codex-orchestrator 2.0.18 → 2.0.19

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/CHANGELOG.md +10 -0
  2. package/README.md +40 -2
  3. package/dist/src/v2/acceptance-proof.d.ts.map +1 -1
  4. package/dist/src/v2/acceptance-proof.js +15 -5
  5. package/dist/src/v2/acceptance-proof.js.map +1 -1
  6. package/dist/src/v2/implementation-reviewer.d.ts +1 -0
  7. package/dist/src/v2/implementation-reviewer.d.ts.map +1 -1
  8. package/dist/src/v2/implementation-reviewer.js +8 -2
  9. package/dist/src/v2/implementation-reviewer.js.map +1 -1
  10. package/dist/src/v2/issue-check-policy.d.ts.map +1 -1
  11. package/dist/src/v2/issue-check-policy.js +25 -9
  12. package/dist/src/v2/issue-check-policy.js.map +1 -1
  13. package/dist/src/v2/run-issue.d.ts +1 -1
  14. package/dist/src/v2/run-issue.d.ts.map +1 -1
  15. package/dist/src/v2/run-issue.js +38 -30
  16. package/dist/src/v2/run-issue.js.map +1 -1
  17. package/dist/src/v2/runtime.js +2 -2
  18. package/dist/src/v2/runtime.js.map +1 -1
  19. package/dist/src/v2/validation-progression.d.ts.map +1 -1
  20. package/dist/src/v2/validation-progression.js +3 -0
  21. package/dist/src/v2/validation-progression.js.map +1 -1
  22. package/internal-workflow/docs/agents/coding-skill-routing.md +4 -0
  23. package/internal-workflow/manifest.json +1 -1
  24. package/internal-workflow/profiles/spec_reviewer.toml +1 -1
  25. package/internal-workflow/profiles/standards_reviewer.toml +1 -1
  26. package/internal-workflow/skills/code-review/SKILL.md +5 -0
  27. package/internal-workflow/skills/implement/SKILL.md +11 -12
  28. package/internal-workflow/skills/implement/evals/evals.json +0 -12
  29. package/internal-workflow/skills/plan/SKILL.md +32 -12
  30. package/internal-workflow/skills/plan/agents/openai.yaml +2 -2
  31. package/internal-workflow/skills/plan/evals/evals.json +27 -0
  32. package/internal-workflow/skills/plan-review/SKILL.md +110 -0
  33. package/internal-workflow/skills/plan-review/agents/openai.yaml +6 -0
  34. package/internal-workflow/skills/plan-review/evals/evals.json +57 -0
  35. package/internal-workflow/skills/tickets-orchestrator/SKILL.md +0 -4
  36. package/internal-workflow/skills/to-spec/SKILL.md +4 -2
  37. package/internal-workflow/skills/to-tickets/SKILL.md +21 -21
  38. package/internal-workflow/skills/to-tickets/evals/evals.json +25 -0
  39. package/package.json +1 -1
@@ -15,7 +15,7 @@ ticket contains only its local observable outcome, scope, blockers, proof, and
15
15
  Parent link. The approved ticket body plus Parent PRD is the final execution
16
16
  authority; no later planning pass is inserted.
17
17
 
18
- `$to-tickets` owns complete whole-packet semantic review, one fresh final review
18
+ `$to-tickets` owns complete whole-packet `$plan-review`, one fresh final review
19
19
  after any consolidated repair, one explicit user approval, serialized
20
20
  publication, reconciliation, and tracker read-back.
21
21
 
@@ -46,10 +46,6 @@ outcome and blocking relationship. Risk strengthens proof and review focus; it
46
46
  does not create tickets. Merge steps that share one owner, release, and
47
47
  validation path.
48
48
 
49
- Do not publish a child whose outcome is only transient evidence or a tracker
50
- comment. Resolve that discovery before compiling the executable graph, or make
51
- the required durable result a committed artifact.
52
-
53
49
  Where repository evidence proves a small prefactor is required, "Make the
54
50
  change easy, then make the easy change." Keep it inside the same vertical
55
51
  outcome unless it is independently verifiable and genuinely blocks later work.
@@ -145,12 +141,12 @@ an explicit blocking discovery outcome. The expected review verdict must be
145
141
 
146
142
  ### 4. Run one fresh semantic packet review
147
143
 
148
- After the complete packet satisfies the freeze conditions, launch exactly one
149
- fresh `standards_reviewer` without history
144
+ After the complete packet satisfies the freeze conditions, invoke
145
+ `$plan-review` with exactly one fresh `plan_reviewer` without history
150
146
  (`fork_context=false` on V1; `fork_turns="none"` on V2). Begin with
151
- `Assigned role: standards_reviewer`, provide the full authority and packet, and
152
- apply all three lenses in the same activation: source fidelity, ticket
153
- executability, and minimum solution and scope conservation.
147
+ `Assigned role: plan_reviewer`, provide the full authority and packet, and apply
148
+ all three lenses in the same activation: source fidelity, ticket executability,
149
+ and minimum solution and scope conservation.
154
150
 
155
151
  - **Source fidelity:** every product claim, decision, scope boundary,
156
152
  consequence, and blocker is grounded in the source; no behavior or ownership
@@ -193,17 +189,21 @@ whole-packet review and must not stop after representative findings. Capture a
193
189
  non-empty fresh child identity and wait for that same child. Do not split the
194
190
  lenses across children and do not launch the delivery Standards review.
195
191
 
196
- After `NEEDS_WORK`, repair all verified blockers together and sweep the
197
- complete packet for every defect class they expose. Do not review intermediate
198
- repair edits. If a blocker exposes unfinished inventory, authority, or
199
- composition, return to drafting and pass the freeze conditions again. Once the
200
- complete revised packet satisfies the freeze conditions, launch one fresh
201
- final whole-packet reviewer without prior review history. A same-context or
202
- findings-only recheck cannot approve. Further review is justified only by a
203
- remaining material blocker; optional hardening, broader proof, stylistic
204
- refinement, or requirements without authority do not reopen the review cycle.
205
- Missing or failed review blocks publication; product-changing repairs return
206
- to the user.
192
+ When review returns a plan-changing `QUESTION`, return it through Plan to the
193
+ user and stop without revising or publishing the packet. Resume only after the
194
+ answer becomes authority and the complete packet is settled again.
195
+
196
+ After `NEEDS_WORK` with verified blockers, repair all blockers together and
197
+ sweep the complete packet for every defect class they expose. Do not review
198
+ intermediate repair edits. If a blocker exposes unfinished inventory,
199
+ authority, or composition, return to drafting and pass the freeze conditions
200
+ again. Once the complete revised packet satisfies the freeze conditions,
201
+ launch one fresh final whole-packet `plan_reviewer` without prior review
202
+ history. Use one fresh reviewer per settled revision; a same-context recheck
203
+ cannot approve. Further review is justified only by a remaining material
204
+ blocker; optional hardening, broader proof, stylistic refinement, or
205
+ requirements without authority do not reopen the review cycle. Missing or
206
+ failed review blocks publication; product-changing repairs return to the user.
207
207
 
208
208
  ### 5. Get one explicit approval
209
209
 
@@ -128,6 +128,31 @@
128
128
  "prompt": "UI acceptance requires dynamic content absent from the proposed API or DTO.",
129
129
  "expected": ["reject the packet until an existing or authorized data contract supplies the content"],
130
130
  "forbidden": ["let the UI invent the data", "add a new owner solely for proof"]
131
+ },
132
+ {
133
+ "id": "final-packet-uses-plan-review-once",
134
+ "prompt": "Compile an approved PRD into a complete publish-ready Parent and multi-ticket packet.",
135
+ "expected": [
136
+ "do not review the intermediate PRD",
137
+ "invoke one fresh plan-review over the complete frozen packet",
138
+ "cover source fidelity, ticket executability, and minimum solution in that review"
139
+ ],
140
+ "forbidden": [
141
+ "invoke standards_reviewer for planning review",
142
+ "review both the PRD and final packet"
143
+ ]
144
+ },
145
+ {
146
+ "id": "plan-review-question-returns-to-user",
147
+ "prompt": "The final packet review raises an unresolved ownership question but finds no verified blocker.",
148
+ "expected": [
149
+ "return the question through Plan to the user",
150
+ "resume only after the answer becomes authority and the packet is settled again"
151
+ ],
152
+ "forbidden": [
153
+ "guess the answer",
154
+ "repair or publish the packet"
155
+ ]
131
156
  }
132
157
  ]
133
158
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "codex-orchestrator",
3
- "version": "2.0.18",
3
+ "version": "2.0.19",
4
4
  "description": "Reusable GitHub Issues runner for Codex.",
5
5
  "type": "module",
6
6
  "license": "MIT",