Why: U5 injects the S3-compatible blobstore from the app composition root (env-driven, local fallback) - a legitimate dependency recorded in the baseline.
Evidence: lint-boundaries green after the update.
Impact: baseline bookkeeping only.
Refs: backend PR #157.
Why: backend PR #143 added surfacesvc with app/server/store edges already merged into component main; the Dev baseline must record them (lint failed after task-sync). runmgr->cmdbus no longer exists in code.
Evidence: lint-boundaries.sh green after the update; edges match the merged backend main exactly.
Impact: baseline bookkeeping only; no dependency change made by this task.
Refs: backend PR #143; Dev U4 task.
Why: Backend #114 (EXT-14, commands-as-tools) added the runmgr -> cmdbus
production import but its Dev-side ratchet update went missing, so make test
fails on any Dev head combining it (backend CI does not run the Dev
architecture check). Recorded here with the merge that surfaces it.
Evidence: SELF - lint-boundaries passes after the entry; the edge exists in
backend main (internal/runmgr/runmgr.go imports cmdbus).
Impact: Ratchet baseline only; unblocks the Dev combination for all in-flight
work.
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: Q3 WP1/WP2 moved workflow execution out of runtime (workflow_script.go
deleted, so runtime no longer imports internal/tools) into the new
internal/wfcompile package, which legitimately depends on internal/tools
(script host) and internal/workflow (render/validate/Launch data layer).
Evidence: make test-boundaries green after the baseline update (77 edges,
negative test ok); the lint itself flagged both the stale edge and the new
ones (SELF).
Impact: baseline -1 edge (backend/runtime backend/tools), +3 edges
(backend/runtime backend/wfcompile, backend/wfcompile backend/tools,
backend/wfcompile backend/workflow).
Refs: Q3 plan WP1/WP2; task card .task/feature-agent-stack-q3.md
Why: include the current integration baseline before verification.
Evidence: fetched origin/main=eb0d4b5a499322a23155c8d89a024247f6e7830d.
Impact: integrate upstream changes without rewriting task history.
Refs: task-sync
Why: Backend#89 merged the plugin/bundled skill validation; Native#28
and Squad#32 carried the validator; Dev pins, the plugins→skills edge,
and the increment record follow.
Evidence: check-pins pins ok; WP4 chain CI green on every merge head;
TestV2InvalidSkillRejected GATE on backend main b44f78b0.
Impact: skills now validated against the open Agent Skills spec.
Refs: Agent-Native#28, Agent-Squad#32, Agent-System-Backend#89
Why: include the current integration baseline before verification.
Evidence: fetched origin/main=878e0e7ceba3bb6b78c36c5113eacc846a7f017b.
Impact: integrate upstream changes without rewriting task history.
Refs: task-sync
Why: backend #83 merged the slow-lane wiring (intentsem scorer/
generator, gate SetSemantic/SetGenerator, settings flags default off);
the Dev pins and boundary rules must move with it.
Evidence: backend CI green on 9d29371; check-pins consistent
(agent-intent 343b1e6 across Dev and the backend nested copy);
lint-boundaries registers intentsem as an agent-intent adapter and the
architecture baseline gains backend/app->backend/intentsem.
Impact: product behavior unchanged by default; the two
runtime.intent* flags opt into the slow lane.
Refs: Agent-System-Backend#83, I2 increment 3
Why: The dependency ratchet blocks new edges by default; the unique
router's four edges (route->intentgate, runmgr->intentgate,
runmgr->route, server->route) are the I1 router's intended shape.
Evidence: lint-architecture.sh ok (73 edges) and negative probe ok.
Impact: Policy baseline only.
Why: preserve project direction across tasks and require grounded next-task recommendations.
Evidence: the generated task-card regression fails before the template update and passes afterward; original SELF receipts are in the task card.
Impact: document the planning entrypoint and extend task records without granting new-task execution rights.
Refs: .task/feature-goal-continuity.md; policy/delivery.md
Why: completion claims require tool-written evidence (AGENTS.md).
Evidence: SELF receipt appended by make evidence; full suite green incl. ui 103 tests and agent-command.
Impact: task metadata only.
Refs: .task/feature-ext-5-host-parse.md
Why: independent review found shared submodule metadata risk, quoted header leakage, stale JSON receipt blindness and missing abandon coverage.
Evidence: SELF 92 governance regressions pass; the original review receipt and replay output are recorded in the task card.
Impact: preserves external component worktrees, handles both evidence formats and adds targeted failure-path coverage; no product behavior changes.
Refs: .task/feature-governance-reliability.md; .task/reviews/governance-reliability.json
Why: cleanup, component synchronization, receipt recording and credential handling could contradict the documented development boundaries.
Evidence: SELF 75 isolated governance tests and source checks are captured in .task/feature-governance-reliability.md; combination and CI verification follow.
Impact: hardens local task and CI tooling, aligns policy and component documentation, and adds continuous regression tests without changing product behavior.
Refs: .task/feature-governance-reliability.md; policy/governance.md; policy/platform-admission.md
Why: facts-verify failed closed on first run — the real token file stores keys
as markdown bullets ("- ACCESS_TOKEN=..."), so the ^-anchored sed match in the
registry never fired; the earlier manual probe had used grep (anywhere-in-line)
and passed, which is exactly the drift the registry re-verification exists to
surface.
Evidence: re-run recorded in the task card — [facts-verify] total=4 pass=4
fail=0 (sha256 919401b838d77909), after fixing the sed pattern to
"^[ -]*ACCESS_TOKEN=".
Impact: policy/facts.md F2 command now matches the actual file shape and the
fact text documents the file format; no behavior change elsewhere.
Refs: task card evidence table (failed run sha256 6c61e644395042fa, then pass).
Why: declarations were passing as capability; hand-transcribed outputs flowed
through cards and PR bodies as if they were execution evidence, and stale
external facts (e.g. the dead git-panel host) kept being trusted until burned.
Evidence: guidelines draft.10 (PR Development-Guidelines#4, merged af199ee)
pinned here; policy/facts.md F1-F4 each re-verified on 2026-10-05 before
registration (endpoint version, token HTTP 200 via header only, SSH ls-remote,
dead-host negative probe); scripts syntax-checked (bash -n); tool self-tests
and make test recorded in the task card via the new make evidence.
Impact: new AGENTS.md section (SELF/REPLAY/GATE, tool-written evidence,
replay-on-review, zero-trust facts, honest-empty); make evidence/facts-verify;
precheck gains [hooks]/[facts], task-sync gains stale-evidence-HEAD warning;
task-start cards now embed the evidence table; gitlink advances to draft.10.
Refs: task card .task/feature-evidence-driven-gates.md; guidelines CHANGELOG
0.1.0-draft.10.
Why: The listen guard reads auth and host policy from config before the database opens, so app depending on config is a real edge.
Evidence: make test stopped in lint-boundaries on backend/app backend/config. The edge is now in the baseline.
Impact: New imports still fail the ratchet. This one records the startup guard's dependency.
Refs: .task/feature-sillytavern-review.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: New cross-layer imports and unused exports could land unnoticed, and confirm-waiting reused the success color.
Evidence: bash scripts/lint-boundaries.sh passed, including a probe that a new edge fails. Both design-guard tests passed. Knip counts stay at the baselines.
Impact: make test-boundaries now checks architecture edges. Frontend and ui test targets also run the knip ratchet.
Refs: feature/architecture-baseline
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev has to test the split modules and refuse a core import of a sibling library.
Evidence: bash scripts/lint-boundaries.sh printed boundaries ok. Full make test follows on this pin.
Impact: test-libs runs the intent, native, sqlite, and command modules. The sibling allowlist is empty.
Refs: D1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Dev could ship a combination whose nested gitlinks differed from the top-level pins, and make test never ran the three agent libraries.
Evidence: A go.work was measured and not adopted: workspace MVS selected newer golang.org/x crypto, exp, net, term, and text than backend with GOWORK=off. check-pins passes on the new pins and fails when backend's squad pin is 5cbac00.
Impact: make test adds pin checks and GOWORK=off vet/test for intent, native, and squad. make build still compiles inside backend; the pin check requires those gitlinks to match Dev.
Refs: R0
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: PR test evidence depended on the agent's word (single point); the
running binary could not answer what combination it was built from; and
irreversible operations lacked an explicit agent-stops-here boundary.
Evidence: Gitea runner online (home-runner, ubuntu-latest+docker); make
version prints describe+component SHAs; two-key line maps to baseline hard
boundary 1. CI first run observed on this PR before merge (see Actions tab).
Impact: .gitea/workflows/ci.yaml runs make test + make build on PR/push;
Makefile injects main.version (make version / agent-system version);
AGENTS.md and adoption register the two-key rule. No product code change.
Refs: policy/adoption.md; release-operations requirements
Why: the library now makes precedence, memory tiers, and lesson
mechanization explicit; the composition must pin the revision and register
how its layers map onto the new rules.
Evidence: guidelines PR#3 (ed2af3e) and documents PR#4 (2205138) merged;
make test on this branch per the gitlink rule.
Impact: gitlink advances; adoption registers the hierarchy/memory rows as
manual-with-existing-artifacts. No code change.
Refs: policy/adoption.md; docs/records/2026-09-30-history-migration-sha-map.md
Why: precheck missed uninitialized submodules (git submodule status '-'
prefix), and the branch protection configured today plus the second live
probe outcome must be recorded honestly in the matrices.
Evidence: platform negative: direct push to protected main rejected
(pre-receive hook declined, Logging-System probe); second write-guard probe
confirmed session-start config loading (no hook run in the pre-config
session log).
Impact: precheck sub_dirty now counts '-' prefixed entries; A3 registered
enforced at platform layer across 11 repos; zcode matrix pending-live
annotated with the loading-timing proof.
Refs: policy/tool-adaptation-matrix.md; policy/tool-adaptation-zcode.md
Why: zcode lacks a rules feature (AGENTS.md is the resident layer) but
supports PreToolUse hooks that can block Edit/Write before the write lands,
upgrading A1/A3 from commit-time to write-time enforcement; the two block
shapes (integration branch, detached submodule) mirror the real incidents.
Evidence: script-level suite 8/8 (N1-N3 blocks with exit 2 and remediation
hints, P1-P5 allows incl. fail-open degradation paths); config JSON valid;
client-side live-fire interception marked pending-live in the matrix.
Impact: .zcode/config.json enables the hook runner for this workspace;
.zcode/plans/ ignored (client state); no product code change.
Refs: Development-Guidelines 0.1.0-draft.8; policy/tool-adaptation-zcode.md
Why: the library now defines requirement-level conformance for tool rules
and hooks (draft.8); the composition's existing gate mechanisms should be
honestly graded against A1-A7 rather than implicitly assumed compliant.
Evidence: matrix rows cite the 19/19 scratch suite negatives, the live data/
dirty-tree interception, and PR records; commit-msg python3 dependency
verified fail-closed by reading the hook's test path.
Impact: docs-only; guidelines gitlink advances to c9ab623 (draft.8); no
workflow or code change.
Refs: Development-Guidelines PR#2 (c9ab623); policy/adoption.md
Why: the nine submodule entry docs and the documents migration record merged
via their own PRs; the parent must pin the new combination and register the
adoption with honest enforcement levels.
Evidence: per-repo PR merges (9x entry-docs PR#1, documents PR#2) verified
via API; make test on this branch follows before merge.
Impact: gitlinks advance to post-migration, gate-adopted mains; policy/
adoption.md registers enforced (local hooks) vs advisory vs manual honestly.
Refs: ef89fc8; Development-Guidelines 0.1.0-draft.7
weichen
