Commit Graph
1502 Commits
Author SHA1 Message Date
weichen 16ad4ca8da Record problem-1 real-model A/B and backend test evidence 2026-10-10 07:56:29 +00:00
weichen a58d45e45d Record problem-1 task scope and authorization 2026-10-10 07:56:13 +00:00
weichen 1cc79ee472 Record the task card for feature-final-reply-pollution-fix
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-final-reply-pollution-fix.md; R0=d53efd5f14bb339dfe908c5d8850ed0eedec024e.

Impact: task metadata only; the feature workspace starts at d53efd5f14.

Refs: .task/feature-final-reply-pollution-fix.md
2026-10-10 07:41:56 +00:00
weichen d53efd5f14 Merge pull request 'Dual-speed tasks: observable slow lane and fast-lane guidance (pin d2bb936)' (#301) from feature/dual-speed-tasks into main
ci / test (push) Successful in 2m58s
2026-10-10 07:40:24 +00:00
weichen 000fe380f7 Fill dual-speed results, verification, and stage review records
ci / test (pull_request) Successful in 2m21s
2026-10-10 07:36:09 +00:00
weichen 83fbf3393d Record combined make test evidence at final head 2026-10-10 07:35:40 +00:00
weichen 287a8da2e3 Record real-model dual-speed A/B evidence in the task card 2026-10-10 07:33:33 +00:00
weichen 1648bd34a1 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=890b9b2bf2e9b356351d373a21f358ea04ca958b; candidate=7ee070fbdb87e31e7af63d53d1e73d1e5d8f11c4.

Impact: task metadata only.

Refs: .task/feature-dual-speed-tasks.md
2026-10-10 07:30:52 +00:00
weichen 7ee070fbdb Record dual-speed mock e2e evidence in the task card 2026-10-10 07:18:10 +00:00
weichen 5dd13d24b8 Pin backend to d2bb936 for the dual-speed slow-lane observability merge
Why: Backend #125 (background subagent inbox card lifecycle, delegate/base-method
dual-speed guidance, #background mock demo) merged into component main; the Dev
gitlink must move to the merged head for the combo to build with it.
Evidence: Backend PR #125 CI green (ci/vet-and-test on 43087a7); Dev-level make
test to be rerun on the committed pin (previous run failed only the drift check
that expects exactly this commit).
Impact: modules/backend gitlink 421fee8 -> d2bb936; no other component moves.
Refs: Backend PR #125; task card feature/dual-speed-tasks.
2026-10-10 07:08:47 +00:00
weichen 2b6abfca72 Record dual-speed task scope, rulings, and plan in the task card 2026-10-10 06:47:04 +00:00
weichen 02cefaca62 Record the task card for feature-dual-speed-tasks
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-dual-speed-tasks.md; R0=890b9b2bf2e9b356351d373a21f358ea04ca958b.

Impact: task metadata only; the feature workspace starts at 890b9b2bf2.

Refs: .task/feature-dual-speed-tasks.md
2026-10-10 06:31:53 +00:00
weichen 890b9b2bf2 Merge pull request 'Close merged task cards (feature/card-close-20261010-051432Z)' (#300) from feature/card-close-20261010-051432Z into main
ci / test (push) Successful in 2m19s
Reviewed-on: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/300
2026-10-10 05:21:09 +00:00
weichen ffb19be516 Close 1 merged task card(s) and archive them
ci / test (pull_request) Successful in 2m18s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-v030-backend-pin.md(PR#299) — 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)
2026-10-10 05:14:32 +00:00
weichen 5ca639786c Merge pull request 'Close the G2-2 slash-and-intents card after Dev PR #292' (#293) from feature/card-close-20261010-003509Z into main
ci / test (push) Successful in 2m16s
Reviewed-on: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/293
2026-10-10 05:07:58 +00:00
weichen a3b8449860 Merge pull request 'Close the EXT-16 exec backend task card after PR #285' (#287) from feature/card-close-20261009-171444Z into main
ci / test (push) Successful in 2m17s
Reviewed-on: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/287
2026-10-10 05:07:46 +00:00
weichen 68988a9ab7 Merge pull request 'Close the EXT-13/15/14 task card after PRs #281/#282' (#284) from feature/card-close-20261009-165152Z into main
ci / test (push) Successful in 2m18s
Reviewed-on: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/284
2026-10-10 05:07:40 +00:00
weichen e627e68e16 Merge pull request 'Close merged task cards (feature/card-close-20261009-111104Z)' (#276) from feature/card-close-20261009-111104Z into main
ci / test (push) Successful in 2m16s
Reviewed-on: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/276
2026-10-10 05:07:29 +00:00
weichen 9ac83eddb7 Merge pull request 'Bump backend to the EXT-8 in-proc registration fix (Backend #124) — v0.3.0 candidate pin' (#299) from feature/v030-backend-pin into main
ci / test (push) Successful in 2m14s
v0.3.0
2026-10-10 03:10:25 +00:00
weichen 291f82171b Record the sync checkpoint
ci / test (pull_request) Successful in 2m18s
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=0d84792d678f7aeafefb52cf47b834be3e4e9011; candidate=c408cc5a0ef11ca0da5cbee7eae917e9014ed7ea.

Impact: task metadata only.

Refs: .task/feature-v030-backend-pin.md
2026-10-10 03:07:35 +00:00
weichen c408cc5a0e Record make test evidence at the v0.3.0 pin head 2026-10-10 03:07:11 +00:00
weichen aa1d8444b5 Bump backend to the EXT-8 in-proc registration fix (Backend #124)
Why: the Dev pin sat at e03d3ac while backend main moved to 421fee8
(#124: pluginRegistry now fills the shared EXT-8 authz slot instead of
rejecting in-proc registrations — the fix that restored rdm.* command
availability in the served RDM process). The umbrella must carry it
before v0.3.0 is tagged so the release combination includes the fix.

Evidence: Backend #124 head 72b2098 CI success, merged as 421fee8;
RDM consumed it as pins 421fee8 in RDM #173 with the full MS1
re-acceptance green. Umbrella make test follows via evidence.

Impact: umbrella gitlink only.

Refs: Backend #124; RDM #173; plan G1-8.
2026-10-10 03:04:43 +00:00
weichen 16752d1493 Record the task card for feature-v030-backend-pin
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-v030-backend-pin.md; R0=0d84792d678f7aeafefb52cf47b834be3e4e9011.

Impact: task metadata only; the feature workspace starts at 0d84792d67.

Refs: .task/feature-v030-backend-pin.md
2026-10-10 03:03:46 +00:00
weichen 0d84792d67 Merge pull request 'Close the model A/B task card after PR #296' (#298) from feature/card-close-20261010-ab into main
ci / test (push) Successful in 2m17s
2026-10-10 03:01:43 +00:00
weichen c9ac7686c4 Merge the A/B card-close branch with current main
ci / test (pull_request) Successful in 2m16s
2026-10-10 02:58:10 +00:00
weichen a43bc3743d Merge pull request 'Pass the PG DSN via environment instead of the command line (G1-7)' (#297) from feature/g1-7-dsn-env into main
ci / test (push) Successful in 2m20s
2026-10-10 02:43:05 +00:00
weichen 8c010f6000 Close 1 merged task card: feature/agent-model-ab
ci / test (pull_request) Successful in 2m21s
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).
2026-10-10 02:39:53 +00:00
weichen a6d434e432 Pass the PG DSN via environment instead of the command line (G1-7)
ci / test (pull_request) Successful in 2m18s
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.
2026-10-10 02:39:19 +00:00
weichen 63a2485ec0 Merge pull request 'Model A/B: opus-5-5 eliminates invented numbers (selection report)' (#296) from feature/agent-model-ab into main
ci / test (push) Successful in 2m20s
2026-10-10 02:35:14 +00:00
weichen 8f96b92071 Record the model A/B make-test evidence
ci / test (pull_request) Successful in 2m19s
2026-10-10 02:26:17 +00:00
weichen 112d9e40c9 Complete the model A/B comparison and record the selection report
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.
2026-10-10 02:24:56 +00:00
weichen 66c9edfe05 Record the second quota-blocked A/B attempt after the flash-tier probe
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_*.
2026-10-10 01:19:29 +00:00
weichen 4f97587c9a Record the model A/B pipeline validation and the quota block
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.
2026-10-10 01:04:47 +00:00
weichen 47be266062 Record the task card for feature-agent-model-ab
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
2026-10-10 00:52:59 +00:00
weichen 43f8e27b74 Merge pull request 'Close merged task cards (feature/card-close-20261010-004524Z)' (#295) from feature/card-close-20261010-004524Z into main
ci / test (push) Successful in 2m14s
2026-10-10 00:50:02 +00:00
weichen fedd55c1eb Close 1 merged task card(s) and archive them
ci / test (pull_request) Successful in 2m14s
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)
2026-10-10 00:45:24 +00:00
weichen 83d1cb20f6 Merge pull request 'Quality phase05: hard-fact gate, fact checks, lazy search (Backend #123)' (#294) from feature/agent-quality-phase05 into main
ci / test (push) Successful in 2m14s
2026-10-10 00:45:01 +00:00
weichen df257cd1a3 Close out phase05 with merge links and final evidence
ci / test (pull_request) Successful in 2m15s
2026-10-10 00:35:55 +00:00
weichen 741023a76d Close 1 merged task card(s) and archive them
ci / test (pull_request) Successful in 2m15s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-g2-2-slash-intents.md(PR#292) — 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)
2026-10-10 00:35:09 +00:00
weichen 3ed2d6b1c8 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=57b293d00945173f61e3a5f7bef8153053f49395; candidate=c7a981ed3b09f44610d9674c01409f13300fd08c.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase05.md
2026-10-10 00:35:00 +00:00
weichen c7a981ed3b Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=57b293d00945173f61e3a5f7bef8153053f49395.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-10 00:34:38 +00:00
weichen 9a2b697ecf Point the backend gitlink at the merged phase05 head 2026-10-10 00:34:36 +00:00
weichen 57b293d009 Merge pull request 'Consume the G2-2 slash-and-intents backend (Backend #122)' (#292) from feature/g2-2-slash-intents into main
ci / test (push) Successful in 2m15s
2026-10-10 00:27:14 +00:00
weichen d1a00e0c9a Record the phase05 live eval and result summary 2026-10-10 00:25:37 +00:00
weichen f8228d1f9e Record the sync checkpoint
ci / test (pull_request) Successful in 2m14s
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=d9786f0f4128bbee43e27bdcc1534e320aae1711; candidate=2f87563937d1a75f74e8e9682a9e8bd1ec1546b8.

Impact: task metadata only.

Refs: .task/feature-g2-2-slash-intents.md
2026-10-10 00:24:15 +00:00
weichen 2f87563937 Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=d9786f0f4128bbee43e27bdcc1534e320aae1711.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-10 00:23:54 +00:00
weichen ffdcc59fea Record make test evidence at the G2-2 bump head 2026-10-10 00:23:51 +00:00
weichen 89e88b3965 Bump backend to the G2-2 slash-and-intents merge (Backend #122)
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.
2026-10-10 00:21:51 +00:00
weichen b6bdceb6ed Record the phase05 make-test and sync evidence 2026-10-10 00:07:39 +00:00
weichen 5ea06c51c9 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=d9786f0f4128bbee43e27bdcc1534e320aae1711; candidate=1e60e4d507880c9269e3f9641b01539e9f10a3bd.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase05.md
2026-10-10 00:06:43 +00:00