Why: The model A/B branch merged into main via #296 (the final item of the
quality improvement plan); its task card must be backfilled and archived to
prevent bookkeeping debt.
Evidence: SELF - merge 63a2485 verified via git log --merges against
origin/main; card backfilled with the PR link.
Impact: .task/feature-agent-model-ab.md moved to .task/archive/ with status
backfilled; no code or submodule change.
Refs: task.sh close semantics (replicated from a temp worktree because the
main checkout is occupied by a parallel writer's branch).
Why: the plan section 3.4 observed the local dev service carrying the
credential-bearing DSN as a serve --dsn argument, visible to any
process on the host (ps / /proc/<pid>/cmdline) — including scripts
generated by agents. The base config layer already supports
AGENT_SYSTEM_DSN, so the launcher can move the secret out of the
argument vector without touching the binary.
Evidence: bash -n clean; make test-governance 104/104 green; an
end-to-end probe with a stub binary and a legacy exec= carrying
--dsn ...secret... shows the migration stripping the flag
(MIGRATED:yes), the process args free of the secret
(NO-LEAK-IN-CMDLINE), and AGENT_SYSTEM_DSN present in the process
environment (DSN_IN_ENV:yes). New/rebuilt launches never put the DSN
in argv; legacy persisted configs are migrated on first reuse.
Impact: scripts/svc.sh only — rebuild path sets DSN_ENV instead of
--dsn, reuse path strips --dsn from stored exec= once and logs the
migration, launch injects AGENT_SYSTEM_DSN alongside the existing
guard vars. CLI --dsn still wins inside the binary (config
precedence), so manual invocations are unchanged.
Refs: plan G1-7 (line 356) and section 3.4 (2026-10-09 ps
observation); backend config AGENT_SYSTEM_DSN.
Why: Ruling 5's final item. With the user-provided lmuai endpoint
(claude-opus-5-5) and the P5 build unchanged, the same golden task set ran
both sides to completion (6/6 turns each).
Evidence: SELF - B report .task/model-ab/ab-opus.json (2793s) vs A baseline
.task/phase05-eval/after-p5.json; smoke through the live instance confirmed
the provider switch (after fixing the active-secret shadowing: overlayKey
prefers the secret table, so provider changes need /api/secrets rotation).
Impact: Selection report in the card - opus-5-5 eliminates invented numbers
(7 -> 0, the program's core metric), restores independent verification via
lightweight=deepseek-v4-flash; MiniMax stays as the fast/fallback tier.
Recommended default documented for the owner.
Why: A small max_tokens probe passed (small pre-deduction), suggesting the
account might have been topped up; redeploying with chat=claude-sonnet-4-6
and lightweight=deepseek-v4-flash showed full-turn pre-deduction (CNY 0.62)
still exceeds the CNY 0.48 balance - 6/6 turns quota-failed again.
Evidence: SELF - .task/model-ab/ab-sonnet-quota-blocked-r2.json + evidence
row; settings confirmed chat=claude-sonnet-4-6, lightweight=deepseek-v4-flash
on the instance before the run.
Impact: Still blocked on user-only payment input. Estimated CNY 50-100 covers
multiple full comparison runs on dmxapi; alternatively any OpenAI-compatible
provider key via ~/.secrets/abmodel or .env.dev SVC_MODEL_*.
Why: Ruling 5 authorized the strong-model comparison with uncapped budget.
The A/B infrastructure is proven end to end (qa7 on remote main, seeded
claude-sonnet-4-6 via the user's existing dmxapi aggregator key, eval/live
ran the full golden set), but the account holds CNY 0.49 against a CNY 0.62
per-request pre-deduction - all six turns failed with insufficient quota,
captured honestly in the report.
Evidence: SELF - .task/model-ab/ab-sonnet-quota-blocked.json + evidence row;
smoke test of the dmxapi streaming endpoint succeeded before the run.
Impact: Task blocked on user input only (top up dmxapi or provide another
provider key). No code changes; worktree retained for immediate resumption.
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-agent-model-ab.md; R0=43f8e27b74e5e2213e2099ba04e5a69fe398586f.
Impact: task metadata only; the feature workspace starts at 43f8e27b74.
Refs: .task/feature-agent-model-ab.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-quality-phase05.md(PR#294) — 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: include the current integration baseline before verification.
Evidence: fetched origin/main=57b293d00945173f61e3a5f7bef8153053f49395.
Impact: integrate upstream changes without rewriting task history.
Refs: task-sync
Why: include the current integration baseline before verification.
Evidence: fetched origin/main=d9786f0f4128bbee43e27bdcc1534e320aae1711.
Impact: integrate upstream changes without rewriting task history.
Refs: task-sync
Why: G2-2 lands plugin slash aliases (EXT-10②) and the intent
declaration surface — the bus binds plugin-spec Slash fields into the
shared alias table (four entrances, one audit envelope), extensions
declare intents via AddIntent, and the system.intent builtin routes
natural language through the bus deterministically (longest-phrase
containment). The umbrella carries the backend gitlink forward.
Evidence: Backend #122 head 9c4edc4 CI success, merged as 9a531a6;
full backend suite 32/32 packages green; lib pin Agent-Command 4f583ca
(PR #6).
Impact: umbrella gitlink only.
Refs: plan G2-2; Backend #122; Agent-Command #6.
Why: The Dev combination must test the gate narrowing, fact checks and lazy
search registration.
Evidence: SELF - gitlink equals backend feature/agent-quality-phase05 head.
Impact: Pointer only.
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-agent-quality-phase05.md; R0=d9786f0f4128bbee43e27bdcc1534e320aae1711.
Impact: task metadata only; the feature workspace starts at d9786f0f41.
Refs: .task/feature-agent-quality-phase05.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-quality-phase04.md(PR#290) — 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: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-g2-2-slash-intents.md; R0=4713f04c94eb2512152e412fd010f846caa10021.
Impact: task metadata only; the feature workspace starts at 4713f04c94.
Refs: .task/feature-g2-2-slash-intents.md
Why: The Dev combination must test the working-method prompt set and the
compose demotion.
Evidence: SELF - gitlink equals backend feature/agent-quality-phase04 head.
Impact: Pointer only.
Why: establish the authorized task workspace and its initial baseline.
Evidence: preserved precheck receipt in .task/feature-agent-quality-phase04.md; R0=4713f04c94eb2512152e412fd010f846caa10021.
Impact: task metadata only; the feature workspace starts at 4713f04c94.
Refs: .task/feature-agent-quality-phase04.md
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-quality-phase03.md(PR#288) — 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)
weichen