209-210,249,257,297 -> NG` |
298
298
  | `oat-project-pr-final/SKILL.md` | `4,7,26,43 -> NG`; `104 -> PRFINAL-01` |
299
299
  | `oat-project-complete/SKILL.md` | `7,16 -> NG`; `57,61,63,80,89,92,95,103,105,114,124 -> COMPLETE-01`; `140 -> NG`; `205,214 -> COMPLETE-02`; `219,223 -> COMPLETE-03`; `283,468 -> NG` |
300
- | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `911,927 -> NG` |
300
+ | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `915,931 -> NG` |
301
301
  | `oat-project-review-receive/SKILL.md` | `4,7,26,40,71,128,178,211,215,252,259 -> NG`; `267 -> REVIEWRECEIVE-01`; `273-274,278 -> NG`; `482 -> REVIEWRECEIVE-08`; `517 -> REVIEWRECEIVE-02`; `548 -> REVIEWRECEIVE-04`; `590 -> REVIEWRECEIVE-05`; `614 -> REVIEWRECEIVE-06`; `647 -> REVIEWRECEIVE-07`; `721,724 -> NG` |
302
302
  | `oat-dispatch-subagents/SKILL.md` | `94,98 -> DISPATCH-01`; `110 -> PDISPATCH-01`; `117,123 -> DISPATCH-02`; `126 -> PDISPATCH-01` |
303
303
  | `oat-dispatch-subagents/references/provider-cursor.md` | `40,49 -> NG` |
package/assets/skills/oat-project-implement/SKILL.md CHANGED
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: oat-project-implement
3
- version: 2.2.1
3
+ version: 2.2.2
4
4
  description: Use when plan.md is ready for execution. Dispatches one phase implementer per phase, owns independent phase review and bounded fix routing, and supports plan-declared worktree-isolated parallel phases.
5
5
  oat_gateable: true
6
6
  argument-hint: '[--retry-limit <N>] [--dry-run]'
package/assets/skills/oat-project-implement/references/docs/autonomy-contract.md CHANGED
@@ -187,7 +187,7 @@ remains.
187
187
  | REVIEWPROVIDE-02 | `oat-project-review-provide` | Missing type or scope | Infer then ask for confirmation | Use caller-provided scope or deterministic project-state inference; ambiguity stops | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
188
188
  | REVIEWPROVIDE-03 | `oat-project-review-provide` | Detached branch | Ask which branch to review | Resolve only from authoritative worktree metadata; otherwise stop | `boundary:repository-policy-approval` | Branch-resolution diagnostic |
189
189
  | REVIEWPROVIDE-04 | `oat-project-review-provide` | Different branch without worktree | Switch, inline-only, or cancel | Do not switch branches or discard context autonomously; stop for a correct checkout/worktree | `boundary:repository-policy-approval` | Branch/worktree diagnostic |
190
- | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow to fixes or review full scope | Use configured preference; when unset, narrow to completed fix commits | `auto-resolve` | Review Scope metadata |
190
+ | REVIEWPROVIDE-05 | `oat-project-review-provide` | Re-review narrowing | Narrow automatically or use full scope | Use configured preference without prompting: unset or `true` narrows from a guarded prior same-lineage reviewed head, `false` uses full scope; fail open to full scope when provenance or Git guards fail | `auto-resolve` | Review Scope metadata |
191
191
  | REVIEWPROVIDE-06 | `oat-project-review-provide` | Commit-range fallback | Supply a range or accept merge-base | Use a verified merge-base-to-HEAD range when it covers the declared scope; otherwise stop | `auto-resolve` / `boundary:product-judgment` | Review Scope metadata |
192
192
  | REVIEWPROVIDE-07 | `oat-project-review-provide` | Reviewer delegation authorization | Authorize `oat-reviewer` | Approve once for the exact bounded review scope | `auto-resolve` | Dispatch authorization and record |
193
193
  | REVIEWPROVIDE-08 | `oat-project-review-provide` | Fresh-session or inline fallback | Choose execution route | Use the pre-launch-selected target-preserving route; a blocking review with no adequate route stops | `auto-resolve` / `boundary:missing-credentials` | Dispatch record |
@@ -245,7 +245,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
245
245
  | `oat-project-pr-final/SKILL.md` | `601ac2b890f2 -> NG`; `5eb3949f32e1 -> NG`; `9efcbcee42ea -> NG`; `655d61df0a8f -> NG`; `cf317c17c586 -> PRFINAL-01`; `2de348a391c0 -> PRFINAL-03` |
246
246
  | `oat-project-pr-final/references/docs/autonomy-contract.md` | `* -> NG` |
247
247
  | `oat-project-complete/SKILL.md` | `6ed459f9e462 -> NG`; `a167d03559fa -> NG`; `79c2eeed668c -> COMPLETE-01`; `2c1514b9d9af -> COMPLETE-01`; `31c750b4fea7 -> COMPLETE-01`; `cfba413b1293 -> COMPLETE-01`; `ffcdc9d576c0 -> COMPLETE-01`; `7fcfce0423ac -> COMPLETE-01`; `9497d9f94eed -> COMPLETE-01`; `7b59c728d3fb -> COMPLETE-01`; `48e10a9636fe -> COMPLETE-01`; `c0dad37fc166 -> COMPLETE-01`; `aa9a36243ec1 -> COMPLETE-01`; `7bcbf58b54e9 -> NG`; `4c7f88a7f942 -> COMPLETE-02`; `6a1a95acc8cc -> COMPLETE-02`; `3b559956b3eb -> COMPLETE-03`; `14d161cdf99b -> COMPLETE-03`; `12f7c30a54c8 -> NG`; `fffe5eea5ebd -> NG` |
248
- | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `fab62c510bd0 -> REVIEWPROVIDE-05`; `a9f30853c867 -> REVIEWPROVIDE-05`; `0929c916fc20 -> REVIEWPROVIDE-05`; `f9a37c63afab -> REVIEWPROVIDE-05`; `687bb9368f92 -> REVIEWPROVIDE-05`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
248
+ | `oat-project-review-provide/SKILL.md` | `1f4b981cac8b -> NG`; `adaeca152bb2 -> NG`; `2f7c201c3c06 -> NG`; `88f79700afdc -> NG`; `655d61df0a8f -> NG`; `efafde9ef5a0 -> NG`; `d2a3861d6323 -> REVIEWPROVIDE-02`; `65f5b9cf49cd -> REVIEWPROVIDE-04`; `962cb38d246a -> REVIEWPROVIDE-04`; `1a568483ba0b -> REVIEWPROVIDE-04`; `610e27edfe85 -> REVIEWPROVIDE-04`; `bb0096e95c47 -> REVIEWPROVIDE-06`; `55f6357a987d -> REVIEWPROVIDE-06`; `1bee61f8531c -> REVIEWPROVIDE-07`; `3d35091607a1 -> REVIEWPROVIDE-08`; `fb40c4341c4c -> NG`; `b22d16885150 -> NG`; `d2b25906242e -> REVIEWPROVIDE-08`; `fd8ebf72b3c4 -> NG`; `fcb9de611ff3 -> NG`; `d2a838dfb18d -> NG`; `c3d50ea7cf69 -> NG`; `09b1b8dd445c -> NG`; `7acc8f3718d2 -> REVIEWPROVIDE-09`; `b2fa883fc4a2 -> NG`; `fe4421531b4c -> NG` |
249
249
  | `oat-project-review-receive/SKILL.md` | `9b8a3743d626 -> NG`; `df49c8c6f192 -> NG`; `4ee8730382d3 -> NG`; `655d61df0a8f -> NG`; `765f897d67ac -> NG`; `53b58d16dd32 -> NG`; `fb8755a3bdf4 -> NG`; `c8ab5dd90075 -> NG`; `1f7dd98dff2f -> NG`; `56f78c6740e6 -> NG`; `76f5fb5a88cd -> NG`; `085abfa3599f -> REVIEWRECEIVE-01`; `3ad3aadb8c60 -> NG`; `a7d114059bb6 -> NG`; `ac88cfaa83d9 -> NG`; `3f758313fedb -> REVIEWRECEIVE-08`; `f31f07284718 -> REVIEWRECEIVE-02`; `aba178a21441 -> REVIEWRECEIVE-04`; `a37e601cd731 -> REVIEWRECEIVE-05`; `20e05e1a4381 -> REVIEWRECEIVE-06`; `90001dadf75f -> REVIEWRECEIVE-07`; `f8fd58180ecf -> NG`; `c3abcdc02d9f -> NG`; `f2ebdd6abb9b -> NG` |
250
250
  | `oat-project-review-provide/SKILL.md` | `2e794bf4fc4a -> REVIEWPROVIDE-08`; `5441ab977b46 -> REVIEWPROVIDE-08` |
251
251
  | `oat-project-review-provide/SKILL.md` | `f4238ebb1887 -> NG`; `0360fa2db9a5 -> NG` |
@@ -297,7 +297,7 @@ inventory`). The file-and-line mappings below were captured against that commit.
297
297
  | `oat-project-summary/SKILL.md` | `4,7,30 -> NG`; `86 -> SUMMARY-01`; `201,203,209-210,249,257,297 -> NG` |
298
298
  | `oat-project-pr-final/SKILL.md` | `4,7,26,43 -> NG`; `104 -> PRFINAL-01` |
299
299
  | `oat-project-complete/SKILL.md` | `7,16 -> NG`; `57,61,63,80,89,92,95,103,105,114,124 -> COMPLETE-01`; `140 -> NG`; `205,214 -> COMPLETE-02`; `219,223 -> COMPLETE-03`; `283,468 -> NG` |
300
- | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `911,927 -> NG` |
300
+ | `oat-project-review-provide/SKILL.md` | `4,7,28,34,44,93 -> NG`; `166 -> REVIEWPROVIDE-02`; `236,239-240,261 -> REVIEWPROVIDE-04`; `308,314-316,318 -> REVIEWPROVIDE-05`; `370,373 -> REVIEWPROVIDE-06`; `621 -> REVIEWPROVIDE-07`; `632,664 -> REVIEWPROVIDE-08`; `645,647,751,770-772,778 -> NG`; `869 -> REVIEWPROVIDE-09`; `915,931 -> NG` |
301
301
  | `oat-project-review-receive/SKILL.md` | `4,7,26,40,71,128,178,211,215,252,259 -> NG`; `267 -> REVIEWRECEIVE-01`; `273-274,278 -> NG`; `482 -> REVIEWRECEIVE-08`; `517 -> REVIEWRECEIVE-02`; `548 -> REVIEWRECEIVE-04`; `590 -> REVIEWRECEIVE-05`; `614 -> REVIEWRECEIVE-06`; `647 -> REVIEWRECEIVE-07`; `721,724 -> NG` |
302
302
  | `oat-dispatch-subagents/SKILL.md` | `94,98 -> DISPATCH-01`; `110 -> PDISPATCH-01`; `117,123 -> DISPATCH-02`; `126 -> PDISPATCH-01` |
303
303
  | `oat-dispatch-subagents/references/provider-cursor.md` | `40,49 -> NG` |
package/assets/skills/oat-project-implement/references/phase-execution.md CHANGED
@@ -228,6 +228,33 @@ Gate retry rounds use the same orchestration retry limit. Gate independence,
228
228
  configured provenance, liveness telemetry, and fail-closed behavior are
229
229
  unchanged.
230
230
 
231
+ #### Reviews Ledger Mutation Contract
232
+
233
+ Apply this contract whenever the implementation workflow directly dispositions
234
+ a `## Reviews` event or re-points its artifact during archival or receive
235
+ reconciliation. This includes Step 7 phase/fix outcomes and every checkpoint,
236
+ final-review, gate-receive, and closeout path that mutates a Reviews row:
237
+
238
+ - Parse the table header and resolve `Scope`, `Type`, `Status`, `Date`,
239
+ `Artifact`, `Reviewed Head`, `Invocation`, and `Gate Target` by header name;
240
+ never address a known cell by a fixed position.
241
+ - For a legacy five-column table, append the provenance columns (`Reviewed
242
+ Head`, `Invocation`, and `Gate Target`) to the header and separator, then pad
243
+ every existing row with `-`. For any shorter row in an already widened table,
244
+ pad missing cells with `-` through the current header width before mutation.
245
+ - Preserve every unknown column in its original position and preserve every
246
+ existing known value unless the current operation explicitly advances that
247
+ cell. Never truncate a row to five, eight, or any other assumed width.
248
+ - Populate missing provenance from the event's validated review artifact:
249
+ accept `oat_review_head_sha` only as a full 40-character hexadecimal commit
250
+ SHA, preserve `oat_review_invocation`, and preserve `oat_gate_target` only
251
+ for a gate invocation. Use `-` when validated provenance is unavailable;
252
+ never infer it from the current HEAD, reviewer identity, scope, or target.
253
+ - An archive re-point changes only the bound event's `Artifact` cell (and a
254
+ monotonic status transition when required). It must preserve existing
255
+ provenance and unknown cells, while filling missing provenance when the
256
+ source artifact supplies validated values.
257
+
231
258
  ### Parallel Group Execution
232
259
 
233
260
  For a multi-phase schedule entry:
@@ -269,6 +296,8 @@ After each phase or parallel group:
269
296
  `fixes_completed` / `passed` as appropriate;
270
297
  - never select review bookkeeping by scope alone, replace an earlier event, or
271
298
  move an event status backward;
299
+ - apply the Reviews Ledger Mutation Contract above before every disposition or
300
+ archive re-point;
272
301
  - update `state.md` current task, last commit, and timestamp;
273
302
  - remove legacy `oat_execution_mode: subagent-driven`; and
274
303
  - preserve any configured retry override.