okstra 0.229.0 → 0.230.0
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/README.md +1 -5
- package/dist/cli-registry.mjs +0 -18
- package/dist/cli-registry.mjs.map +1 -1
- package/dist/commands/lifecycle/doctor.mjs +0 -15
- package/dist/commands/lifecycle/doctor.mjs.map +1 -1
- package/dist/lib/skill-catalog.mjs +4 -4
- package/dist/lib/skill-catalog.mjs.map +1 -1
- package/docs/architecture/storage-model.md +105 -16
- package/docs/architecture.md +13 -14
- package/docs/contributor-change-matrix.md +5 -5
- package/docs/project-structure-overview.md +11 -18
- package/package.json +1 -2
- package/runtime/BUILD.json +2 -2
- package/runtime/bin/lib/okstra/interactive.sh +2 -1
- package/runtime/prompts/launch.template.md +5 -5
- package/runtime/prompts/lead/convergence.md +4 -4
- package/runtime/prompts/lead/okstra-lead-contract.md +14 -13
- package/runtime/prompts/lead/phase-routing.md +1 -1
- package/runtime/prompts/lead/report-writer.md +3 -3
- package/runtime/prompts/lead/team-contract.md +3 -3
- package/runtime/python/okstra_ctl/agent/invocation.py +142 -5
- package/runtime/python/okstra_ctl/agent/prompt_cli/materialize.py +31 -1
- package/runtime/python/okstra_ctl/cmux.py +4 -2
- package/runtime/python/okstra_ctl/code_review_census.py +194 -0
- package/runtime/python/okstra_ctl/code_review_coverage.py +3 -1
- package/runtime/python/okstra_ctl/code_review_scope.py +9 -6
- package/runtime/python/okstra_ctl/code_review_target.py +38 -2
- package/runtime/python/okstra_ctl/conformance.py +30 -0
- package/runtime/python/okstra_ctl/conformance_evidence.py +235 -0
- package/runtime/python/okstra_ctl/correction_round.py +19 -13
- package/runtime/python/okstra_ctl/dispatch_core.py +1 -1
- package/runtime/python/okstra_ctl/dispatch_state.py +1 -0
- package/runtime/python/okstra_ctl/generated_input.py +21 -0
- package/runtime/python/okstra_ctl/ids.py +1 -41
- package/runtime/python/okstra_ctl/initial_prompt_materialization.py +30 -0
- package/runtime/python/okstra_ctl/interactive_cli.py +5 -0
- package/runtime/python/okstra_ctl/locks.py +28 -1
- package/runtime/python/okstra_ctl/model_io/renderers.py +7 -0
- package/runtime/python/okstra_ctl/paths.py +75 -33
- package/runtime/python/okstra_ctl/phases/catalog.py +3 -0
- package/runtime/python/okstra_ctl/phases/change_impact_analysis/spec.md +2 -2
- package/runtime/python/okstra_ctl/phases/discussion/spec.md +63 -63
- package/runtime/python/okstra_ctl/phases/discussion/wizard.py +2 -11
- package/runtime/python/okstra_ctl/phases/error_analysis/report_assets/error-analysis-input.template.md +1 -1
- package/runtime/python/okstra_ctl/phases/error_analysis/spec.md +2 -2
- package/runtime/python/okstra_ctl/phases/feature_analysis/spec.md +1 -1
- package/runtime/python/okstra_ctl/phases/final_verification/profile.md +4 -4
- package/runtime/python/okstra_ctl/phases/final_verification/report_assets/final-verification-input.template.md +1 -1
- package/runtime/python/okstra_ctl/phases/final_verification/spec.md +4 -4
- package/runtime/python/okstra_ctl/phases/implementation/host-rules.md +1 -1
- package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-deliverable.md +2 -2
- package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-executor.md +1 -1
- package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-verifier.md +4 -4
- package/runtime/python/okstra_ctl/phases/implementation/report_assets/implementation-input.template.md +1 -1
- package/runtime/python/okstra_ctl/phases/implementation/spec.md +4 -4
- package/runtime/python/okstra_ctl/phases/implementation_option_selection/spec.md +2 -2
- package/runtime/python/okstra_ctl/phases/implementation_planning/instructions/plan-body-verification.md +11 -11
- package/runtime/python/okstra_ctl/phases/implementation_planning/plan_body.py +14 -0
- package/runtime/python/okstra_ctl/phases/implementation_planning/profile.md +4 -4
- package/runtime/python/okstra_ctl/phases/implementation_planning/report_assets/implementation-planning-input.template.md +1 -1
- package/runtime/python/okstra_ctl/phases/implementation_planning/spec.md +1 -1
- package/runtime/python/okstra_ctl/phases/project_analysis/spec.md +2 -2
- package/runtime/python/okstra_ctl/phases/release_handoff/entry.py +7 -3
- package/runtime/python/okstra_ctl/phases/release_handoff/report_assets/release-handoff-input.template.md +1 -1
- package/runtime/python/okstra_ctl/phases/release_handoff/spec.md +4 -4
- package/runtime/python/okstra_ctl/phases/technical_verification/spec.md +1 -1
- package/runtime/python/okstra_ctl/process_group.py +26 -3
- package/runtime/python/okstra_ctl/qa_commands.py +5 -1
- package/runtime/python/okstra_ctl/recap.py +1 -2
- package/runtime/python/okstra_ctl/render.py +10 -2
- package/runtime/python/okstra_ctl/report_finalize.py +3 -3
- package/runtime/python/okstra_ctl/report_synthesis_packet.py +5 -0
- package/runtime/python/okstra_ctl/run.py +24 -20
- package/runtime/python/okstra_ctl/stage_command_commits.py +143 -0
- package/runtime/python/okstra_ctl/verification_capture.py +291 -0
- package/runtime/python/okstra_ctl/verification_conformance.py +28 -9
- package/runtime/python/okstra_ctl/verification_dispatch.py +130 -0
- package/runtime/python/okstra_ctl/verification_evidence.py +652 -0
- package/runtime/python/okstra_ctl/verification_generation.py +22 -12
- package/runtime/python/okstra_ctl/verification_input_ref.py +9 -0
- package/runtime/python/okstra_ctl/verification_input_types.py +2 -0
- package/runtime/python/okstra_ctl/verification_inputs.py +73 -2
- package/runtime/python/okstra_ctl/verification_invocation.py +139 -0
- package/runtime/python/okstra_ctl/verification_target.py +10 -3
- package/runtime/python/okstra_ctl/wizard/registry.py +2 -1
- package/runtime/python/okstra_ctl/wizard/render.py +2 -1
- package/runtime/python/okstra_ctl/wizard/sources.py +14 -3
- package/runtime/python/okstra_ctl/wizard/steps_identity.py +2 -1
- package/runtime/python/okstra_ctl/worker_runner.py +1 -1
- package/runtime/python/okstra_ctl/worktree_lock_cli.py +70 -17
- package/runtime/python/okstra_ctl/worktree_registry.py +4 -0
- package/runtime/skills/okstra-code-review/SKILL.md +7 -5
- package/runtime/skills/okstra-code-review/references/census-rules.md +2 -2
- package/runtime/skills/okstra-explain-flow/SKILL.md +1 -1
- package/runtime/skills/okstra-run/SKILL.md +6 -6
- package/runtime/skills/okstra-schedule-gen/SKILL.md +3 -3
- package/runtime/skills/okstra-setup/SKILL.md +2 -3
- package/runtime/validators/validate-run.py +110 -19
- package/docs/cli.md +0 -1060
- package/docs/container.md +0 -100
- package/docs/follow-ups/2026-07-10-final-report-option-3.md +0 -51
- package/docs/performance-improvement-plan-v2.md +0 -369
- package/runtime/python/okstra_ctl/container.py +0 -702
- package/runtime/python/okstra_ctl/rollup.py +0 -241
- package/runtime/python/okstra_ctl/usage_report.py +0 -362
- package/runtime/skills/okstra-container-build/SKILL.md +0 -139
- package/runtime/skills/okstra-inspect/SKILL.md +0 -100
- package/runtime/skills/okstra-inspect/facets/cost.md +0 -84
- package/runtime/skills/okstra-inspect/facets/error-zip.md +0 -41
- package/runtime/skills/okstra-inspect/facets/errors.md +0 -69
- package/runtime/skills/okstra-inspect/facets/history.md +0 -86
- package/runtime/skills/okstra-inspect/facets/logs.md +0 -89
- package/runtime/skills/okstra-inspect/facets/recap.md +0 -167
- package/runtime/skills/okstra-inspect/facets/report.md +0 -57
- package/runtime/skills/okstra-inspect/facets/run-audit.md +0 -34
- package/runtime/skills/okstra-inspect/facets/status.md +0 -163
- package/runtime/skills/okstra-inspect/facets/time.md +0 -57
- package/runtime/skills/okstra-rollup/SKILL.md +0 -75
- package/runtime/skills/okstra-usage/SKILL.md +0 -71
|
@@ -4,64 +4,64 @@
|
|
|
4
4
|
|
|
5
5
|
| ID | Guarantee | Enforcement |
|
|
6
6
|
|---|---|---|
|
|
7
|
-
| DS-1 | `discussion` is a registered task type whose profile, role contract and report assets live in this package |
|
|
8
|
-
| DS-2 | Roles are analyser 1..5 (recommended 3), report-writer 1 and a dynamic verifier per selected analyser; the lead is the facilitator |
|
|
7
|
+
| DS-1 | `discussion` is a registered task type whose profile, role contract and report assets live in this package | unenforced |
|
|
8
|
+
| DS-2 | Roles are analyser 1..5 (recommended 3), report-writer 1 and a dynamic verifier per selected analyser; the lead is the facilitator | unenforced |
|
|
9
9
|
| DS-3 | Analysers receive the `discussion-worker` duty through the common prompt policy | `scripts/okstra_ctl/worker_prompt_policy.py::ANALYSIS_DUTY_BY_TASK_TYPE` |
|
|
10
|
-
| DS-4 | A supported lead reaches the common worker dispatch plan without a separate executor |
|
|
11
|
-
| DS-5 | A non-`claude-code` lead outside cmux is rejected before any task artifact is written |
|
|
10
|
+
| DS-4 | A supported lead reaches the common worker dispatch plan without a separate executor | unenforced |
|
|
11
|
+
| DS-5 | A non-`claude-code` lead outside cmux is rejected before any task artifact is written | unenforced |
|
|
12
12
|
| DS-6 | The run carries no lifecycle routing; the next-phase pointer stays pending | `scripts/okstra_ctl/next_phase.py::_SIDETRACK_TASK_TYPES` |
|
|
13
|
-
| DS-7 | Completion requires the user's confirmation, not agent consensus or a convergence stop: the derived phase reaches `completed` only from a revision published by `confirm-completion`, and `cycle-close` only ends a verification cycle (DS-19) |
|
|
14
|
-
| DS-8 | A discussion starts without a brief: prepare takes `--discussion-start`, refuses `--task-brief`, and writes the input document that takes the brief's place |
|
|
15
|
-
| DS-9 | A start-input error is refused before prepare writes any run artifact or discussion record |
|
|
16
|
-
| DS-10 | The wizard asks for the start input instead of a brief, from a new task (`okstra wizard init --task-type discussion`) and from an existing task; every other task type keeps its question order |
|
|
17
|
-
| DS-11 | A resent question, answer or decision returns the stored record instead of adding a second one; a different answer to an answered question is refused |
|
|
18
|
-
| DS-12 | An append cut off mid-line and a draft that lags the records both recover on the next read or write |
|
|
19
|
-
| DS-13 | Concurrent writers keep every record and get distinct ids |
|
|
20
|
-
| DS-14 | A record names its author and the discussion run it came from; a run manifest of another task, or a start input naming another task's discussion, is refused |
|
|
21
|
-
| DS-15 | Continuing a discussion hands the next run the confirmed subject, the user decisions and the questions still waiting for an answer |
|
|
22
|
-
| DS-16 | A direct question is dispatched alone to its addressee as a new `discussion-question` invocation built from the discussion read model, through the common `agent-prompt materialize --batch` path; its whole result is recorded once as the addressee's answer and reaches every participant's next instruction |
|
|
23
|
-
| DS-17 | Questions go to the user one at a time in record order, and no research cycle opens while a question waits for the user or a participant |
|
|
24
|
-
| DS-18 | A research cycle whose input references (start inputs, subject, answers, materials) equal the last closed cycle's is not dispatched; the remaining disagreements and options go to the user. New evidence or a new alternative opens the next cycle in a continuation run |
|
|
25
|
-
| DS-19 | Closing a cycle imports the convergence findings as claims with their origin author and the verifiers' verdicts, ends that verification cycle only, and leaves user decisions and user questions untouched |
|
|
26
|
-
| DS-20 | An author's vote on its own claim is refused, not counted as a refutation — the convergence engine's final-state validation is reused |
|
|
27
|
-
| DS-21 | A batch-start failure and a failure left after the dispatcher's retry loop are recorded per participant without deleting completed results; the cycle neither reopens research nor closes until the user chooses retry, replace or reduce, and a second, different choice for the same failure is refused |
|
|
28
|
-
| DS-22 | A retry stays in the same run as a new invocation; a replacement continues in a run prepared with `--discussion-start <task-key>`, whose research input carries the earlier results under their original author and run, and every cycle records its roster |
|
|
29
|
-
| DS-23 | A failed direct question waits for the user's choice; `reduce` drops it from the participants' pending questions and `replace` is refused for it |
|
|
30
|
-
| DS-24 | Concurrent `cycle-open` calls for one run record one cycle |
|
|
31
|
-
| DS-25 | On a `claude-code` lead, whose analysers run as native sessions, `settle` reads the common `record-dispatch` / `link-result` / `abandon-attempt` records: a linked result is a result, an attempt closed without one is a failure, and an open attempt refuses settlement |
|
|
32
|
-
| DS-26 | A `discussion-question` prompt keeps the analysis contract but stays outside the analysis-core prompt equality group |
|
|
33
|
-
| DS-27 | A confirmation names the draft version the user saw; a version older than the current records, or a stored confirmation followed by any later record, publishes nothing |
|
|
34
|
-
| DS-28 | Completion is refused while the subject, a requirement, an in-scope or an excluded entry, a closed research cycle, a user or participant answer, or a failure choice is missing; remaining disagreements do not block and are carried into the revision with their standing |
|
|
35
|
-
| DS-29 | A revision carries the subject, start inputs, requirements with the follow-up they apply to, scope and exclusions, direction, the user's confirmation, decisions, disagreements, evidence claims, unverified scope, every cycle's roster and every failure with the user's choice; a reduced roster is marked and its failure listed as unverified |
|
|
36
|
-
| DS-30 | One confirmation publishes one revision, `<task-key>/revision-NNN` by completion sequence, written once read-only; a resent or concurrent confirmation returns that revision |
|
|
37
|
-
| DS-31 | A publication interrupted before the revision file is written leaves no revision; resending the same confirmation publishes it |
|
|
38
|
-
| DS-32 | A completed discussion takes no record but `reopen` naming its latest revision, and prepare refuses a new start input for it; after `reopen`, the new draft and the earlier revision read side by side, the earlier revision's bytes never change, and the next revision carries its id, content digest and the reason for change |
|
|
39
|
-
| DS-33 | The final report's `discussion` block is written by report assembly, never by the report writer, and carries only the revision id and content digest (or the draft version); assembly refuses a block whose digest no longer matches the revision file, `validate-run` reports the mismatch, and the run passes the reachable `report-finalize` steps without real providers |
|
|
40
|
-
| DS-34 | Finalizing a run whose discussion is still a draft publishes no revision; its report carries the draft version |
|
|
41
|
-
| DS-35 | A follow-up brief carries the revision's common requirements and those of its follow-up label, each with its record id; the other follow-ups' requirements and the excluded scope are listed as out of scope; it passes `validators/validate-brief.py` and recommends `requirements-discovery`. A discussion with no follow-up lists its labels as unlinked |
|
|
42
|
-
| DS-36 | Fields reused from the user's confirmations name their record in the revision; an observation method the revision does not carry is new meaning, so the brief stays `reporter-confirmations: pending` with an `intent-check:` row and prepare refuses it until the user confirms |
|
|
43
|
-
| DS-37 | The follow-up's brief pins the discussion, revision id, content digest and requirement ids; prepare records them in the run inputs as `discussionRevisionRef`, and the manager launch packet carries the same reference and starts a new child at `requirements-discovery` |
|
|
44
|
-
| DS-38 | A newer revision flags every linked follow-up `needs-impact-review` with the changes from its pinned revision; a follow-up never moves by itself (`follow-up-brief` for another revision is refused), only the follow-up the user adopts with `apply` moves, a resent `apply` returns the stored record, and a different choice for the same follow-up and revision is refused |
|
|
45
|
-
| DS-39 | Adopting a revision for a follow-up that has an implementation-planning plan routes it to the plan amendment path and leaves its plan and brief byte-identical |
|
|
46
|
-
| DS-40 | The target brief is written before the link record; a link write interrupted after the brief, or a torn link line, is completed by resending the same command, and the link is recorded once |
|
|
47
|
-
| DS-41 | `links` re-reads each target's brief, also in another project; a target that cannot be read is `unknown`, never `current`; a brief this command did not write last is not replaced without `--replace` |
|
|
48
|
-
| DS-42 | `confirm-completion` registers the published revision in the Memory Book without a prompt, through `okstra memory add --source-key discussion:<revision-id>`; the entry holds a summary of decisions, disagreements, risks and unverified scope with the revision id, content digest, project and task — not the start inputs or the agreed evidence — and searching the revision id finds it |
|
|
49
|
-
| DS-43 | A re-discussion's revision is a new source key and a separate Memory Book entry |
|
|
50
|
-
| DS-44 | A resent confirmation does not call the Memory Book again, and concurrent registrations of one revision leave one entry; with the discussion's registration state lost, the Memory Book's own source-key check returns the stored entry | `
|
|
51
|
-
| DS-45 | A failed registration leaves the revision published and `pending`; `status` lists it under `memoryRegistration` and `memory-sync` retries it with the same source key |
|
|
52
|
-
| DS-46 | A summary the Memory Book refuses as a likely secret is `refused` with the secret kinds shown; `memory-sync` does not retry it, and an unchanged `--summary-file` is refused; only a changed summary registers | `
|
|
13
|
+
| DS-7 | Completion requires the user's confirmation, not agent consensus or a convergence stop: the derived phase reaches `completed` only from a revision published by `confirm-completion`, and `cycle-close` only ends a verification cycle (DS-19) | unenforced |
|
|
14
|
+
| DS-8 | A discussion starts without a brief: prepare takes `--discussion-start`, refuses `--task-brief`, and writes the input document that takes the brief's place | unenforced |
|
|
15
|
+
| DS-9 | A start-input error is refused before prepare writes any run artifact or discussion record | unenforced |
|
|
16
|
+
| DS-10 | The wizard asks for the start input instead of a brief, from a new task (`okstra wizard init --task-type discussion`) and from an existing task; every other task type keeps its question order | unenforced |
|
|
17
|
+
| DS-11 | A resent question, answer or decision returns the stored record instead of adding a second one; a different answer to an answered question is refused | unenforced |
|
|
18
|
+
| DS-12 | An append cut off mid-line and a draft that lags the records both recover on the next read or write | unenforced |
|
|
19
|
+
| DS-13 | Concurrent writers keep every record and get distinct ids | unenforced |
|
|
20
|
+
| DS-14 | A record names its author and the discussion run it came from; a run manifest of another task, or a start input naming another task's discussion, is refused | unenforced |
|
|
21
|
+
| DS-15 | Continuing a discussion hands the next run the confirmed subject, the user decisions and the questions still waiting for an answer | unenforced |
|
|
22
|
+
| DS-16 | A direct question is dispatched alone to its addressee as a new `discussion-question` invocation built from the discussion read model, through the common `agent-prompt materialize --batch` path; its whole result is recorded once as the addressee's answer and reaches every participant's next instruction | unenforced |
|
|
23
|
+
| DS-17 | Questions go to the user one at a time in record order, and no research cycle opens while a question waits for the user or a participant | unenforced |
|
|
24
|
+
| DS-18 | A research cycle whose input references (start inputs, subject, answers, materials) equal the last closed cycle's is not dispatched; the remaining disagreements and options go to the user. New evidence or a new alternative opens the next cycle in a continuation run | unenforced |
|
|
25
|
+
| DS-19 | Closing a cycle imports the convergence findings as claims with their origin author and the verifiers' verdicts, ends that verification cycle only, and leaves user decisions and user questions untouched | unenforced |
|
|
26
|
+
| DS-20 | An author's vote on its own claim is refused, not counted as a refutation — the convergence engine's final-state validation is reused | unenforced |
|
|
27
|
+
| DS-21 | A batch-start failure and a failure left after the dispatcher's retry loop are recorded per participant without deleting completed results; the cycle neither reopens research nor closes until the user chooses retry, replace or reduce, and a second, different choice for the same failure is refused | unenforced |
|
|
28
|
+
| DS-22 | A retry stays in the same run as a new invocation; a replacement continues in a run prepared with `--discussion-start <task-key>`, whose research input carries the earlier results under their original author and run, and every cycle records its roster | unenforced |
|
|
29
|
+
| DS-23 | A failed direct question waits for the user's choice; `reduce` drops it from the participants' pending questions and `replace` is refused for it | unenforced |
|
|
30
|
+
| DS-24 | Concurrent `cycle-open` calls for one run record one cycle | unenforced |
|
|
31
|
+
| DS-25 | On a `claude-code` lead, whose analysers run as native sessions, `settle` reads the common `record-dispatch` / `link-result` / `abandon-attempt` records: a linked result is a result, an attempt closed without one is a failure, and an open attempt refuses settlement | unenforced |
|
|
32
|
+
| DS-26 | A `discussion-question` prompt keeps the analysis contract but stays outside the analysis-core prompt equality group | unenforced |
|
|
33
|
+
| DS-27 | A confirmation names the draft version the user saw; a version older than the current records, or a stored confirmation followed by any later record, publishes nothing | unenforced |
|
|
34
|
+
| DS-28 | Completion is refused while the subject, a requirement, an in-scope or an excluded entry, a closed research cycle, a user or participant answer, or a failure choice is missing; remaining disagreements do not block and are carried into the revision with their standing | unenforced |
|
|
35
|
+
| DS-29 | A revision carries the subject, start inputs, requirements with the follow-up they apply to, scope and exclusions, direction, the user's confirmation, decisions, disagreements, evidence claims, unverified scope, every cycle's roster and every failure with the user's choice; a reduced roster is marked and its failure listed as unverified | unenforced |
|
|
36
|
+
| DS-30 | One confirmation publishes one revision, `<task-key>/revision-NNN` by completion sequence, written once read-only; a resent or concurrent confirmation returns that revision | unenforced |
|
|
37
|
+
| DS-31 | A publication interrupted before the revision file is written leaves no revision; resending the same confirmation publishes it | unenforced |
|
|
38
|
+
| DS-32 | A completed discussion takes no record but `reopen` naming its latest revision, and prepare refuses a new start input for it; after `reopen`, the new draft and the earlier revision read side by side, the earlier revision's bytes never change, and the next revision carries its id, content digest and the reason for change | unenforced |
|
|
39
|
+
| DS-33 | The final report's `discussion` block is written by report assembly, never by the report writer, and carries only the revision id and content digest (or the draft version); assembly refuses a block whose digest no longer matches the revision file, `validate-run` reports the mismatch, and the run passes the reachable `report-finalize` steps without real providers | unenforced |
|
|
40
|
+
| DS-34 | Finalizing a run whose discussion is still a draft publishes no revision; its report carries the draft version | unenforced |
|
|
41
|
+
| DS-35 | A follow-up brief carries the revision's common requirements and those of its follow-up label, each with its record id; the other follow-ups' requirements and the excluded scope are listed as out of scope; it passes `validators/validate-brief.py` and recommends `requirements-discovery`. A discussion with no follow-up lists its labels as unlinked | unenforced |
|
|
42
|
+
| DS-36 | Fields reused from the user's confirmations name their record in the revision; an observation method the revision does not carry is new meaning, so the brief stays `reporter-confirmations: pending` with an `intent-check:` row and prepare refuses it until the user confirms | unenforced |
|
|
43
|
+
| DS-37 | The follow-up's brief pins the discussion, revision id, content digest and requirement ids; prepare records them in the run inputs as `discussionRevisionRef`, and the manager launch packet carries the same reference and starts a new child at `requirements-discovery` | unenforced |
|
|
44
|
+
| DS-38 | A newer revision flags every linked follow-up `needs-impact-review` with the changes from its pinned revision; a follow-up never moves by itself (`follow-up-brief` for another revision is refused), only the follow-up the user adopts with `apply` moves, a resent `apply` returns the stored record, and a different choice for the same follow-up and revision is refused | unenforced |
|
|
45
|
+
| DS-39 | Adopting a revision for a follow-up that has an implementation-planning plan routes it to the plan amendment path and leaves its plan and brief byte-identical | unenforced |
|
|
46
|
+
| DS-40 | The target brief is written before the link record; a link write interrupted after the brief, or a torn link line, is completed by resending the same command, and the link is recorded once | unenforced |
|
|
47
|
+
| DS-41 | `links` re-reads each target's brief, also in another project; a target that cannot be read is `unknown`, never `current`; a brief this command did not write last is not replaced without `--replace` | unenforced |
|
|
48
|
+
| DS-42 | `confirm-completion` registers the published revision in the Memory Book without a prompt, through `okstra memory add --source-key discussion:<revision-id>`; the entry holds a summary of decisions, disagreements, risks and unverified scope with the revision id, content digest, project and task — not the start inputs or the agreed evidence — and searching the revision id finds it | unenforced |
|
|
49
|
+
| DS-43 | A re-discussion's revision is a new source key and a separate Memory Book entry | unenforced |
|
|
50
|
+
| DS-44 | A resent confirmation does not call the Memory Book again, and concurrent registrations of one revision leave one entry; with the discussion's registration state lost, the Memory Book's own source-key check returns the stored entry | `tests-js/memory.test.mjs::concurrent memory add --source-key of one key leaves one entry` |
|
|
51
|
+
| DS-45 | A failed registration leaves the revision published and `pending`; `status` lists it under `memoryRegistration` and `memory-sync` retries it with the same source key | unenforced |
|
|
52
|
+
| DS-46 | A summary the Memory Book refuses as a likely secret is `refused` with the secret kinds shown; `memory-sync` does not retry it, and an unchanged `--summary-file` is refused; only a changed summary registers | `tests-js/memory.test.mjs::memory add --source-key --json reports a secret refusal as JSON on stdout` |
|
|
53
53
|
| DS-47 | `memory add` without `--source-key` writes the same index row and frontmatter as before and takes no source-key lock | `tests-js/memory.test.mjs::a plain memory add keeps its index row and frontmatter free of a source key` |
|
|
54
|
-
| DS-48 | `okstra manager task sync` records a discussion child's state, phase, pending questions, revisions with their change reasons and each follow-up's pinned revision and review state by reference — no requirement or revision content — without writing to the discussion's project; `task status` counts the child under `discussion`, never `done`, and a discussion completes with no manager |
|
|
55
|
-
| DS-49 | A discussion record or follow-up brief the manager cannot read is `unknown` on the next sync, not its last synced value |
|
|
56
|
-
| DS-50 | A manager child without a registered brief launches with the follow-up brief `follow-up-brief` wrote for it, found in the last-synced links of a discussion child of the same manager task, and carries its pinned revision |
|
|
57
|
-
| DS-51 | `okstra-discussion` (`okstra wizard init --task-type discussion`) and `okstra-run`'s task-type pick produce the same `render-bundle` argv and the same prepared run inputs |
|
|
58
|
-
| DS-52 | `okstra.sh` forwards `--discussion-start`, asks for it instead of a brief, and passes no `--task-brief` for a discussion |
|
|
59
|
-
| DS-53 | A same-provider and a mixed-provider roster go through the same prepare, assignment and research-batch `materialize` path; on a `claude-code` lead only the analysers outside the host's provider are planned by `worker-dispatch` as `cli-wrapper` |
|
|
60
|
-
| DS-54 | The lead instructions carry the boundary's source-edit and implementation-plan prohibitions; every discussion worker runs under a `source-readonly` write policy, and a worker that edits source is refused by the common mutation audit and recorded as a failure, never a result |
|
|
61
|
-
| DS-55 | Concurrent `apply` choices for one follow-up and revision record one `apply`; the other choices are refused and the brief follows only the recorded choice |
|
|
62
|
-
| DS-56 | One isolated project runs the whole flow through prepare and `okstra discussion`: a description start (no research before the subject is confirmed), a refutation cycle, an interrupted run resumed with the same pending question and a resent answer stored once, a second cycle opened only by new input, completion with a remaining disagreement and Memory Book registration, two follow-ups at `requirements-discovery` with the revision in the run inputs, a re-discussion, and adoption of the new revision by one follow-up only; the project source stays unchanged |
|
|
63
|
-
| DS-57 | After `reopen` the draft starts with the reopened revision's requirements and scope under their original record ids, each marked with that revision; completion needs no re-entry of them; adding an item the draft holds returns it; `withdraw` removes one item with the user's reason, a resend returns it and a second withdrawal of the same item is refused; the next revision's `itemChanges` lists what it carried, added and withdrawn, `impact` shows each withdrawal's reason, and the earlier revision's bytes do not change |
|
|
64
|
-
| DS-58 | A follow-up routed to plan amendment moves only through `complete-amendment`, and only after the target has an implementation-planning report newer than the one at routing with `frontmatter.approved: true`; without it the command is refused naming what is missing and `links` stays `amendment-pending` with that reason (`unknown` when the plan cannot be read). Completion rewrites the brief under the `--replace` rule, records the previous and new revision, the routed `apply` and the plan report, leaves every plan byte unchanged, turns the target `current`, and a resend returns the record |
|
|
54
|
+
| DS-48 | `okstra manager task sync` records a discussion child's state, phase, pending questions, revisions with their change reasons and each follow-up's pinned revision and review state by reference — no requirement or revision content — without writing to the discussion's project; `task status` counts the child under `discussion`, never `done`, and a discussion completes with no manager | unenforced |
|
|
55
|
+
| DS-49 | A discussion record or follow-up brief the manager cannot read is `unknown` on the next sync, not its last synced value | unenforced |
|
|
56
|
+
| DS-50 | A manager child without a registered brief launches with the follow-up brief `follow-up-brief` wrote for it, found in the last-synced links of a discussion child of the same manager task, and carries its pinned revision | unenforced |
|
|
57
|
+
| DS-51 | `okstra-discussion` (`okstra wizard init --task-type discussion`) and `okstra-run`'s task-type pick produce the same `render-bundle` argv and the same prepared run inputs | unenforced |
|
|
58
|
+
| DS-52 | `okstra.sh` forwards `--discussion-start`, asks for it instead of a brief, and passes no `--task-brief` for a discussion | unenforced |
|
|
59
|
+
| DS-53 | A same-provider and a mixed-provider roster go through the same prepare, assignment and research-batch `materialize` path; on a `claude-code` lead only the analysers outside the host's provider are planned by `worker-dispatch` as `cli-wrapper` | unenforced |
|
|
60
|
+
| DS-54 | The lead instructions carry the boundary's source-edit and implementation-plan prohibitions; every discussion worker runs under a `source-readonly` write policy, and a worker that edits source is refused by the common mutation audit and recorded as a failure, never a result | unenforced |
|
|
61
|
+
| DS-55 | Concurrent `apply` choices for one follow-up and revision record one `apply`; the other choices are refused and the brief follows only the recorded choice | unenforced |
|
|
62
|
+
| DS-56 | One isolated project runs the whole flow through prepare and `okstra discussion`: a description start (no research before the subject is confirmed), a refutation cycle, an interrupted run resumed with the same pending question and a resent answer stored once, a second cycle opened only by new input, completion with a remaining disagreement and Memory Book registration, two follow-ups at `requirements-discovery` with the revision in the run inputs, a re-discussion, and adoption of the new revision by one follow-up only; the project source stays unchanged | unenforced |
|
|
63
|
+
| DS-57 | After `reopen` the draft starts with the reopened revision's requirements and scope under their original record ids, each marked with that revision; completion needs no re-entry of them; adding an item the draft holds returns it; `withdraw` removes one item with the user's reason, a resend returns it and a second withdrawal of the same item is refused; the next revision's `itemChanges` lists what it carried, added and withdrawn, `impact` shows each withdrawal's reason, and the earlier revision's bytes do not change | unenforced |
|
|
64
|
+
| DS-58 | A follow-up routed to plan amendment moves only through `complete-amendment`, and only after the target has an implementation-planning report newer than the one at routing with `frontmatter.approved: true`; without it the command is refused naming what is missing and `links` stays `amendment-pending` with that reason (`unknown` when the plan cannot be read). Completion rewrites the brief under the `--replace` rule, records the previous and new revision, the routed `apply` and the plan report, leaves every plan byte unchanged, turns the target `current`, and a resend returns the record | unenforced |
|
|
65
65
|
|
|
66
66
|
## 1. Purpose
|
|
67
67
|
|
|
@@ -165,20 +165,20 @@ The design's acceptance scenarios and the tests that prove them. Each test drive
|
|
|
165
165
|
|
|
166
166
|
| # | Scenario | Tests |
|
|
167
167
|
|---|---|---|
|
|
168
|
-
| 1 | A short description starts the discussion; research runs in parallel only after the user confirms the subject | `test_discussion_end_to_end.py::test_a_discussion_runs_from_a_description_to_one_adopted_follow_up
|
|
169
|
-
| 2 | Same-provider and mixed-provider rosters use the same prepare and assignment path |
|
|
168
|
+
| 1 | A short description starts the discussion; research runs in parallel only after the user confirms the subject | `test_discussion_end_to_end.py::test_a_discussion_runs_from_a_description_to_one_adopted_follow_up` |
|
|
169
|
+
| 2 | Same-provider and mixed-provider rosters use the same prepare and assignment path | unenforced |
|
|
170
170
|
| 3 | A question to one participant and its answer reach every participant's next input | `test_discussion_workflow.py::test_a_direct_question_is_dispatched_alone_and_its_answer_reaches_every_participant` |
|
|
171
|
-
| 4 | Resuming while a question waits restores it, and a stored answer is not processed twice | `
|
|
171
|
+
| 4 | Resuming while a question waits restores it, and a stored answer is not processed twice | `test_discussion_store.py::test_a_resent_answer_is_stored_once_and_a_different_one_is_refused`, `test_discussion_end_to_end.py::test_a_discussion_runs_from_a_description_to_one_adopted_follow_up` |
|
|
172
172
|
| 5 | A repeated claim set stops further calls and presents disagreements and options | `test_discussion_workflow.py::test_a_repeated_input_is_not_researched_again_and_goes_to_the_user` |
|
|
173
173
|
| 6 | With a grounded disagreement left, the user's risk confirmation publishes a revision that carries it | `test_discussion_completion.py::test_the_user_completes_with_disagreements_and_the_revision_keeps_them` |
|
|
174
174
|
| 7 | Replacing a failed participant opens a new run of the same discussion and keeps earlier authors and results | `test_discussion_workflow.py::test_a_replacement_continues_in_a_new_run_and_keeps_the_original_authors` |
|
|
175
175
|
| 8 | After a re-discussion both follow-ups of the first revision need impact review; only the one the user picks adopts the new revision | `test_discussion_followup.py::test_only_the_follow_up_the_user_selects_adopts_the_new_revision`, `test_discussion_end_to_end.py::test_a_discussion_runs_from_a_description_to_one_adopted_follow_up` |
|
|
176
176
|
| 9 | A failed Memory Book registration keeps the revision; retries leave one entry per revision | `test_discussion_memory.py::test_a_failed_registration_keeps_the_revision_and_memory_sync_recovers`, `test_discussion_memory.py::test_a_resent_or_concurrent_registration_leaves_one_entry` |
|
|
177
|
-
| 10 | A discussion completes without a manager; a linked manager keeps discussion completion apart from implementation completion |
|
|
178
|
-
| 11 | A discussion run neither edits project source nor writes a detailed implementation plan | `
|
|
179
|
-
| 12 | The `okstra-run` wizard starts a discussion without a brief; other task types keep their question order |
|
|
180
|
-
| 13 | A lead host outside the supported combinations is refused before the run |
|
|
181
|
-
| 14 | A follow-up starts at `requirements-discovery` and its run inputs keep the revision reference | `test_discussion_followup.py::test_a_follow_up_brief_carries_its_requirements_and_starts_at_requirements_discovery
|
|
177
|
+
| 10 | A discussion completes without a manager; a linked manager keeps discussion completion apart from implementation completion | unenforced |
|
|
178
|
+
| 11 | A discussion run neither edits project source nor writes a detailed implementation plan | `test_discussion_end_to_end.py::test_a_discussion_runs_from_a_description_to_one_adopted_follow_up` |
|
|
179
|
+
| 12 | The `okstra-run` wizard starts a discussion without a brief; other task types keep their question order | unenforced |
|
|
180
|
+
| 13 | A lead host outside the supported combinations is refused before the run | unenforced |
|
|
181
|
+
| 14 | A follow-up starts at `requirements-discovery` and its run inputs keep the revision reference | `test_discussion_followup.py::test_a_follow_up_brief_carries_its_requirements_and_starts_at_requirements_discovery` |
|
|
182
182
|
| 15 | A secret refusal is shown and not retried; the revision stays | `test_discussion_memory.py::test_a_secret_refusal_is_shown_and_retried_only_after_the_summary_changes` |
|
|
183
183
|
|
|
184
184
|
Scenario 11 rests on the write-policy audit for source edits. For plans it rests on the boundary text only: the `validate-run` forbidden-action scan (`validators/forbidden_actions.py::forbidden_patterns_for`) matches shell commands, so a plan written into a worker result or the report narrative is not detected.
|
|
@@ -31,17 +31,8 @@ def _has_discussion(state: WizardState) -> bool:
|
|
|
31
31
|
|
|
32
32
|
|
|
33
33
|
def _brief(state: WizardState) -> str:
|
|
34
|
-
"""새 task 는 방금 고른 brief, 기존 task 는 매니페스트에 등록된 brief.
|
|
35
|
-
|
|
36
|
-
토론 run 이 등록한 brief 는 prepare 가 만든 입력 문서라 후보가 아니다."""
|
|
37
|
-
if state.brief_path:
|
|
38
|
-
return state.brief_path
|
|
39
|
-
existing = state.existing_brief_path
|
|
40
|
-
if not existing:
|
|
41
|
-
return ""
|
|
42
|
-
generated = DiscussionStore(Path(state.project_root), _task_key(state)).input_path
|
|
43
|
-
resolved = Path(existing) if Path(existing).is_absolute() else Path(state.project_root) / existing
|
|
44
|
-
return "" if resolved.resolve() == generated.resolve() else existing
|
|
34
|
+
"""새 task 는 방금 고른 brief, 기존 task 는 매니페스트에 등록된 brief."""
|
|
35
|
+
return state.brief_path or state.existing_brief_path
|
|
45
36
|
|
|
46
37
|
|
|
47
38
|
def _accept(state: WizardState, value: str) -> str:
|
|
@@ -80,7 +80,7 @@ taskType: "{{FM_TASK_TYPE}}"
|
|
|
80
80
|
|
|
81
81
|
> Analysers MUST NOT expand the hypothesis space or evidence collection into items listed here. If an analyser believes an excluded item is causally linked to the symptom, it is reported as a recommended follow-up analysis task in the final report — never silently merged into the current root-cause narrative. If this section is left empty, analysers treat any cause beyond what `Symptom Summary` and `Reproduction Context` describe as out of scope by default.
|
|
82
82
|
|
|
83
|
-
**Enforced (delivery only):**
|
|
83
|
+
**Enforced (delivery only):** the retired Python suite pins that a filled section reaches every analysis worker through `okstra_ctl.analysis_packet` — drop it from `CANONICAL_BRIEF_SECTIONS` and every run's exclusions vanish silently. The exclusions themselves are prose and are **not** machine-checked: only the codebase-scan `out-of-scope` frontmatter is a path list, and `scripts/okstra_ctl/phases/improvement_discovery/validation.py` checks that one.
|
|
84
84
|
|
|
85
85
|
## Questions for Analysers
|
|
86
86
|
|
|
@@ -5,9 +5,9 @@
|
|
|
5
5
|
| ID | Guarantee | Enforcement |
|
|
6
6
|
|---|---|---|
|
|
7
7
|
| EA-1 | A blocked reproduction names its blocking reason; other statuses carry an empty reason | `scripts/okstra_ctl/phases/error_analysis/validation.py::_validate_reproduction` |
|
|
8
|
-
| EA-2 | Cause-chain links reference sibling candidates and reject self-links and cycles |
|
|
8
|
+
| EA-2 | Cause-chain links reference sibling candidates and reject self-links and cycles | unenforced |
|
|
9
9
|
| EA-3 | A selected destination agrees with the cause reference, verdict directions, and continuation row | `scripts/okstra_ctl/phases/error_analysis/validation.py::_validate_error_analysis_consistency` |
|
|
10
|
-
| EA-4 | Common routing destinations match both supported report schemas |
|
|
10
|
+
| EA-4 | Common routing destinations match both supported report schemas | unenforced |
|
|
11
11
|
|
|
12
12
|
## Index
|
|
13
13
|
|
|
@@ -19,4 +19,4 @@ This phase describes a confirmed feature's normal, alternate and failure flows,
|
|
|
19
19
|
| FA-1 | A feature-index target resolves to exactly one selected project-context feature; free text cannot be empty. | `scripts/okstra_ctl/phases/feature_analysis/entry.py::resolve_analysis_target` |
|
|
20
20
|
| FA-2 | Report target identity matches the resolved analysis target. | `scripts/okstra_ctl/phases/feature_analysis/validation.py::_validate_feature_semantics` |
|
|
21
21
|
| FA-3 | Current-code evidence remains within the declared analysis scope. | `validators/validate_analysis_report.py::_validate_all_current_code_evidence` |
|
|
22
|
-
| FA-4 | Feature target selection preserves the wizard's rendered arguments. |
|
|
22
|
+
| FA-4 | Feature target selection preserves the wizard's rendered arguments. | unenforced |
|
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
- **whole-task mutates only when it has to.** When one stage branch already contains every other done stage's commit — the usual shape of a linear plan, since each stage branches from its predecessor's done commit — that branch IS the whole task, and verification runs in that stage's worktree with no merge at all (`stage_targets.containing_stage`). Only when the stage graph has several tips does entry auto-merge (with `--no-ff`) the done stages into the task branch to create an integration commit; that case is the mutating one. The stage worktrees are NOT removed on entry: they are reclaimed after the verdict, by the Phase 7 `teardown-stages` step, and only when the verdict clears the work for release (`accepted`, or `conditional-accept` with no condition blocking release). A `blocked` verdict therefore leaves every stage worktree in place, so the rework it routes to can start immediately. The stage branches are kept as the reviewable stack (the target of `okstra handoff local-checkout --stage <N>`). If a merge conflict occurs it reports the conflicting files and aborts (the user resolves them manually and retries). A stage worktree with uncommitted changes remaining is preserved. Therefore the "fully-merged, clean target" the entry gate above refers to is the state after this auto-integration step completes, and whole-task final-verification must be treated as a mutating phase that creates the integration commit.
|
|
27
27
|
- **single-stage scope** (`--stage N`): prep verified stage N is `status:done` and its isolated stage worktree exists and is clean. Other stages' state is irrelevant. A single-stage run is a partial verification of one stage, and that is exactly the unit release-handoff ships: an `accepted` verdict here makes the stage PR-eligible, so `release-handoff` is the routing target. It says nothing about any other stage.
|
|
28
28
|
- the lead still captures `git status --short` from the injected worktree to confirm the analysis ran against the delivered work-tree state; an unexpected divergence (dirty tree outside `.okstra/`, missing worktree) is a `tool-failure`, not a silent proceed.
|
|
29
|
-
- **Stage worktree lifecycle:** implementation finalization may already have removed a completed stage's directory. Preparation restores the preserved stage branch for single-stage verification, or the containing tip branch for a linear whole-task target. After successful report validation, a release-ready single-stage verdict reclaims that stage's clean worktree; a whole-task verdict reclaims completed stages without any cleanup-time merge. Blocked, active, dirty, nested, or changed stages remain available for rework. The branch and registry base survive cleanup. After finalization use the main project root or absolute artifact paths because the verification cwd may have been removed. Enforcement: `report_finalize._teardown_stage_worktrees`, `stage_targets.teardown_completed_stage_worktrees`, and
|
|
29
|
+
- **Stage worktree lifecycle:** implementation finalization may already have removed a completed stage's directory. Preparation restores the preserved stage branch for single-stage verification, or the containing tip branch for a linear whole-task target. After successful report validation, a release-ready single-stage verdict reclaims that stage's clean worktree; a whole-task verdict reclaims completed stages without any cleanup-time merge. Blocked, active, dirty, nested, or changed stages remain available for rework. The branch and registry base survive cleanup. After finalization use the main project root or absolute artifact paths because the verification cwd may have been removed. Enforcement: `report_finalize._teardown_stage_worktrees`, `stage_targets.teardown_completed_stage_worktrees`, and the retired Python suite.
|
|
30
30
|
- Worker verification procedure:
|
|
31
31
|
- **Target confirmation:** analyse the injected target and nothing else. Read `verification-target.md` for the stage/report mapping and the complete diff stat. Prepare fixed that target and `phases/final_verification/validation.py` `validate_verification_target_match` (called by `validators/validate-run.py`) re-checks the report against its digest, so the procedure to follow here is simply: if the worktree you can see does not match the injected target, record a `tool-failure` — never reselect a target.
|
|
32
32
|
- **Evidence:** attach file:line, exact command + exit code, log excerpt, or MCP SELECT evidence to every finding. Mark a requirement as covered only when the cited artifact demonstrates it.
|
|
@@ -44,9 +44,9 @@
|
|
|
44
44
|
performs the core advisory classification/reduction;
|
|
45
45
|
`validators/validate-run.py` (`_validate_conformance`) routes that status to
|
|
46
46
|
warnings instead of failures; and
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
and
|
|
47
|
+
the retired Python suite (`test_external_non_pass_is_advisory`),
|
|
48
|
+
the retired Python suite (`test_external_non_pass_returns_warning_not_failure`),
|
|
49
|
+
and the retired Python suite (`test_external_qa_advisory_renders_without_downgrading_accepted_verdict`)
|
|
50
50
|
lock the core, gate, and accepted-report behavior respectively.
|
|
51
51
|
- **Manual user test:** read only the source implementation report's `implementation.manualUserTest`. Execute reproducible steps and record `pass`, `fail`, or `blocked` with observed evidence. Human-only or environment-unavailable steps remain `blocked` with the exact reason. Reaffirm an `applicable=false` exemption; do not execute planning `designPreparation` or manual-test PREP items directly.
|
|
52
52
|
- **Design-preparation carry-in:** read only source implementation report `missingInformation` rows whose `source` starts with `design-prep:`. Recommend `ifStillOpen: block` as an acceptance blocker and `ifStillOpen: follow-up` as residual risk. This phase does not read planning PREP sidecars directly or mutate planning snapshots.
|
|
@@ -85,7 +85,7 @@ taskType: "{{FM_TASK_TYPE}}"
|
|
|
85
85
|
|
|
86
86
|
> Verifiers MUST NOT extend acceptance checks, regression scans, or sign-off recommendations into items listed here. If a verifier believes an excluded item must pass before release, it is reported as a recommended follow-up verification task in the final report — never silently included in the pass/fail decision of this run. If this section is left empty, verifiers treat any check beyond what `Acceptance Criteria` enumerates as out of scope by default.
|
|
87
87
|
|
|
88
|
-
**Enforced (delivery only):**
|
|
88
|
+
**Enforced (delivery only):** the retired Python suite pins that a filled section reaches every analysis worker through `okstra_ctl.analysis_packet` — drop it from `CANONICAL_BRIEF_SECTIONS` and every run's exclusions vanish silently. The exclusions themselves are prose and are **not** machine-checked: only the codebase-scan `out-of-scope` frontmatter is a path list, and `scripts/okstra_ctl/phases/improvement_discovery/validation.py` checks that one.
|
|
89
89
|
|
|
90
90
|
## Config and Deployment Verification Targets
|
|
91
91
|
|
|
@@ -8,8 +8,8 @@ This directory is the canonical home of the final-verification phase. Report fie
|
|
|
8
8
|
|---|---|---|
|
|
9
9
|
| FV-1 | A report that does not match the prepared verification target is rejected | `scripts/okstra_ctl/phases/final_verification/validation.py::validate_verification_target_match` |
|
|
10
10
|
| FV-2 | A release-handoff route requires a release-ready verdict | `validators/validate-run.py::_refuse_unsuitable_final_verification_route` |
|
|
11
|
-
| FV-3 | The final-verification destination list matches the report schema |
|
|
12
|
-
| FV-4 | The phase profile is not also stored under prompts/profiles |
|
|
11
|
+
| FV-3 | The final-verification destination list matches the report schema | unenforced |
|
|
12
|
+
| FV-4 | The phase profile is not also stored under prompts/profiles | unenforced |
|
|
13
13
|
|
|
14
14
|
## Process
|
|
15
15
|
|
|
@@ -108,7 +108,7 @@ This is a worker guideline, not command-execution evidence or an execution-log
|
|
|
108
108
|
validator. The named `model-io verification-input` projection validates the run
|
|
109
109
|
and snapshot before exposing frozen declarations as quoted scalar rows.
|
|
110
110
|
`test_verification_input_projection_rejects_invalid_input_before_output` checks
|
|
111
|
-
the read boundary.
|
|
111
|
+
the read boundary. the retired Python suite
|
|
112
112
|
checks instruction/spec alignment. Existing read-only execution, target scope,
|
|
113
113
|
independent QA and outcome policies remain in force.
|
|
114
114
|
|
|
@@ -192,7 +192,7 @@ flowchart TD
|
|
|
192
192
|
|
|
193
193
|
The stage merge of whole-task mode is a runtime-owned integration step that prepare performs; the matching teardown is a runtime-owned step too, but it runs after the verdict (Phase 7 `teardown-stages`) and only when the verdict clears the work for release. After that, lead verification is read-only. Source edit, follow-up fix, and scope expansion are all forbidden. When a defect is found, it is not fixed within the current run. The lead chooses the next phase from `prompts/lead/phase-routing.md` using the blocker facts this phase recorded.
|
|
194
194
|
|
|
195
|
-
Implementation finalization may already have reclaimed completed stage worktrees. Target acquisition restores a missing single-stage worktree, or the containing tip-stage worktree for a linear whole-task target, from its preserved branch. Restoration does not merge into the task branch. After a release-ready single-stage verdict, `report-finalize` also reclaims that stage's worktree using the captured verification head; a blocked verdict keeps the restored worktree for rework. Cleanup never merges stages: `stage_targets.teardown_completed_stage_worktrees` only reclaims completed, inactive worktrees whose tips match the selected completion commits. Tests:
|
|
195
|
+
Implementation finalization may already have reclaimed completed stage worktrees. Target acquisition restores a missing single-stage worktree, or the containing tip-stage worktree for a linear whole-task target, from its preserved branch. Restoration does not merge into the task branch. After a release-ready single-stage verdict, `report-finalize` also reclaims that stage's worktree using the captured verification head; a blocked verdict keeps the restored worktree for rework. Cleanup never merges stages: `stage_targets.teardown_completed_stage_worktrees` only reclaims completed, inactive worktrees whose tips match the selected completion commits. Tests: the retired Python suite.
|
|
196
196
|
|
|
197
197
|
### 8. Verified code
|
|
198
198
|
|
|
@@ -34,7 +34,7 @@ When the user picks a waiver, append `--qa-waiver "<stageKey>:<reason>"` to the
|
|
|
34
34
|
If `render-bundle` stdout carries an `okstra concurrent-run stages: <stages>` label line (another implementation run on the same task-key is occupying `<stages>`), the launch prompt has already been rendered with the "Concurrent-run marker" gate. If this line is absent it is not a concurrent run, so skip this branch. If present, before dispatch present a 3-option recommendation picker to the user (run-prompt recommendation rule: 1–2 recommendations + Enter directly; this picker is authored by the skill, so it is unconstrained by the wizard `options[]` rule):
|
|
35
35
|
|
|
36
36
|
1. (recommended) Proceed as-is — use the already-rendered bundle. Each session uses its own implicit team, so concurrent runs have no team conflict and split-pane works fine.
|
|
37
|
-
2. Wait — hold the dispatch for now. The stage worktree·run-context are preserved, so after the other occupying run finishes, resuming the same stage takes the normal team path.
|
|
37
|
+
2. Wait — hold the dispatch for now. The stage worktree·run-context are preserved, so after the other occupying run finishes, resuming the same stage takes the normal team path. Tell the user to resume the same stage with `okstra-run` after the other run finishes.
|
|
38
38
|
3. Enter directly.
|
|
39
39
|
|
|
40
40
|
### Stale git SHA recovery (git-reconcile gate)
|
package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-deliverable.md
CHANGED
|
@@ -33,7 +33,7 @@ are collected and convergence finished. Phase 1-5 do not need it.
|
|
|
33
33
|
- **Pure code changes** (no persisted state, no infra mutation): a reachable revert SHA is sufficient. Record the exact `git revert <SHA>` command that would undo the change, and confirm `git rev-parse <SHA>` resolves.
|
|
34
34
|
- **Feature-flag-gated changes**: prefer confirming the off-switch path was exercised in this run's validation evidence (i.e. one of the validation commands ran with the flag off and succeeded). If the off-path was not exercised here, record the row as `advisory — human-run` rather than treating it as a blocking requirement.
|
|
35
35
|
- **Schema migrations, config-format changes, or any change with persisted state**: record the exact rollback command and, when the migration tool offers a dry-run mode (`--dry-run`, `--plan`, equivalent), its captured exit code / stdout. The rollback itself is a **human-run operation**, not an okstra worker or verifier step — so an unavailable dry-run is documented as such (advisory) and does NOT block the run, does NOT produce a `contract-violated` outcome, and does NOT route back to `implementation-planning`. The deliverable here is recording the revert path clearly enough that a human can act on it.
|
|
36
|
-
- **Manual user test draft**: when this run produces a user-observable change (UI / API / CLI / artifact), write `target / environment / steps / expected result` per change into §5.7.9 (data field `implementation.manualUserTest`, `applicable=true` with `items`). Treat effective `manual-user-test` PREP content only as a seed: reconcile it with the approved plan's `Acceptance:` and this run's actual diff before writing the final steps. Environment line:
|
|
36
|
+
- **Manual user test draft**: when this run produces a user-observable change (UI / API / CLI / artifact), write `target / environment / steps / expected result` per change into §5.7.9 (data field `implementation.manualUserTest`, `applicable=true` with `items`). Treat effective `manual-user-test` PREP content only as a seed: reconcile it with the approved plan's `Acceptance:` and this run's actual diff before writing the final steps. Environment line: use the project's documented run command (e.g. `npm start`). When there is no user-observable change, set `applicable=false` and give a one-line `exemptionReason` instead of items. These are the steps a human (or `final-verification`) re-runs by hand, NOT the automated validation commands in `Validation evidence`; planning PREP is never a second final-verification manual-test source.
|
|
37
37
|
- **Design preparation handoff**: `implementation.manualUserTest` remains the only manual-test handoff to final-verification. For each effective non-`manual-user-test` item whose `reviewAt.phase` is `final-verification` and whose question remains unresolved after inspecting the actual diff, add one common `missingInformation` row. Set `source` to `design-prep:<PREP-ID>:<assessment-fingerprint>`, put `ifStillOpen` and the unresolved question in `item`, and put the guardrails plus risk in `risk`. Do not introduce an implementation-only PREP schema.
|
|
38
38
|
- **External QA advisory handoff:** for every external Tier 3 result that did
|
|
39
39
|
not PASS, preserve the exact command and observed result in validation
|
|
@@ -118,7 +118,7 @@ Changing a test's expected value is allowed here when the finding shows the orac
|
|
|
118
118
|
- **A run that ends with no verifier result still closes.** When the stage ends before any verifier returned a verdict — the executor stopped without a change and the user chose not to verify, or every dispatched verifier ended without a result — append the `failed` row as above, record each roster verifier `not-run` with its reason (`okstra worker-state transition --team-state <path> --worker <worker-id> --status not-run --reason <text>`; a worker the dispatch skipped already carries one), and write the convergence state with `okstra convergence skip --run-manifest <path> --reason <text>` before dispatching the report writer. Without that state the report-writer packet refuses with `convergence … required source is missing`. The command refuses while any analyser, verifier, or critic attempt returned a result or is still running; such a run converges normally. In the report, write each verifier's `verifierResults[]` row as `verdict: not-run`, and state the reason under `Stage sidecar evidence` as `withheld`.
|
|
119
119
|
- On a non-`FAIL` verdict, for this run's single stage: save the executor's `### Stage Carry Evidence` JSON (after a passing lead minor fix, with the head, files, and note that §"Lead minor fix" adds; after a correction round, the last round's executor block) to a file under this run's `state/`, then run `okstra stage-done <impl-task-key> --stage <N> --carry <that file> --report <this run's final-report path>`. It writes the sidecar to the flat `runs/implementation/carry/stage-<N>.json` (the readers glob `carry/stage-*.json`: `okstra_ctl.stage_map`, `okstra_ctl.consumers.backfill_done_from_carry`, and validate-run's `RunRef.carry`), refuses to replace another head's sidecar of a stage that was never settled, and for a stage reopened after a `done` row (see "Reopening a settled stage" below) moves the previous sidecar unchanged to `carry/superseded/stage-<N>-from-<task-type>-<seq>.json` first. Name the `carryPath` and any `supersededCarryPath` it prints in `Stage sidecar evidence`. A reopened stage whose run ends `FAIL` writes nothing and leaves the old file where it is.
|
|
120
120
|
- The same `okstra stage-done` call appends the `status:"done"` row to `runs/<plan-task-key>/consumers.jsonl` with `completed_at`, `carry_path`, `report_path` (relative to the report's run directory) and the carry's head, through `append_consumer` — so the consumers lock applies and this stage's worktree-registry occupancy is released. Never call `append_consumer` from python. `report_path` lets `final-verification` cite each stage's originating report when assembling its Source Implementation Report list.
|
|
121
|
-
- **Automatic stage worktree cleanup:** after the report passes finalization, `report-finalize` reclaims this completed stage's clean worktree. It compares the report's final commit with the completion ledger and branch tip, preserves active or unfinished stages and dirty or nested worktrees, and keeps the branch and registry base for dependency rebases and later re-entry. Never remove the directory by hand before finalization. A later implementation or final-verification entry restores it from the preserved branch. After finalization, use the main project root or absolute artifact paths: this run's stage cwd may no longer exist. Enforcement: `report_finalize._teardown_stage_worktrees`, `stage_targets.teardown_completed_stage_worktrees`, and the cleanup/restoration tests in
|
|
121
|
+
- **Automatic stage worktree cleanup:** after the report passes finalization, `report-finalize` reclaims this completed stage's clean worktree. It compares the report's final commit with the completion ledger and branch tip, preserves active or unfinished stages and dirty or nested worktrees, and keeps the branch and registry base for dependency rebases and later re-entry. Never remove the directory by hand before finalization. A later implementation or final-verification entry restores it from the preserved branch. After finalization, use the main project root or absolute artifact paths: this run's stage cwd may no longer exist. Enforcement: `report_finalize._teardown_stage_worktrees`, `stage_targets.teardown_completed_stage_worktrees`, and the cleanup/restoration tests in the retired Python suite.
|
|
122
122
|
- **Reopening a settled stage.** Appending a `status:"failed"` row after a `done` one withdraws that stage: `--stage N` accepts it again, its dependents stop resolving a base from the withdrawn head, and whole-task final-verification blocks until it is settled again. Write it with `okstra stage-reopen <task-key> --stage <N> --reason "<why>" [--evidence <report>]`, which records the reason and the report that found the defect, and re-run the stage rather than repairing the tree outside okstra — a stage reverted outside the ledger leaves the recorded `head_commit` and the carry sidecar naming a tree that no longer exists, and the next stage branches from it.
|
|
123
123
|
- The verifier round, Phase 5.5 convergence, and this Phase 6 report run **once per run** over this stage's diff — NOT per step.
|
|
124
124
|
- Record this stage's new contents in the final report's `Stage sidecar evidence` deliverable section: the sidecar by path with its one-line summary, and the new consumers row quoted by itself.
|
package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-executor.md
CHANGED
|
@@ -11,7 +11,7 @@ until Phase 5 ends, then drop from active context for Phase 6/7.
|
|
|
11
11
|
|
|
12
12
|
Follow the `**Verification inputs:**` declaration-source rule when that header is present. References to project `qaCommands` in this sidecar mean the baseline selected by that rule. The legacy lookup uses the existing plan and project baseline only where no frozen declaration replaces them.
|
|
13
13
|
|
|
14
|
-
- **Moving dependency bases:** never run `git merge <predecessor>` or merge an old origin branch into this stage to update its base. Runtime preparation rebases downstream stages in dependency order through `okstra_ctl.stage_rebase`; a predecessor moving during execution requires stopping and re-entering preparation after the current stage claim is released. Do not rewrite another active stage or repair registry/ledger SHAs by hand. Enforcement of preparation ordering and conflict recovery is covered by
|
|
14
|
+
- **Moving dependency bases:** never run `git merge <predecessor>` or merge an old origin branch into this stage to update its base. Runtime preparation rebases downstream stages in dependency order through `okstra_ctl.stage_rebase`; a predecessor moving during execution requires stopping and re-entering preparation after the current stage claim is released. Do not rewrite another active stage or repair registry/ledger SHAs by hand. Enforcement of preparation ordering and conflict recovery is covered by the former Python suite; that regression check is now retired.
|
|
15
15
|
- The `Executor` (bound in `implementation.md` thin core) is the **only worker permitted to mutate project files**. All other workers run read-only. A `runner=native-session` executor uses the selected host adapter's native edit and command primitives. A `runner=cli-wrapper` executor mutates files inside its provider CLI's auto-edit mode. The safety rules in this sidecar apply identically to both runners.
|
|
16
16
|
- When the thin core's Task worktree block resolves status to `created` or `reused`, the Executor MUST run every Edit / Write / build / test / commit command with the worktree path as cwd. Treat it as `project_root` for the duration of this run. Do NOT mutate the caller's original checkout. Do NOT `cd` out of the worktree to reach files. If a file outside the worktree is genuinely needed, treat it as a planning gap: record it in `Out-of-plan edits` and continue.
|
|
17
17
|
- **How to set the working directory**: every command and native edit MUST target `{{EXECUTOR_WORKTREE_PATH}}`, never the lead session's original project directory. The selected runtime adapter owns the exact native command syntax. Provider CLI wrappers inject the worktree at the CLI layer. For tools that accept an explicit working-directory flag (`git -C <path>`, `cargo --manifest-path`, `pytest --rootdir`), prefer that form.
|
package/runtime/python/okstra_ctl/phases/implementation/instructions/_implementation-verifier.md
CHANGED
|
@@ -58,7 +58,7 @@ Launch every Tier 1 command through the worktree lock:
|
|
|
58
58
|
okstra worktree-lock --worktree <target.cwd> --command '<target.command>'
|
|
59
59
|
```
|
|
60
60
|
|
|
61
|
-
The verifiers of a stage share one worktree and run at the same time, and each re-runs every Tier 1 command. A Tier 1 command that starts servers on fixed ports (a dev server on 3000 plus a fixture API on 8899 behind one `playwright test` line, fontsninja-v3-site dev-11126 stage 1) collides with the same command from another verifier: each kills or attaches to the other's servers, and the exit codes stop describing the code. The lock is keyed by the worktree, so each verifier still runs the command itself, only one at a time. The wrapper is the launcher, not the command: record the declared `target.command` as the command line, and the wrapper's exit code and stdout/stderr tail as that command's — the wrapper passes both through unchanged and adds only stderr lines prefixed `okstra worktree-lock:`. A `waiting` notice means another verifier held the lock; a `running unlocked` warning means the lock file could not be created, so record that warning beside the result. This is a guideline: nothing checks the command log for the launcher. The lock behaviour (no overlap on one worktree, no blocking across worktrees, output and exit-code pass-through, lock file outside the worktree) is covered by
|
|
61
|
+
The verifiers of a stage share one worktree and run at the same time, and each re-runs every Tier 1 command. A Tier 1 command that starts servers on fixed ports (a dev server on 3000 plus a fixture API on 8899 behind one `playwright test` line, fontsninja-v3-site dev-11126 stage 1) collides with the same command from another verifier: each kills or attaches to the other's servers, and the exit codes stop describing the code. The lock is keyed by the worktree, so each verifier still runs the command itself, only one at a time. The wrapper is the launcher, not the command: record the declared `target.command` as the command line, and the wrapper's exit code and stdout/stderr tail as that command's — the wrapper passes both through unchanged and adds only stderr lines prefixed `okstra worktree-lock:`. A `waiting` notice means another verifier held the lock; a `running unlocked` warning means the lock file could not be created, so record that warning beside the result. This is a guideline: nothing checks the command log for the launcher. The lock behaviour (no overlap on one worktree, no blocking across worktrees, output and exit-code pass-through, lock file outside the worktree) is covered by the former Python suite; that regression check is now retired.
|
|
62
62
|
|
|
63
63
|
### Stage QA owner
|
|
64
64
|
|
|
@@ -85,9 +85,9 @@ Enforcement: `scripts/okstra_ctl/conformance.py` (`decide_conformance_gate`)
|
|
|
85
85
|
performs the core advisory classification/reduction;
|
|
86
86
|
`validators/validate-run.py` (`_validate_conformance`) routes that status to
|
|
87
87
|
warnings instead of failures; and
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
and
|
|
88
|
+
the retired Python suite (`test_external_non_pass_is_advisory`),
|
|
89
|
+
the retired Python suite (`test_external_non_pass_returns_warning_not_failure`),
|
|
90
|
+
and the retired Python suite (`test_external_qa_advisory_renders_without_downgrading_accepted_verdict`)
|
|
91
91
|
lock the core, gate, and accepted-report behavior respectively.
|
|
92
92
|
|
|
93
93
|
An `io`-only non-PASS remains BLOCKING. Manifest/schema/source-mutation defects
|
|
@@ -52,7 +52,7 @@ taskType: "{{FM_TASK_TYPE}}"
|
|
|
52
52
|
|
|
53
53
|
> The executor MUST NOT modify items listed here, even when an edit looks "trivial" or "while I'm in this file". Excluded items that block plan execution are reported back as a recommended follow-up task and the run halts for re-planning rather than silently expanding scope. This section is enforced together with `Forbidden In This Run` below.
|
|
54
54
|
|
|
55
|
-
**Enforced (delivery only):**
|
|
55
|
+
**Enforced (delivery only):** the retired Python suite pins that a filled section reaches every analysis worker through `okstra_ctl.analysis_packet` — drop it from `CANONICAL_BRIEF_SECTIONS` and every run's exclusions vanish silently. The exclusions themselves are prose and are **not** machine-checked: only the codebase-scan `out-of-scope` frontmatter is a path list, and `scripts/okstra_ctl/phases/improvement_discovery/validation.py` checks that one.
|
|
56
56
|
|
|
57
57
|
**Enforced (declared edits only):** `_validate_out_of_plan_edits_are_real` in `validators/validate-run.py` fails an `Out-of-plan edits` row naming a file that is absent from `diffSummary`. The other direction — a file changed outside the approved plan and never declared — needs the plan's own file list resolved through `approvedPlanReference.planFile`, and is not built.
|
|
58
58
|
|
|
@@ -140,7 +140,7 @@ frozen scalar fields. Quoted strings preserve command and procedure characters.
|
|
|
140
140
|
the read boundary. Snapshot references
|
|
141
141
|
are not command-execution evidence; stage scope, checklist timing and independent
|
|
142
142
|
QA ownership remain in force. This is a worker guideline, not an execution-log
|
|
143
|
-
validator.
|
|
143
|
+
validator. the retired Python suite
|
|
144
144
|
checks instruction/spec alignment, and the header and recovery tests cover the
|
|
145
145
|
generated reference contract.
|
|
146
146
|
|
|
@@ -186,9 +186,9 @@ Stage selection is `auto` or a number. If `--stage` comes from another task-type
|
|
|
186
186
|
|
|
187
187
|
The stage worktree base is decided by dependency shape. An independent stage uses the task-key worktree HEAD fixed at first implementation entry as its anchor, and a single-dependency stage branches from the predecessor stage's done `head_commit`. A multi-dependency stage branches from a commit holding exactly its predecessors: the predecessor commit that already contains the others, or else an integration branch merging them (`<work-category-namespace>/<task-id-segment>-g<n1>-<n2>`). okstra creates that branch itself, so a predecessor that has not been merged into the task branch no longer blocks the stage; release-handoff later reuses the same branch as that stage's PR base.
|
|
188
188
|
|
|
189
|
-
When a predecessor advances, implementation entry synchronizes existing completed stage branches in dependency order through `okstra_ctl.stage_rebase.synchronize_stage_stack`. Each downstream stage is rebased with `git rebase --onto <new-base> <recorded-old-base>`; merging a moving predecessor into that stage is not an update strategy. Re-entering an unfinished stage also rebases its existing worktree when the computed base changes. Old heads are preserved under `refs/okstra/rebase-backups/`, registry bases and completion records are updated, and previous verification no longer qualifies. Conflicts abort the current rebase and stop the chain; active runs and dirty worktrees are not rewritten. A completed stage whose predecessor was reopened, and so has no done row, is left unchanged; the first synchronization after that predecessor is done again rebases it. Tests:
|
|
189
|
+
When a predecessor advances, implementation entry synchronizes existing completed stage branches in dependency order through `okstra_ctl.stage_rebase.synchronize_stage_stack`. Each downstream stage is rebased with `git rebase --onto <new-base> <recorded-old-base>`; merging a moving predecessor into that stage is not an update strategy. Re-entering an unfinished stage also rebases its existing worktree when the computed base changes. Old heads are preserved under `refs/okstra/rebase-backups/`, registry bases and completion records are updated, and previous verification no longer qualifies. Conflicts abort the current rebase and stop the chain; active runs and dirty worktrees are not rewritten. A completed stage whose predecessor was reopened, and so has no done row, is left unchanged; the first synchronization after that predecessor is done again rebases it. Tests: the retired Python suite.
|
|
190
190
|
|
|
191
|
-
Successful implementation report finalization automatically removes that stage's clean worktree after its `done` record is persisted. The report's last commit, the completion ledger, and the current branch tip must agree for cleanup (`stage_integrate.reclaim_completed_stage`). Failed, active, dirty, nested, or moved stages are preserved with a reason in the finalization step result. Cleanup retains the branch and registry base; implementation re-entry and final-verification restore the worktree from that branch. The task worktree and other stages are outside this scoped cleanup. Tests:
|
|
191
|
+
Successful implementation report finalization automatically removes that stage's clean worktree after its `done` record is persisted. The report's last commit, the completion ledger, and the current branch tip must agree for cleanup (`stage_integrate.reclaim_completed_stage`). Failed, active, dirty, nested, or moved stages are preserved with a reason in the finalization step result. Cleanup retains the branch and registry base; implementation re-entry and final-verification restore the worktree from that branch. The task worktree and other stages are outside this scoped cleanup. Tests: the retired Python suite and the retired Python suite.
|
|
192
192
|
|
|
193
193
|
## 6. Deliverables
|
|
194
194
|
|
|
@@ -255,4 +255,4 @@ This phase does not declare final acceptance. It says only ready for final-verif
|
|
|
255
255
|
|---|---|---|
|
|
256
256
|
| I-1 | An empty independent rerun record fails validation. | `scripts/okstra_ctl/phases/implementation/validation.py::_validate_verifier_reran_independently` |
|
|
257
257
|
| I-2 | A verifier cannot report a discrepancy with a PASS verdict. | `scripts/okstra_ctl/phases/implementation/validation.py::_validate_verifier_discrepancy_is_not_passed` |
|
|
258
|
-
| I-3 | Frozen legacy instruction pointers resolve within the selected installation without rewriting the frozen profile. |
|
|
258
|
+
| I-3 | Frozen legacy instruction pointers resolve within the selected installation without rewriting the frozen profile. | unenforced |
|
|
@@ -8,8 +8,8 @@ This directory owns candidate evaluation, vote completion, comparison projection
|
|
|
8
8
|
|---|---|---|
|
|
9
9
|
| IOS-1 | Candidate scores, coverage, votes and ranking are recomputed | `scripts/okstra_ctl/phases/implementation_option_selection/validation.py::validate_implementation_option_selection` |
|
|
10
10
|
| IOS-2 | Blocked facts retain their user decision or technical evidence channel | `scripts/okstra_ctl/phases/implementation_option_selection/validation.py::validate_blocked_answer_channel` |
|
|
11
|
-
| IOS-3 | A valid candidate needs two `feasible` votes, or the single vote when the user selected one designer | `scripts/okstra_ctl/phases/implementation_option_selection/validation.py::required_feasible_votes
|
|
12
|
-
| IOS-4 | Candidate fingerprints deduplicate equivalent mechanisms |
|
|
11
|
+
| IOS-3 | A valid candidate needs two `feasible` votes, or the single vote when the user selected one designer | `scripts/okstra_ctl/phases/implementation_option_selection/validation.py::required_feasible_votes` |
|
|
12
|
+
| IOS-4 | Candidate fingerprints deduplicate equivalent mechanisms | unenforced |
|
|
13
13
|
|
|
14
14
|
Report schemas remain in `schemas/final-report-v2.0.schema.json` and `schemas/final-report-v3.0.schema.json`, under `implementationOptionSelection`. Next-phase decisions belong to `prompts/lead/phase-routing.md`.
|
|
15
15
|
|