Commit Graph
1452 Commits
Author SHA1 Message Date
weichen 9a2b697ecf Point the backend gitlink at the merged phase05 head 2026-10-10 00:34:36 +00:00
weichen d1a00e0c9a Record the phase05 live eval and result summary 2026-10-10 00:25:37 +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
weichen 1e60e4d507 Fill the phase05 task card scope 2026-10-10 00:05:08 +00:00
weichen ff3a9d4726 Point the backend gitlink at the phase05 head
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.
2026-10-10 00:05:08 +00:00
weichen d715e95de1 Record the task card for feature-agent-quality-phase05
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
2026-10-09 23:55:54 +00:00
weichen d9786f0f41 Merge pull request 'Close merged task cards (feature/card-close-20261009-234849Z)' (#291) from feature/card-close-20261009-234849Z into main
ci / test (push) Successful in 2m12s
2026-10-09 23:53:26 +00:00
weichen d0e3e2e728 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-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)
2026-10-09 23:48:49 +00:00
weichen b7489d4431 Merge pull request 'Quality phase04: working-method prompts, compose demotion (Backend #121)' (#290) from feature/agent-quality-phase04 into main
ci / test (push) Successful in 2m14s
2026-10-09 23:48:27 +00:00
weichen d78f3bedf5 Record the phase04 final green make-test evidence (SSE flake rerun)
ci / test (pull_request) Successful in 2m12s
2026-10-09 23:43:49 +00:00
weichen c03ddc2652 Close out phase04 with merge links and final evidence 2026-10-09 23:41:55 +00:00
weichen c14193353f Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=4713f04c94eb2512152e412fd010f846caa10021; candidate=d5185c5ff32d909a823237b5c264b1e3007c3476.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase04.md
2026-10-09 23:41:02 +00:00
weichen d5185c5ff3 Point the backend gitlink at the merged phase04 head 2026-10-09 23:40:39 +00:00
weichen 80a35b888b Record the phase04 live eval and result summary 2026-10-09 23:35:48 +00:00
weichen dd18b9fd6f Record the phase04 make-test and sync evidence 2026-10-09 23:15:31 +00:00
weichen 27246370b7 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=4713f04c94eb2512152e412fd010f846caa10021; candidate=8b09cdc411fa59b8a53a82c746c7ba42913574a0.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase04.md
2026-10-09 23:14:35 +00:00
weichen 8b09cdc411 Point the backend gitlink at the phase04 head
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.
2026-10-09 23:12:58 +00:00
weichen 2cbb00befa Record the task card for feature-agent-quality-phase04
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
2026-10-09 23:09:09 +00:00
weichen 4713f04c94 Merge pull request 'Close merged task cards (feature/card-close-20261009-230217Z)' (#289) from feature/card-close-20261009-230217Z into main
ci / test (push) Successful in 2m32s
2026-10-09 23:06:58 +00:00
weichen 3ab92b8c0f Close 1 merged task card(s) and archive them
ci / test (pull_request) Successful in 2m11s
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)
2026-10-09 23:02:17 +00:00
weichen 8033c53be3 Merge pull request 'Quality phase03: workspace tools + markdown-source pipeline (Backend #120)' (#288) from feature/agent-quality-phase03 into main
ci / test (push) Successful in 2m12s
2026-10-09 18:36:09 +00:00
weichen 9134f8462c Close out phase03 with merge links
ci / test (pull_request) Successful in 2m13s
2026-10-09 18:31:17 +00:00
weichen 497dfd3738 Record the phase03 final evidence 2026-10-09 18:31:08 +00:00
weichen 60114463a4 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=02f2c1bcfb1b8ac936e357b90fa7a2973f4ce0c0; candidate=d610523a95d9a19c5d5b416e27a23a7324a710f4.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase03.md
2026-10-09 18:30:10 +00:00
weichen d610523a95 Point the backend gitlink at the merged phase03 head
Why: Backend #120 merged; the Dev combination tests the merged head.

Evidence: SELF - gitlink equals backend origin/main head.

Impact: Pointer only.
2026-10-09 18:29:46 +00:00
weichen c4b581d6f9 Record the phase03 live eval and result summary 2026-10-09 18:24:50 +00:00
weichen e7e9b26ae5 Record the phase03 make-test and sync evidence 2026-10-09 18:03:51 +00:00
weichen 2410dd2946 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=02f2c1bcfb1b8ac936e357b90fa7a2973f4ce0c0; candidate=5e42db6ea86f0ae2cdb40bb27f72c4688451258a.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase03.md
2026-10-09 18:02:54 +00:00
weichen 5e42db6ea8 Fill the phase03 task card scope 2026-10-09 18:01:21 +00:00
weichen fcbf74b24e Point the backend gitlink at the phase03 head
Why: The Dev combination must test the workspace-tool opening and the build
pipeline.

Evidence: SELF - gitlink equals backend feature/agent-quality-phase03 head.

Impact: Pointer only.
2026-10-09 18:01:21 +00:00
weichen 8c08461e28 Record the task card for feature-agent-quality-phase03
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-agent-quality-phase03.md; R0=02f2c1bcfb1b8ac936e357b90fa7a2973f4ce0c0.

Impact: task metadata only; the feature workspace starts at 02f2c1bcfb.

Refs: .task/feature-agent-quality-phase03.md
2026-10-09 17:56:09 +00:00
weichen 02f2c1bcfb Merge pull request 'Close the EXT-13/15/14 task card after PRs #281/#282 (and archive merged cards)' (#283) from feature/card-close-20261009-165106Z into main
ci / test (push) Successful in 2m14s
2026-10-09 17:53:32 +00:00
weichen 843465ba49 Merge current origin/main into the card-close branch (main side wins for the g1 archive)
ci / test (pull_request) Successful in 2m14s
2026-10-09 17:48:24 +00:00
weichen 57e7b62326 Merge origin/main into the card-close branch (archive side wins)
ci / test (pull_request) Successful in 2m14s
2026-10-09 17:41:15 +00:00
weichen 911bec70a4 Merge pull request 'Quality phase02 I2: transcript-authoritative context (Native #41, Backend #115/#118, Squad #49)' (#286) from feature/agent-quality-phase02 into main
ci / test (push) Successful in 2m19s
2026-10-09 17:36:03 +00:00
weichen fe0333e44f Record the sync checkpoint
ci / test (pull_request) Successful in 2m13s
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=7d52861f15f2b25dd5121301ac1e92b5a5e16f8d; candidate=1164b96838753528ae55eb8dff87729da05f9815.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase02.md
2026-10-09 17:31:42 +00:00
weichen 1164b96838 Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=7d52861f15f2b25dd5121301ac1e92b5a5e16f8d.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-09 17:31:21 +00:00
weichen 7d52861f15 Merge pull request 'Consume the EXT-16 exec backend interface (Backend #119)' (#285) from feature/ext-16-exec-backend into main
ci / test (push) Successful in 2m21s
2026-10-09 17:14:11 +00:00
weichen 3246a7c47b Record the phase02 final make-test evidence at the synced head
ci / test (pull_request) Successful in 2m24s
2026-10-09 17:12:55 +00:00
weichen 65d1621123 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=13e03ab15d89d13e0b1cc6848d76776c723a6f96; candidate=6caac63ec0b979df9ff692df2fe3b8f88d32f8ad.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase02.md
2026-10-09 17:11:33 +00:00
weichen 6caac63ec0 Record the failing make-test segment for the pin cascade 2026-10-09 17:11:11 +00:00
weichen 68f5f0da8c Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=13e03ab15d89d13e0b1cc6848d76776c723a6f96.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-09 17:10:32 +00:00
weichen 3b700db79d Allow the runmgr-to-cmdbus edge in the architecture ratchet
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.
2026-10-09 17:10:30 +00:00
weichen bbdd3f4505 Disable auto-gc in the task-lifecycle remote fixture
ci / test (pull_request) Successful in 2m13s
Why: git receive-pack runs 'gc --auto' in the background after a push;
the fixture's TemporaryDirectory teardown then races the gc writer and
fails with OSError 39 (remote.git not empty) — observed on the PR #285
runner (job 1967). The fixture remote holds no durable value, so auto-gc
is pure flake surface.

Evidence: the failing test passes 5/5 locally after the fix; full
make test-governance green (104 tests).

Impact: test fixture only; no governance-script behavior change.

Refs: Dev CI run 1438 job 1967; same race family as the upload-host
TempDir flake fixed earlier.
2026-10-09 17:10:18 +00:00
weichen 4a63537a52 Point the backend gitlink at the merged phase02 heads
Why: Backend #115 (transcript-authoritative switch) and #118 (squad pin
alignment) merged; the Dev combination tests the merged head.

Evidence: SELF - gitlink equals backend origin/main head; make test recorded
on the task card after this commit.

Impact: Pointer only.
2026-10-09 17:10:17 +00:00
weichen fdf373b78a Record the sync checkpoint
ci / test (pull_request) Failing after 45s
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=13e03ab15d89d13e0b1cc6848d76776c723a6f96; candidate=44c436ed339b3f2189ec8c426c18a9358eada63c.

Impact: task metadata only.

Refs: .task/feature-ext-16-exec-backend.md
2026-10-09 17:06:06 +00:00
weichen 44c436ed33 Record the sandbox escape-negative evidence row and fill the result summary
Why: the EXT-16 acceptance is escape-negative driven; the tool-written
evidence row captures the local bwrap run (all probes blocked, product
task visible) and the card summary states scope and follow-ups.

Evidence: go test -run 'TestSetExecBackendValidation|TestSandboxArgvShape|
TestSandbox|TestDirect' via CMD=... make evidence exit 0 (10 tests,
bwrap 0.11.1); make test row recorded earlier at this head.

Impact: task card only.

Refs: proposal 2026-10-09-ext-g1-b1-b3 (EXT-16); Backend #119.
2026-10-09 17:05:42 +00:00
weichen b46b0fefba Record the make test evidence row at the EXT-16 bump head 2026-10-09 17:05:19 +00:00
weichen efad2d1570 Bump backend to the EXT-16 exec backend merge (Backend #119)
Why: EXT-16 abstracts the interpreter launch point into an ExecBackend
port (direct = byte-identical status quo; sandbox = bwrap isolation:
ro root, tmpfs /home+/tmp, session/skills-only writable mounts, no
network, ulimit -u fork cap, timeout kills the namespace) with config
key execBackend, env AGENT_SYSTEM_EXEC_BACKEND, CLI --exec-backend and
extension.Options.ExecBackend (SurfaceVersion 2.6.0-experimental).
DisableExecTools stays the top-priority fail-closed switch; RDM keeps
DisableExecTools=true until G3-7.

Evidence: Backend #119 head 4badecb vet-and-test CI success, merged as
1a55089; local escape negatives all blocked (home secret, sibling
session, network, 400-proc spawn storm, 60s-sleep timeout kill,
orphan die-with-namespace) recorded in the task card evidence rows;
full make test at this head recorded on the card.

Impact: umbrella gitlink only; no source edits outside modules/backend.

Refs: proposal modules/documents docs/proposals/2026-10-09-ext-g1-b1-b3
(EXT-16); Backend #119; Backend #110 (DisableExecTools).
2026-10-09 17:03:12 +00:00