Why: The backend branch gained the user-scope model capture fix, and the
live eval produced the before-baseline report on remote main (1ebd46e) that
the task card and the improvement-plan record reference as evidence.
Evidence: SELF - report .task/phase01-eval/before-main-1ebd46e.json (model
MiniMax-M2.7-highspeed, 4 golden tasks, 17 min run): reproduces the diagnosed
failure chain on the pre-fix build - readability dead-loop x4 on two tasks,
9 full regens with 0 original-material reads in plan-followup, 8 unverified
percentages, forged-marker false positive, internal check text leaked to the
user.
Impact: Report committed for the after-comparison once this PR merges; gitlink
points at the harness-inclusive backend head.
Why: The lint skills-root injection moved from the app root to the runner,
keeping the architecture ratchet green; the Dev combination must test that head.
Evidence: SELF - gitlink equals backend feature/agent-quality-phase01 head;
make test rerun recorded on the task card.
Impact: Pointer only.
Why: The previous pointer predated the eval/live package commit; the
combination must test the full phase01 backend branch.
Evidence: SELF - gitlink equals backend feature/agent-quality-phase01 head.
Impact: Pointer only.
Why: Backend carries the seven quality-gate repairs with the eval/live
harness; documents carries the improvement-plan main record with the six user
rulings. The Dev combination must test these heads together.
Evidence: SELF - gitlink pointers match the pushed branch heads; make test
recorded on the task card after this commit.
Impact: Combined test surface now includes the phase01 backend and documents
content; no behavior change from the pointers alone.
Refs: feature/agent-quality-phase01 (backend), feature/agent-quality-plan (documents).
Why: The 2026-10-09 diagnosis showed behavior-surface regressions (gate
deadlocks, silently broken lint, wrong artifact verdicts) passing every unit
test because no task-level check ran the real model. User ruling 6 approved
making before/after live-eval evidence a delivery requirement for prompt,
skill, tool-description, context-assembly and gate changes.
Evidence: SELF - clause drafted to reference modules/backend/eval/live and the
GATE/REPLAY/SELF sourcing already defined in AGENTS.md; task card for
feature/agent-quality-phase01 filled with the P0+P1 scope and requirements.
Impact: policy/delivery.md gains the 智能体行为面的真实验证 subsection;
NOT_RUN stays legal but must be explicit. Phase01 task card records scope,
requirements R1-R4 and the before/after eval protocol.
Refs: modules/documents proposal 2026-10-09-agent-quality-improvement-plan.md (ruling 6).
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-agent-quality-phase01.md; R0=1ebd46edc5239d0d87418e9a8dd9aa225955e1dd.
Impact: task metadata only; the feature workspace starts at 1ebd46edc5.
Refs: .task/feature-agent-quality-phase01.md
Why: v0.2.0 must carry the DOCX tracked-change fix and the exec hard
switch (Backend #110) and the release record (Documents #50); RDM shared
work is blocked until v0.2.0 is tagged.
Evidence: SELF - make test exits 0 on this tree; Backend #110 CI success
on the merge commit; the composite CI on this PR is the GATE source.
Impact: modules/backend 92ede3b -> f1c9cc0, modules/documents 9995552 ->
d3c9b45. core/frontend/ui pins unchanged (a253a40/84b73ab/76d6633).
Refs: Backend #110; Documents #50; docs/records/2026-10-09-base-v0.2.0-release.md
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-base-v020-release.md; R0=007247f1e7a423fe900f6ab1638b51369e4e7497.
Impact: task metadata only; the feature workspace starts at 007247f1e7.
Refs: .task/feature-base-v020-release.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-ext8-remaining-shared-reads.md(PR#273) — merges verified via git log --merges against origin/main.
Impact: .task/*.md moved to .task/archive/ with status backfilled; no code or submodule change.
Refs: task.sh close (card-autoclose-r1)
Why: CI on PR HEAD is the authoritative gate before merge.
Evidence: Backend#109 success; Dev#273 success.
Impact: Task card only.
Refs: AGENTS.md evidence gate.
Why: The Dev combination must pin the closure commit; make test validates the fixed combination.
Evidence: modules/backend -> 92ede3b970dd8bc0a40b3359a04a6e35b812a9d1 (Backend PR #109).
Impact: Gitlink only.
Refs: Backend PR #109; task card.
Why: EXT-8 closure needs vector-channel sharing, the hostapi face, and citation-ref consistency; scope and non-goals (no base graph endpoint exists - RDM trace net is downstream) must be recorded first.
Evidence: rag Retrieve/rrfMerge and hostapi search shapes verified at source.
Impact: Task card only.
Refs: EXT-8 proposal; slice-1/2 cards.
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-ext8-remaining-shared-reads.md; R0=28a4dbcbf4d61d44b1e0300993962da419e98666.
Impact: task metadata only; the feature workspace starts at 28a4dbcbf4.
Refs: .task/feature-ext8-remaining-shared-reads.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-ext-11-scoped-host-factory.md(PR#271) — merges verified via git log --merges against origin/main.
Impact: .task/*.md moved to .task/archive/ with status backfilled; no code or submodule change.
Refs: task.sh close (card-autoclose-r1)
Why: CI on PR HEAD is the authoritative gate before merge.
Evidence: Backend#108 success; Dev#271 success.
Impact: Task card only.
Refs: AGENTS.md evidence gate.
Why: The Dev combination must pin the EXT-11 commit; make test validates the fixed combination.
Evidence: modules/backend -> bbe39b475fc79d4e1fbf211d3d6d55dcad9fac4a (Backend PR #108).
Impact: Gitlink only.
Refs: Backend PR #108; task card.
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-ext-11-scoped-host-factory.md; R0=c637d9516d93ab5674bac38e58238e2453c5ce87.
Impact: task metadata only; the feature workspace starts at c637d9516d.
Refs: .task/feature-ext-11-scoped-host-factory.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-ext8-slice2-shared-retrieval.md(PR#269) — merges verified via git log --merges against origin/main.
Impact: .task/*.md moved to .task/archive/ with status backfilled; no code or submodule change.
Refs: task.sh close (card-autoclose-r1)
Why: CI on PR HEAD is the authoritative gate before merge.
Evidence: Backend#107 success; Dev#269 success.
Impact: Task card only.
Refs: AGENTS.md evidence gate.
Why: The Dev combination must pin the slice-2 commit; make test validates the fixed combination.
Evidence: modules/backend -> 1de663a8d3302eddbd35d8a1906e4234e17c28e8 (Backend PR #107).
Impact: Gitlink only.
Refs: Backend PR #107; task card.
weichen