@open-agent-toolkit/cli 0.2.25 → 0.2.26
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.
- package/assets/docs/cli-utilities/configuration.md +42 -11
- package/assets/docs/workflows/projects/dispatch-ceiling.md +67 -16
- package/assets/public-package-versions.json +4 -4
- package/assets/skills/oat-project-autonomous/references/gate-inventory.md +1 -1
- package/assets/skills/oat-project-document/references/docs/autonomy-contract.md +1 -1
- package/assets/skills/oat-project-implement/SKILL.md +9 -11
- package/assets/skills/oat-project-implement/references/dispatch-and-dry-run.md +18 -9
- package/assets/skills/oat-project-implement/references/docs/autonomy-contract.md +1 -1
- package/assets/skills/oat-project-implement/references/phase-execution.md +13 -4
- package/assets/skills/oat-project-pr-final/references/docs/autonomy-contract.md +1 -1
- package/assets/skills/oat-project-quick-start/references/docs/autonomy-contract.md +1 -1
- package/dist/commands/config/index.d.ts.map +1 -1
- package/dist/commands/config/index.js +27 -3
- package/dist/commands/project/dispatch-ceiling/index.d.ts.map +1 -1
- package/dist/commands/project/dispatch-ceiling/index.js +90 -0
- package/dist/config/dispatch-notices.d.ts +8 -0
- package/dist/config/dispatch-notices.d.ts.map +1 -0
- package/dist/config/dispatch-notices.js +79 -0
- package/dist/config/dispatch-policy-options.d.ts +2 -0
- package/dist/config/dispatch-policy-options.d.ts.map +1 -1
- package/dist/config/dispatch-policy-options.js +14 -2
- package/dist/providers/identity/dispatch-report.d.ts +17 -0
- package/dist/providers/identity/dispatch-report.d.ts.map +1 -1
- package/dist/providers/identity/dispatch-report.js +30 -0
- package/package.json +2 -2
|
@@ -308,6 +308,15 @@ Adoption fills missing provider/tier cells and preserves explicit existing
|
|
|
308
308
|
values. Planning shows the complete bundled recommendation before asking for
|
|
309
309
|
this scope, then rechecks the effective ladder. If explicit cells still leave
|
|
310
310
|
the ladder incomplete, readiness blocks; OAT does not overwrite them.
|
|
311
|
+
`workflow.dispatchCeiling.recommendationVersion` describes only the bundled
|
|
312
|
+
recommendation that was adopted. Dispatch targets, structured notices, and
|
|
313
|
+
runtime disclosure come from the effective ladder after explicit cells have
|
|
314
|
+
been preserved.
|
|
315
|
+
|
|
316
|
+
A recommended Fable target may require model access from the executing
|
|
317
|
+
provider. The adopting organization is responsible for confirming its
|
|
318
|
+
applicable retention policy. OAT does not determine model access or
|
|
319
|
+
organizational retention eligibility.
|
|
311
320
|
|
|
312
321
|
Scope determines ownership and Codex/Cursor materialization:
|
|
313
322
|
|
|
@@ -366,13 +375,13 @@ tiers are trimmed for readability.
|
|
|
366
375
|
|
|
367
376
|
The bundled recommendation covers 13 Codex model/effort combinations: Luna and
|
|
368
377
|
Terra at `low`, `medium`, `high`, and `xhigh`, plus Sol at those efforts and
|
|
369
|
-
`max`. Claude covers `haiku`, `sonnet`, `opus`, and `fable`.
|
|
370
|
-
candidates across four tiers, drawn from a materialization
|
|
371
|
-
|
|
372
|
-
Fable), GPT, and Grok; the two figures differ because some
|
|
373
|
-
stay materializable without being recommended. An explicit
|
|
374
|
-
each flat ladder ID to a separate bracket-form frontmatter
|
|
375
|
-
and skills never derive or normalize either form.
|
|
378
|
+
`max`. Claude covers `haiku`, `sonnet`, `opus`, and `fable`. The recommendation
|
|
379
|
+
carries 14 Cursor candidates across four tiers, drawn from a materialization
|
|
380
|
+
catalogue with 18 catalogued multi-family flat IDs spanning Composer, Claude
|
|
381
|
+
(Sonnet, Opus, and Fable), GPT, and Grok; the two figures differ because some
|
|
382
|
+
approved mappings stay materializable without being recommended. An explicit
|
|
383
|
+
mapping connects each flat ladder ID to a separate bracket-form frontmatter
|
|
384
|
+
model; configuration and skills never derive or normalize either form.
|
|
376
385
|
|
|
377
386
|
The corresponding pinned Codex variant catalogue includes
|
|
378
387
|
`gpt-5.6-luna-high`, `gpt-5.6-terra-xhigh`, `gpt-5.6-sol-high`, and
|
|
@@ -432,6 +441,10 @@ oat project dispatch-ceiling resolve \
|
|
|
432
441
|
--ceiling-tier high \
|
|
433
442
|
--candidate-model gpt-5.6-terra \
|
|
434
443
|
--candidate-effort medium \
|
|
444
|
+
--task-class default-implementation \
|
|
445
|
+
--task-effort medium \
|
|
446
|
+
--report-scope p02 \
|
|
447
|
+
--report-action implementation \
|
|
435
448
|
--json
|
|
436
449
|
|
|
437
450
|
oat project dispatch-ceiling resolve \
|
|
@@ -439,6 +452,9 @@ oat project dispatch-ceiling resolve \
|
|
|
439
452
|
--role implementer \
|
|
440
453
|
--ceiling-tier high \
|
|
441
454
|
--candidate-model sonnet \
|
|
455
|
+
--task-class default-implementation \
|
|
456
|
+
--report-scope p02 \
|
|
457
|
+
--report-action implementation \
|
|
442
458
|
--json
|
|
443
459
|
|
|
444
460
|
oat project dispatch-ceiling resolve \
|
|
@@ -446,19 +462,34 @@ oat project dispatch-ceiling resolve \
|
|
|
446
462
|
--role implementer \
|
|
447
463
|
--ceiling-tier high \
|
|
448
464
|
--candidate-model gpt-5.6-sol-high \
|
|
465
|
+
--task-class default-implementation \
|
|
466
|
+
--report-scope p02 \
|
|
467
|
+
--report-action implementation \
|
|
449
468
|
--json
|
|
450
469
|
```
|
|
451
470
|
|
|
471
|
+
Use the same classification flags and `--report-action fix` for bounded fixes.
|
|
472
|
+
Reviewer routes carry neither `--task-class` nor `--task-effort`; the CLI
|
|
473
|
+
rejects classification flags for reviewers. Before any implementation, fix, or
|
|
474
|
+
reviewer launch, display `dispatchReport.notices` and the formatted report. The
|
|
475
|
+
effective resolver target—not the recommendation version—owns runtime
|
|
476
|
+
disclosure.
|
|
477
|
+
|
|
452
478
|
`--ceiling-tier` is invocation-only. It accepts `economy`, `balanced`, `high`,
|
|
453
479
|
or `frontier`, overrides layered active-policy ceilings for that call, and never
|
|
454
480
|
writes user, shared, local, or project configuration. JSON reports top-level
|
|
455
481
|
`source: invocation`; `providers.<provider>.cellSource` still identifies the
|
|
456
482
|
config layer that owns the selected candidate.
|
|
457
483
|
|
|
458
|
-
The resolver fails closed when a candidate is
|
|
459
|
-
ambiguous, malformed, or cannot compile exact provider controls.
|
|
460
|
-
|
|
461
|
-
|
|
484
|
+
The resolver fails closed when a requested candidate is above the maximum,
|
|
485
|
+
ambiguous, malformed, or cannot compile exact provider controls. Omitting an
|
|
486
|
+
exact candidate from a managed named-cap implementation or fix currently
|
|
487
|
+
preserves compatibility by resolving successfully at the cap; with report
|
|
488
|
+
context, human and JSON output include the
|
|
489
|
+
`managed-capped-selection-skipped` warning. Callers must surface that warning
|
|
490
|
+
and select an exact candidate before launch. `--preferred` remains
|
|
491
|
+
compatibility behavior for legacy scalar ceilings and managed `Uncapped`; it is
|
|
492
|
+
not the exact managed phase-agent path.
|
|
462
493
|
|
|
463
494
|
### Provider enforcement and materialization
|
|
464
495
|
|
|
@@ -63,6 +63,10 @@ Adoption fills missing provider/tier cells and records
|
|
|
63
63
|
existing cells. Planning shows the complete recommendation before asking which
|
|
64
64
|
scope should own it. If the resulting ladder is still missing or incomplete,
|
|
65
65
|
planning remains blocked rather than replacing the user's explicit values.
|
|
66
|
+
The recommendation version describes only the bundled recommendation. After
|
|
67
|
+
preserving existing cells, OAT resolves the effective ladder and uses that
|
|
68
|
+
effective result—not the recommendation version—for dispatch targets and
|
|
69
|
+
runtime disclosure.
|
|
66
70
|
|
|
67
71
|
### Upgrading to a newer recommendation version
|
|
68
72
|
|
|
@@ -91,6 +95,12 @@ does not compare the two rungs. Both models remain in the pin catalog and stay
|
|
|
91
95
|
available to a hand-edited ladder. An adopter still on the prior version keeps their existing
|
|
92
96
|
Cursor tiers untouched until they take one of the actions above.
|
|
93
97
|
|
|
98
|
+
The terminal Fable target may require model access from the executing provider.
|
|
99
|
+
The adopting organization is responsible for confirming its applicable
|
|
100
|
+
retention policy. OAT does not determine model access or organizational
|
|
101
|
+
retention eligibility; recommendation membership and catalogue presence are
|
|
102
|
+
configuration data, not an eligibility decision.
|
|
103
|
+
|
|
94
104
|
The terminal entries in that version are chosen, not incidental. Because the
|
|
95
105
|
final candidate in a tier is the target its implementation-phase self-review
|
|
96
106
|
pins, reordering a tier changes who reviews it even when the membership is
|
|
@@ -274,6 +284,10 @@ oat project dispatch-ceiling resolve \
|
|
|
274
284
|
--ceiling-tier high \
|
|
275
285
|
--candidate-model gpt-5.6-terra \
|
|
276
286
|
--candidate-effort medium \
|
|
287
|
+
--task-class default-implementation \
|
|
288
|
+
--task-effort medium \
|
|
289
|
+
--report-scope p02 \
|
|
290
|
+
--report-action implementation \
|
|
277
291
|
--json
|
|
278
292
|
|
|
279
293
|
# Claude: exact model argument
|
|
@@ -282,6 +296,9 @@ oat project dispatch-ceiling resolve \
|
|
|
282
296
|
--role implementer \
|
|
283
297
|
--ceiling-tier high \
|
|
284
298
|
--candidate-model sonnet \
|
|
299
|
+
--task-class default-implementation \
|
|
300
|
+
--report-scope p02 \
|
|
301
|
+
--report-action implementation \
|
|
285
302
|
--json
|
|
286
303
|
|
|
287
304
|
# Cursor: exact opaque configured string
|
|
@@ -290,9 +307,16 @@ oat project dispatch-ceiling resolve \
|
|
|
290
307
|
--role implementer \
|
|
291
308
|
--ceiling-tier high \
|
|
292
309
|
--candidate-model gpt-5.6-sol-high \
|
|
310
|
+
--task-class default-implementation \
|
|
311
|
+
--report-scope p02 \
|
|
312
|
+
--report-action implementation \
|
|
293
313
|
--json
|
|
294
314
|
```
|
|
295
315
|
|
|
316
|
+
Use the same classification flags and `--report-action fix` for a bounded fix.
|
|
317
|
+
Reviewer routes use neither `--task-class` nor `--task-effort`; the CLI rejects
|
|
318
|
+
classification flags for reviewers.
|
|
319
|
+
|
|
296
320
|
`--ceiling-tier` accepts `economy`, `balanced`, `high`, or `frontier`. It
|
|
297
321
|
overrides a layered active-policy ceiling for that resolver invocation only. It
|
|
298
322
|
does not modify user, shared, local, or project configuration.
|
|
@@ -306,10 +330,14 @@ Successful JSON reports:
|
|
|
306
330
|
`selection.requestedCandidate`
|
|
307
331
|
- the exact provider-specific `dispatchArgs`
|
|
308
332
|
|
|
309
|
-
The resolver rejects
|
|
310
|
-
|
|
311
|
-
|
|
312
|
-
|
|
333
|
+
The resolver rejects an above-ceiling candidate, an ambiguous route, malformed
|
|
334
|
+
ordering, a reviewer candidate request, or controls that cannot compile
|
|
335
|
+
exactly. For compatibility, omitting an exact candidate from a managed
|
|
336
|
+
named-cap implementation or fix still resolves successfully at the cap. When
|
|
337
|
+
report context is present, that path emits the coded
|
|
338
|
+
`managed-capped-selection-skipped` warning in human and JSON output. The root
|
|
339
|
+
must treat the warning as a dispatch-policy violation and select an exact
|
|
340
|
+
candidate before launch even though the command retains exit code `0`.
|
|
313
341
|
|
|
314
342
|
Implementer and fix resolution has two mutually exclusive selection branches:
|
|
315
343
|
|
|
@@ -411,20 +439,38 @@ write authority. See
|
|
|
411
439
|
|
|
412
440
|
Resolver calls that pass `--report-scope` and `--report-action` include a
|
|
413
441
|
`dispatchReport` object in JSON output. Consumers must require
|
|
414
|
-
`dispatchReport.schemaVersion: 1` before dispatch. The report keeps
|
|
415
|
-
|
|
416
|
-
|
|
417
|
-
| Report area | What it means
|
|
418
|
-
| ------------------------------------------------------------------- |
|
|
419
|
-
| `policy` | The resolved managed/inherit policy, its status, name, and source
|
|
420
|
-
| `selection.ceilingTier` / `selection.ceilingTarget` | The maximum allowed tier and its boundary target
|
|
421
|
-
| `selection.requestedCandidate` / `candidateTier` / `candidateIndex` | The exact candidate requested for this bounded task and its position
|
|
422
|
-
| `selection.
|
|
442
|
+
`dispatchReport.schemaVersion: 1` before dispatch. The report keeps these
|
|
443
|
+
concerns separate:
|
|
444
|
+
|
|
445
|
+
| Report area | What it means |
|
|
446
|
+
| ------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
|
|
447
|
+
| `policy` | The resolved managed/inherit policy, its status, name, and source |
|
|
448
|
+
| `selection.ceilingTier` / `selection.ceilingTarget` | The maximum allowed tier and its boundary target |
|
|
449
|
+
| `selection.requestedCandidate` / `candidateTier` / `candidateIndex` | The exact candidate requested for this bounded task and its position |
|
|
450
|
+
| `selection.preferredValue` | The legacy `--preferred` selection value, or `null` when that compatibility path was not used |
|
|
451
|
+
| `selection.exactSelectedTarget` / `route.target` | The compiled provider target and actual invocation route |
|
|
452
|
+
| `classification` | Caller-reported task class, applicable Codex preferred effort, and provenance source |
|
|
453
|
+
| `notices` | Ordered coded warnings and advisories derived from the effective dispatch context |
|
|
423
454
|
|
|
424
455
|
A named policy or ceiling is never a substitute for the requested candidate or
|
|
425
|
-
exact selected target.
|
|
426
|
-
|
|
427
|
-
|
|
456
|
+
exact selected target. Classification is provenance only: it records the
|
|
457
|
+
root's judgment but does not participate in candidate normalization or let OAT
|
|
458
|
+
judge whether that classification was correct. `requestedControls` records
|
|
459
|
+
what OAT put into the host payload. `configuredDefaults` records fallback
|
|
460
|
+
configuration and is explicitly not a runtime observation.
|
|
461
|
+
|
|
462
|
+
Managed named-cap implementation and fix reports can include two warning codes:
|
|
463
|
+
|
|
464
|
+
- `managed-capped-selection-skipped` means no exact candidate or legacy
|
|
465
|
+
preferred value was supplied, so compatibility behavior selected the cap.
|
|
466
|
+
- `managed-capped-classification-missing` means an exact candidate was supplied
|
|
467
|
+
without `--task-class`.
|
|
468
|
+
|
|
469
|
+
Both warnings preserve resolved status and exit code `0`. They do not apply to
|
|
470
|
+
policy-only preflight, reviewer, inherit, uncapped, unresolved, or
|
|
471
|
+
legacy-preferred routes. `terminal-reviewer-eligibility` is an advisory tied to
|
|
472
|
+
an effective Fable reviewer target, not proof of model access or organizational
|
|
473
|
+
retention eligibility.
|
|
428
474
|
|
|
429
475
|
`gateInvocation` is an immutable copy of configured gate controls.
|
|
430
476
|
`runtimeIdentity` is separate and stays `not-reported` until independently
|
|
@@ -446,6 +492,11 @@ when OAT can establish it; otherwise it is `unknown`. `provenance` is
|
|
|
446
492
|
`declared`, `observed`, `inferred`, or `unknown`. Selected model and effort axes
|
|
447
493
|
can remain exact even when runtime producer identity is not reported.
|
|
448
494
|
|
|
495
|
+
Before launching an implementation, fix, or reviewer, surface the structured
|
|
496
|
+
notices in `dispatchReport.notices` and render the report. Structured notices
|
|
497
|
+
and runtime disclosure use the effective target returned by that resolver call,
|
|
498
|
+
never a target inferred from the bundled recommendation version.
|
|
499
|
+
|
|
449
500
|
## Legacy Compatibility
|
|
450
501
|
|
|
451
502
|
The following remain readable during migration:
|
|
@@ -233,7 +233,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
|
|
|
233
233
|
| `oat-project-design/references/selective-review-pass.md` | `d4956192b82e -> DES-06`; `7d6e1f926ecb -> DES-06`; `04f918a5fcac -> DES-07` |
|
|
234
234
|
| `oat-project-plan/SKILL.md` | `5eb3949f32e1 -> NG`; `64a08153bb9e -> NG`; `655d61df0a8f -> NG`; `56b37486f09d -> PLAN-01`; `cf317c17c586 -> PLAN-02`; `781643b0f2c3 -> NG`; `01fd7cca8253 -> PLAN-04`; `7bc7fa3f2cbb -> NG`; `da28ce0a5f2e -> NG`; `e334f94c4d35 -> NG`; `1fa55762c038 -> NG`; `c0935b5484a2 -> NG`; `6008163054f8 -> PLAN-05`; `571271f4d71b -> PLAN-06`; `746b760289e4 -> PLAN-06`; `de195590ff83 -> NG`; `49640510829a -> PLAN-07`; `4bef7afa7a71 -> PLAN-08`; `e5886632533e -> PLAN-08`; `4cfe1df14372 -> NG`; `d116c97a500c -> PLAN-10`; `aa62facff547 -> PLAN-10`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> PLAN-11`; `1734b2c85c5d -> NG`; `b4af2220eb91 -> PLAN-11` |
|
|
235
235
|
| `oat-project-import-plan/SKILL.md` | `f7ca8635452f -> NG`; `c2e5fa410069 -> NG`; `655d61df0a8f -> NG`; `dceff5cc04b5 -> NG`; `1af4957a1af2 -> IMPORT-01`; `45b699c1c0b5 -> IMPORT-01`; `ba6d120791c1 -> IMPORT-01`; `070ebc5259af -> IMPORT-03`; `c11552696e2e -> IMPORT-03`; `cfe661966baf -> IMPORT-04`; `baa91c0a0bf8 -> NG`; `e364e84b2702 -> NG`; `39031985a945 -> IMPORT-06`; `f106aa29a217 -> IMPORT-07`; `65038450aee3 -> IMPORT-07`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> IMPORT-09` |
|
|
236
|
-
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `
|
|
236
|
+
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `e0355c7a05e9 -> IMPLEMENT-11+IMPLEMENT-13+IMPLEMENT-16`; `6296f41ae11c -> NG`; `a167d03559fa -> NG`; `cf317c17c586 -> IMPLEMENT-01`; `8ce8a09feca4 -> NG`; `bd0cb4988188 -> NG`; `28af4ee0055d -> NG` |
|
|
237
237
|
| `oat-project-implement/references/completion-and-closeout.md` | `f7dab9c1f96c -> IMPLEMENT-12`; `c69c17a069a8 -> IMPLEMENT-14`; `a97fa5634a68 -> IMPLEMENT-14`; `3af58881811c -> IMPLEMENT-14`; `4203e1f49d0f -> IMPLEMENT-14`; `c3bd2458a3d3 -> IMPLEMENT-13`; `95b5eafc070d -> IMPLEMENT-13`; `25ecbe9c998b -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f6f24fd71da4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f18283bc1cf9 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `2c1ffc4a82dd -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `3454a07aa843 -> IMPLEMENT-16`; `0d86e2098cfb -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d5fe597d266f -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `55a152e944c1 -> IMPLEMENT-16`; `effac7cbd573 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d2a34d8b148 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d27462aaed26 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d52ecb17268 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `5b91aabe3757 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `fd0ad919f702 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `63bf28df1474 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a4ed471dbc78 -> IMPLEMENT-16`; `6b7a64cec6e5 -> IMPLEMENT-16`; `0a4fdba0ebc0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a5033c2aada5 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `e77609eddba0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `351156e8dde4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `51d45bd2bbd1 -> IMPLEMENT-16`; `f7796ffcc804 -> IMPLEMENT-16`; `990d730cb494 -> IMPLEMENT-16`; `6ed28bb7d384 -> IMPLEMENT-16`; `8b7d4b5bcf1b -> IMPLEMENT-16`; `88aad500e6e9 -> IMPLEMENT-16`; `877e3e3f9eda -> IMPLEMENT-16`; `fc03c97f834e -> IMPLEMENT-16`; `12939a3da5e0 -> IMPLEMENT-16`; `bdb418335a88 -> IMPLEMENT-16`; `fba97e596ebd -> IMPLEMENT-16`; `3d0b5e2f14f0 -> IMPLEMENT-17`; `87f1424a8692 -> NG`; `6b1ec05182f0 -> IMPLEMENT-11`; `e6d696a27c91 -> NG`; `c77f8ccb52ad -> NG`; `48de2614c0ba -> IMPLEMENT-11`; `32d53f5212e5 -> IMPLEMENT-11`; `7cdb4a9c57b7 -> IMPLEMENT-11`; `16ffc0aa099b -> IMPLEMENT-11`; `d6868ea10b3f -> IMPLEMENT-11`; `4f05ff5567be -> IMPLEMENT-11`; `c70b47ae7a6d -> IMPLEMENT-11`; `5fafd093b58e -> NG`; `567d43ab0c2e -> NG`; `21ceaf7e658a -> NG`; `249427a9f475 -> NG`; `8a7ec13a9b7c -> NG`; `9aeb7fce2012 -> IMPLEMENT-18`; `f11a7cdda220 -> IMPLEMENT-18`; `4523ac029152 -> NG`; `6e87b08c4046 -> NG`; `baa6052c7f0a -> IMPLEMENT-18`; `27d3fad116b1 -> IMPLEMENT-18`; `2cfbeb4388a5 -> IMPLEMENT-18`; `c56ea56a56db -> NG`; `43e2e3c1380d -> IMPLEMENT-17`; `b49690277fb5 -> NG`; `df12304d6a36 -> NG`; `52eacac11fef -> IMPLEMENT-17`; `60092df6b17b -> IMPLEMENT-17`; `361872c6b00e -> IMPLEMENT-17`; `d2bc711a75fb -> IMPLEMENT-17` |
|
|
238
238
|
| `oat-project-implement/references/dispatch-and-dry-run.md` | `21b85f5e4daa -> IMPLEMENT-08`; `74c92b32bb2a -> IMPLEMENT-08`; `8efd2d0517ab -> IMPLEMENT-09`; `461ed9b3e495 -> IMPLEMENT-09`; `b5ad64fd744d -> NG`; `14ce436cfffa -> NG`; `043ca36da3e2 -> NG`; `a23e45c1dc8d -> NG`; `498143bb41a7 -> NG`; `4fe3eb179023 -> NG`; `7f75485e5a33 -> NG`; `8ec3a96df029 -> NG`; `16c3f96e758d -> NG`; `5915c41fe058 -> NG`; `f51e43eeac56 -> NG`; `fd41c25623cb -> NG`; `58a932ed6453 -> NG`; `4718bd3ce12d -> NG`; `58c444a2126b -> NG`; `2df3adae4120 -> NG`; `e75df892b55c -> NG`; `8ba5dbd2a0d8 -> NG` |
|
|
239
239
|
| `oat-project-implement/references/docs/autonomy-contract.md` | `* -> NG` |
|
|
@@ -233,7 +233,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
|
|
|
233
233
|
| `oat-project-design/references/selective-review-pass.md` | `d4956192b82e -> DES-06`; `7d6e1f926ecb -> DES-06`; `04f918a5fcac -> DES-07` |
|
|
234
234
|
| `oat-project-plan/SKILL.md` | `5eb3949f32e1 -> NG`; `64a08153bb9e -> NG`; `655d61df0a8f -> NG`; `56b37486f09d -> PLAN-01`; `cf317c17c586 -> PLAN-02`; `781643b0f2c3 -> NG`; `01fd7cca8253 -> PLAN-04`; `7bc7fa3f2cbb -> NG`; `da28ce0a5f2e -> NG`; `e334f94c4d35 -> NG`; `1fa55762c038 -> NG`; `c0935b5484a2 -> NG`; `6008163054f8 -> PLAN-05`; `571271f4d71b -> PLAN-06`; `746b760289e4 -> PLAN-06`; `de195590ff83 -> NG`; `49640510829a -> PLAN-07`; `4bef7afa7a71 -> PLAN-08`; `e5886632533e -> PLAN-08`; `4cfe1df14372 -> NG`; `d116c97a500c -> PLAN-10`; `aa62facff547 -> PLAN-10`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> PLAN-11`; `1734b2c85c5d -> NG`; `b4af2220eb91 -> PLAN-11` |
|
|
235
235
|
| `oat-project-import-plan/SKILL.md` | `f7ca8635452f -> NG`; `c2e5fa410069 -> NG`; `655d61df0a8f -> NG`; `dceff5cc04b5 -> NG`; `1af4957a1af2 -> IMPORT-01`; `45b699c1c0b5 -> IMPORT-01`; `ba6d120791c1 -> IMPORT-01`; `070ebc5259af -> IMPORT-03`; `c11552696e2e -> IMPORT-03`; `cfe661966baf -> IMPORT-04`; `baa91c0a0bf8 -> NG`; `e364e84b2702 -> NG`; `39031985a945 -> IMPORT-06`; `f106aa29a217 -> IMPORT-07`; `65038450aee3 -> IMPORT-07`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> IMPORT-09` |
|
|
236
|
-
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `
|
|
236
|
+
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `e0355c7a05e9 -> IMPLEMENT-11+IMPLEMENT-13+IMPLEMENT-16`; `6296f41ae11c -> NG`; `a167d03559fa -> NG`; `cf317c17c586 -> IMPLEMENT-01`; `8ce8a09feca4 -> NG`; `bd0cb4988188 -> NG`; `28af4ee0055d -> NG` |
|
|
237
237
|
| `oat-project-implement/references/completion-and-closeout.md` | `f7dab9c1f96c -> IMPLEMENT-12`; `c69c17a069a8 -> IMPLEMENT-14`; `a97fa5634a68 -> IMPLEMENT-14`; `3af58881811c -> IMPLEMENT-14`; `4203e1f49d0f -> IMPLEMENT-14`; `c3bd2458a3d3 -> IMPLEMENT-13`; `95b5eafc070d -> IMPLEMENT-13`; `25ecbe9c998b -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f6f24fd71da4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f18283bc1cf9 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `2c1ffc4a82dd -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `3454a07aa843 -> IMPLEMENT-16`; `0d86e2098cfb -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d5fe597d266f -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `55a152e944c1 -> IMPLEMENT-16`; `effac7cbd573 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d2a34d8b148 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d27462aaed26 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d52ecb17268 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `5b91aabe3757 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `fd0ad919f702 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `63bf28df1474 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a4ed471dbc78 -> IMPLEMENT-16`; `6b7a64cec6e5 -> IMPLEMENT-16`; `0a4fdba0ebc0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a5033c2aada5 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `e77609eddba0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `351156e8dde4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `51d45bd2bbd1 -> IMPLEMENT-16`; `f7796ffcc804 -> IMPLEMENT-16`; `990d730cb494 -> IMPLEMENT-16`; `6ed28bb7d384 -> IMPLEMENT-16`; `8b7d4b5bcf1b -> IMPLEMENT-16`; `88aad500e6e9 -> IMPLEMENT-16`; `877e3e3f9eda -> IMPLEMENT-16`; `fc03c97f834e -> IMPLEMENT-16`; `12939a3da5e0 -> IMPLEMENT-16`; `bdb418335a88 -> IMPLEMENT-16`; `fba97e596ebd -> IMPLEMENT-16`; `3d0b5e2f14f0 -> IMPLEMENT-17`; `87f1424a8692 -> NG`; `6b1ec05182f0 -> IMPLEMENT-11`; `e6d696a27c91 -> NG`; `c77f8ccb52ad -> NG`; `48de2614c0ba -> IMPLEMENT-11`; `32d53f5212e5 -> IMPLEMENT-11`; `7cdb4a9c57b7 -> IMPLEMENT-11`; `16ffc0aa099b -> IMPLEMENT-11`; `d6868ea10b3f -> IMPLEMENT-11`; `4f05ff5567be -> IMPLEMENT-11`; `c70b47ae7a6d -> IMPLEMENT-11`; `5fafd093b58e -> NG`; `567d43ab0c2e -> NG`; `21ceaf7e658a -> NG`; `249427a9f475 -> NG`; `8a7ec13a9b7c -> NG`; `9aeb7fce2012 -> IMPLEMENT-18`; `f11a7cdda220 -> IMPLEMENT-18`; `4523ac029152 -> NG`; `6e87b08c4046 -> NG`; `baa6052c7f0a -> IMPLEMENT-18`; `27d3fad116b1 -> IMPLEMENT-18`; `2cfbeb4388a5 -> IMPLEMENT-18`; `c56ea56a56db -> NG`; `43e2e3c1380d -> IMPLEMENT-17`; `b49690277fb5 -> NG`; `df12304d6a36 -> NG`; `52eacac11fef -> IMPLEMENT-17`; `60092df6b17b -> IMPLEMENT-17`; `361872c6b00e -> IMPLEMENT-17`; `d2bc711a75fb -> IMPLEMENT-17` |
|
|
238
238
|
| `oat-project-implement/references/dispatch-and-dry-run.md` | `21b85f5e4daa -> IMPLEMENT-08`; `74c92b32bb2a -> IMPLEMENT-08`; `8efd2d0517ab -> IMPLEMENT-09`; `461ed9b3e495 -> IMPLEMENT-09`; `b5ad64fd744d -> NG`; `14ce436cfffa -> NG`; `043ca36da3e2 -> NG`; `a23e45c1dc8d -> NG`; `498143bb41a7 -> NG`; `4fe3eb179023 -> NG`; `7f75485e5a33 -> NG`; `8ec3a96df029 -> NG`; `16c3f96e758d -> NG`; `5915c41fe058 -> NG`; `f51e43eeac56 -> NG`; `fd41c25623cb -> NG`; `58a932ed6453 -> NG`; `4718bd3ce12d -> NG`; `58c444a2126b -> NG`; `2df3adae4120 -> NG`; `e75df892b55c -> NG`; `8ba5dbd2a0d8 -> NG` |
|
|
239
239
|
| `oat-project-implement/references/docs/autonomy-contract.md` | `* -> NG` |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: oat-project-implement
|
|
3
|
-
version: 2.2.
|
|
3
|
+
version: 2.2.3
|
|
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]'
|
|
@@ -19,16 +19,14 @@ Execute the implementation plan task-by-task with full state tracking.
|
|
|
19
19
|
|
|
20
20
|
## Shared Subagent Dispatch Contract
|
|
21
21
|
|
|
22
|
-
Before resolving or launching
|
|
23
|
-
|
|
24
|
-
`.agents/skills/oat-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
closeout.
|
|
31
|
-
Correctness must not require a provider restart or hot reload.
|
|
22
|
+
Before resolving or launching a phase implementer, optional child, fix, or
|
|
23
|
+
reviewer, read `.agents/skills/oat-project-dispatch-subagents/SKILL.md`, then
|
|
24
|
+
`.agents/skills/oat-dispatch-subagents/SKILL.md`. The former resolves lifecycle
|
|
25
|
+
scope; the latter owns provider-neutral selection, recovery, and evidence.
|
|
26
|
+
Display structured resolver notices before every implementation, fix, or
|
|
27
|
+
reviewer launch. Runtime disclosure uses the effective resolved target, never
|
|
28
|
+
the bundled recommendation version. This explicit load is mandatory, and
|
|
29
|
+
correctness must not require a provider restart or hot reload.
|
|
32
30
|
|
|
33
31
|
Read
|
|
34
32
|
`.agents/skills/subagent-orchestration/references/model-selection-principles.md`.
|
|
@@ -157,7 +157,7 @@ Use the CLI resolver as the source of truth. The command name remains
|
|
|
157
157
|
policy:
|
|
158
158
|
|
|
159
159
|
```bash
|
|
160
|
-
oat project dispatch-ceiling resolve --provider <active-provider> --preflight --report-scope implementation-preflight --report-action implementation --json
|
|
160
|
+
oat project dispatch-ceiling resolve --provider <active-provider> --preflight --task-class <task-class> [--task-effort <codex-preferred-effort>] --report-scope implementation-preflight --report-action implementation --json
|
|
161
161
|
```
|
|
162
162
|
|
|
163
163
|
If `oat` is not in PATH, run the same command through
|
|
@@ -317,9 +317,11 @@ report context:
|
|
|
317
317
|
- review: `--report-scope <phase-or-review-scope> --report-action review`
|
|
318
318
|
|
|
319
319
|
Require `dispatchReport.schemaVersion: 1` in the completed resolver JSON before
|
|
320
|
-
dispatch.
|
|
321
|
-
block with `formatDispatchReport(dispatchReport)`
|
|
322
|
-
|
|
320
|
+
dispatch. Surface every structured entry in `dispatchReport.notices`, then
|
|
321
|
+
render the versioned block with `formatDispatchReport(dispatchReport)`
|
|
322
|
+
semantics, before the implementation, fix, or reviewer launch. Consume the
|
|
323
|
+
report as the human/audit source, and derive the formal compatibility line only
|
|
324
|
+
through
|
|
323
325
|
`formatDispatchStamp(dispatchReport)` / `toDispatchStampRecord(dispatchReport)`.
|
|
324
326
|
Never hand-assemble a second `Dispatch:` schema from policy labels, role names,
|
|
325
327
|
candidate strings, or target names.
|
|
@@ -329,6 +331,10 @@ The exact provider invocation remains authoritative in
|
|
|
329
331
|
the report does not replace or weaken target-pinned dispatch. Add independently
|
|
330
332
|
observed runtime identity to `dispatchReport.runtimeIdentity` only when such an
|
|
331
333
|
observation exists. Requested/configured controls are not runtime observation.
|
|
334
|
+
Runtime disclosure must use the effective resolved target in that completed
|
|
335
|
+
response. Never infer runtime controls or eligibility from
|
|
336
|
+
`recommendationVersion`, which identifies only the bundled recommendation that
|
|
337
|
+
was adopted.
|
|
332
338
|
For gate-originated review, keep `dispatchReport.gateInvocation`, existing
|
|
333
339
|
work-producer `diversity`, and reviewer `runtimeIdentity` as three distinct
|
|
334
340
|
facts; producer stamps or self-report never overwrite configured invocation.
|
|
@@ -369,8 +375,9 @@ requested; never silently downgrade to it.
|
|
|
369
375
|
6. For managed capped phase-implementer/fix dispatch, choose an exact
|
|
370
376
|
configured candidate and use the exact-candidate branch, not the
|
|
371
377
|
preferred-selection branch. For implementation, call
|
|
372
|
-
`oat project dispatch-ceiling resolve --provider codex --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <model> --candidate-effort <effort> --escalation-level <route-level> --report-scope <phase-id> --report-action implementation --json`.
|
|
378
|
+
`oat project dispatch-ceiling resolve --provider codex --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <model> --candidate-effort <effort> --task-class <task-class> --task-effort <preferred-effort> --escalation-level <route-level> --report-scope <phase-id> --report-action implementation --json`.
|
|
373
379
|
For a bounded fix, use the same phase target with
|
|
380
|
+
the same `--task-class` and `--task-effort` classification provenance and
|
|
374
381
|
`--report-scope <phase-or-fix-scope> --report-action fix`. Read
|
|
375
382
|
`providers.codex.dispatchArgs.variant` and
|
|
376
383
|
`providers.codex.selection.target`; never reuse a cap-only variant.
|
|
@@ -406,8 +413,9 @@ Claude rules:
|
|
|
406
413
|
- Capped managed policy: target the configured policy cap directly.
|
|
407
414
|
- Managed `Uncapped` or inherit/default: no reviewer target exists; omit `model` and log inherited/default model behavior.
|
|
408
415
|
- For managed capped phase-implementer/fix dispatch, call
|
|
409
|
-
`oat project dispatch-ceiling resolve --provider claude --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <model> --orchestrator-tier <current-orchestrator-tier> --escalation-level <route-level> --report-scope <phase-id> --report-action implementation --json`.
|
|
410
|
-
For bounded fixes, reuse the exact phase target
|
|
416
|
+
`oat project dispatch-ceiling resolve --provider claude --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <model> --task-class <task-class> --orchestrator-tier <current-orchestrator-tier> --escalation-level <route-level> --report-scope <phase-id> --report-action implementation --json`.
|
|
417
|
+
For bounded fixes, reuse the exact phase target and task classification with a
|
|
418
|
+
bounded fix scope.
|
|
411
419
|
For review dispatch, call the resolver with
|
|
412
420
|
`--role reviewer --report-scope <phase-or-review-scope> --report-action review --json`
|
|
413
421
|
and no candidate flags. Read `providers.claude.dispatchArgs.model` and pass it
|
|
@@ -443,8 +451,9 @@ Cursor rules:
|
|
|
443
451
|
task-class resolution independently arrives there; reaching it because no
|
|
444
452
|
candidate was selected is a defect.
|
|
445
453
|
- For managed capped phase-implementer/fix dispatch, call
|
|
446
|
-
`oat project dispatch-ceiling resolve --provider cursor --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <opaque-model> --report-scope <phase-id> --report-action implementation --json`.
|
|
447
|
-
For bounded fixes, reuse the exact phase target
|
|
454
|
+
`oat project dispatch-ceiling resolve --provider cursor --role implementer --ceiling-tier <project-or-phase-tier> --candidate-model <opaque-model> --task-class <task-class> --report-scope <phase-id> --report-action implementation --json`.
|
|
455
|
+
For bounded fixes, reuse the exact phase target and task classification with a
|
|
456
|
+
bounded fix scope.
|
|
448
457
|
- Require `providers.cursor.dispatchArgs.variant` and launch that exact
|
|
449
458
|
resolver-selected native agent type first. Native acceptance plus the
|
|
450
459
|
complete launcher payload is configured invocation evidence; it does not
|
|
@@ -233,7 +233,7 @@ remains immutable baseline evidence for the original p01-t01 verification.
|
|
|
233
233
|
| `oat-project-design/references/selective-review-pass.md` | `d4956192b82e -> DES-06`; `7d6e1f926ecb -> DES-06`; `04f918a5fcac -> DES-07` |
|
|
234
234
|
| `oat-project-plan/SKILL.md` | `5eb3949f32e1 -> NG`; `64a08153bb9e -> NG`; `655d61df0a8f -> NG`; `56b37486f09d -> PLAN-01`; `cf317c17c586 -> PLAN-02`; `781643b0f2c3 -> NG`; `01fd7cca8253 -> PLAN-04`; `7bc7fa3f2cbb -> NG`; `da28ce0a5f2e -> NG`; `e334f94c4d35 -> NG`; `1fa55762c038 -> NG`; `c0935b5484a2 -> NG`; `6008163054f8 -> PLAN-05`; `571271f4d71b -> PLAN-06`; `746b760289e4 -> PLAN-06`; `de195590ff83 -> NG`; `49640510829a -> PLAN-07`; `4bef7afa7a71 -> PLAN-08`; `e5886632533e -> PLAN-08`; `4cfe1df14372 -> NG`; `d116c97a500c -> PLAN-10`; `aa62facff547 -> PLAN-10`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> PLAN-11`; `1734b2c85c5d -> NG`; `b4af2220eb91 -> PLAN-11` |
|
|
235
235
|
| `oat-project-import-plan/SKILL.md` | `f7ca8635452f -> NG`; `c2e5fa410069 -> NG`; `655d61df0a8f -> NG`; `dceff5cc04b5 -> NG`; `1af4957a1af2 -> IMPORT-01`; `45b699c1c0b5 -> IMPORT-01`; `ba6d120791c1 -> IMPORT-01`; `070ebc5259af -> IMPORT-03`; `c11552696e2e -> IMPORT-03`; `cfe661966baf -> IMPORT-04`; `baa91c0a0bf8 -> NG`; `e364e84b2702 -> NG`; `39031985a945 -> IMPORT-06`; `f106aa29a217 -> IMPORT-07`; `65038450aee3 -> IMPORT-07`; `bee4c4aa34c6 -> NG`; `3f0b53056edd -> IMPORT-09` |
|
|
236
|
-
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `
|
|
236
|
+
| `oat-project-implement/SKILL.md` | `18980f6bc1a6 -> NG`; `e0355c7a05e9 -> IMPLEMENT-11+IMPLEMENT-13+IMPLEMENT-16`; `6296f41ae11c -> NG`; `a167d03559fa -> NG`; `cf317c17c586 -> IMPLEMENT-01`; `8ce8a09feca4 -> NG`; `bd0cb4988188 -> NG`; `28af4ee0055d -> NG` |
|
|
237
237
|
| `oat-project-implement/references/completion-and-closeout.md` | `f7dab9c1f96c -> IMPLEMENT-12`; `c69c17a069a8 -> IMPLEMENT-14`; `a97fa5634a68 -> IMPLEMENT-14`; `3af58881811c -> IMPLEMENT-14`; `4203e1f49d0f -> IMPLEMENT-14`; `c3bd2458a3d3 -> IMPLEMENT-13`; `95b5eafc070d -> IMPLEMENT-13`; `25ecbe9c998b -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f6f24fd71da4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `f18283bc1cf9 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `2c1ffc4a82dd -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `3454a07aa843 -> IMPLEMENT-16`; `0d86e2098cfb -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d5fe597d266f -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `55a152e944c1 -> IMPLEMENT-16`; `effac7cbd573 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d2a34d8b148 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `d27462aaed26 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `9d52ecb17268 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `5b91aabe3757 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `fd0ad919f702 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `63bf28df1474 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a4ed471dbc78 -> IMPLEMENT-16`; `6b7a64cec6e5 -> IMPLEMENT-16`; `0a4fdba0ebc0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `a5033c2aada5 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `e77609eddba0 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `351156e8dde4 -> IMPLEMENT-13+IMPLEMENT-14+IMPLEMENT-15+IMPLEMENT-16`; `51d45bd2bbd1 -> IMPLEMENT-16`; `f7796ffcc804 -> IMPLEMENT-16`; `990d730cb494 -> IMPLEMENT-16`; `6ed28bb7d384 -> IMPLEMENT-16`; `8b7d4b5bcf1b -> IMPLEMENT-16`; `88aad500e6e9 -> IMPLEMENT-16`; `877e3e3f9eda -> IMPLEMENT-16`; `fc03c97f834e -> IMPLEMENT-16`; `12939a3da5e0 -> IMPLEMENT-16`; `bdb418335a88 -> IMPLEMENT-16`; `fba97e596ebd -> IMPLEMENT-16`; `3d0b5e2f14f0 -> IMPLEMENT-17`; `87f1424a8692 -> NG`; `6b1ec05182f0 -> IMPLEMENT-11`; `e6d696a27c91 -> NG`; `c77f8ccb52ad -> NG`; `48de2614c0ba -> IMPLEMENT-11`; `32d53f5212e5 -> IMPLEMENT-11`; `7cdb4a9c57b7 -> IMPLEMENT-11`; `16ffc0aa099b -> IMPLEMENT-11`; `d6868ea10b3f -> IMPLEMENT-11`; `4f05ff5567be -> IMPLEMENT-11`; `c70b47ae7a6d -> IMPLEMENT-11`; `5fafd093b58e -> NG`; `567d43ab0c2e -> NG`; `21ceaf7e658a -> NG`; `249427a9f475 -> NG`; `8a7ec13a9b7c -> NG`; `9aeb7fce2012 -> IMPLEMENT-18`; `f11a7cdda220 -> IMPLEMENT-18`; `4523ac029152 -> NG`; `6e87b08c4046 -> NG`; `baa6052c7f0a -> IMPLEMENT-18`; `27d3fad116b1 -> IMPLEMENT-18`; `2cfbeb4388a5 -> IMPLEMENT-18`; `c56ea56a56db -> NG`; `43e2e3c1380d -> IMPLEMENT-17`; `b49690277fb5 -> NG`; `df12304d6a36 -> NG`; `52eacac11fef -> IMPLEMENT-17`; `60092df6b17b -> IMPLEMENT-17`; `361872c6b00e -> IMPLEMENT-17`; `d2bc711a75fb -> IMPLEMENT-17` |
|
|
238
238
|
| `oat-project-implement/references/dispatch-and-dry-run.md` | `21b85f5e4daa -> IMPLEMENT-08`; `74c92b32bb2a -> IMPLEMENT-08`; `8efd2d0517ab -> IMPLEMENT-09`; `461ed9b3e495 -> IMPLEMENT-09`; `b5ad64fd744d -> NG`; `14ce436cfffa -> NG`; `043ca36da3e2 -> NG`; `a23e45c1dc8d -> NG`; `498143bb41a7 -> NG`; `4fe3eb179023 -> NG`; `7f75485e5a33 -> NG`; `8ec3a96df029 -> NG`; `16c3f96e758d -> NG`; `5915c41fe058 -> NG`; `f51e43eeac56 -> NG`; `fd41c25623cb -> NG`; `58a932ed6453 -> NG`; `4718bd3ce12d -> NG`; `58c444a2126b -> NG`; `2df3adae4120 -> NG`; `e75df892b55c -> NG`; `8ba5dbd2a0d8 -> NG` |
|
|
239
239
|
| `oat-project-implement/references/docs/autonomy-contract.md` | `* -> NG` |
|
|
@@ -20,13 +20,18 @@ responsible for file boundaries, verification, and task commits.
|
|
|
20
20
|
Before each phase:
|
|
21
21
|
|
|
22
22
|
1. Resolve the project dispatch policy and optional narrower phase maximum from
|
|
23
|
-
the plan's `## Dispatch Profile`.
|
|
23
|
+
the plan's `## Dispatch Profile`. Classify the complete phase scope and
|
|
24
|
+
record the classification source and rationale. For Codex, also classify
|
|
25
|
+
the preferred task effort.
|
|
24
26
|
2. Resolve one exact phase implementer target with
|
|
25
|
-
`--role implementer --ceiling-tier <project-or-phase-named-tier> --report-scope <pNN> --report-action implementation`.
|
|
27
|
+
`--role implementer --ceiling-tier <project-or-phase-named-tier> --task-class <task-class> [--task-effort <codex-preferred-effort>] --report-scope <pNN> --report-action implementation`.
|
|
26
28
|
Use the phase scope, not each task ID. Omit `--ceiling-tier` only for
|
|
27
29
|
uncapped or inherit/default policy.
|
|
28
|
-
3.
|
|
29
|
-
|
|
30
|
+
3. Require the completed Dispatch Report, surface its structured notices, and
|
|
31
|
+
render the report before launch. Build the provider invocation before
|
|
32
|
+
recording target, model/effort axes, selection reason, candidates, and
|
|
33
|
+
formal dispatch stamp. Runtime disclosure comes from the effective resolved
|
|
34
|
+
target, never `recommendationVersion`.
|
|
30
35
|
4. Record `PHASE_BASE_HEAD=$(git rev-parse HEAD)` and require a clean worktree.
|
|
31
36
|
5. Send one self-contained Phase Scope:
|
|
32
37
|
|
|
@@ -54,6 +59,10 @@ Before each phase:
|
|
|
54
59
|
dispatch_args: {complete provider invocation payload}
|
|
55
60
|
model_axis: {resolver value}
|
|
56
61
|
effort_axis: {resolver value}
|
|
62
|
+
task_class: {mechanical-recon|intelligent-recon|default-implementation|hard-reasoning|consequential}
|
|
63
|
+
preferred_effort: {codex low|medium|high|xhigh|max; null for other providers}
|
|
64
|
+
classification_source: {plan dispatch profile|phase scope analysis|other explicit source}
|
|
65
|
+
classification_rationale: {short rationale grounded in the complete phase scope}
|
|
57
66
|
selection_reason: {stable shared reason}
|
|
58
67
|
candidates_considered: {ordered exact candidates}
|
|
59
68
|
dispatch_stamp: {formal Dispatch: line}
|