Commit Graph
1403 Commits
Author SHA1 Message Date
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 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 794104f0aa Point the backend gitlink at the squad-pin alignment head 2026-10-09 16:55:03 +00:00
weichen 13e03ab15d Merge pull request 'Consume the EXT-14 backend (commands-as-tools) with the full pin cascade' (#282) from feature/ext-13-15-shared-runs into main
ci / test (push) Successful in 2m28s
2026-10-09 16:49:25 +00:00
weichen e442af362f Record make test evidence at the cascaded pin head and fill the result summary
ci / test (pull_request) Successful in 2m22s
Why: the EXT-14 umbrella bump now carries the full pin cascade
(backend 31965fd, agent-command 5c6dd0c, agent-native 3b92cb63,
agent-squad 8bbf850) and the combined suite is green; the completion
declaration needs the tool-written evidence row plus the result summary.

Evidence: make test via 'CMD=make test make evidence' exit 0 at HEAD
(receipt appended, SELF); GATE rows cited in the summary (Backend
#114/#116/#117 CI success).

Impact: task card only.

Refs: Backend #114/#116/#117; Squad #49; agent-command lib #4/#5.
2026-10-09 16:44:04 +00:00
weichen 13a3e63628 Bump backend past the EXT-14 dependency fix and cascade dep pins
Why: consuming backend main (#115 kernel-transcript + #116 EXT-14
dependency inversion) moves backend pins for agent-native (3b92cb63)
and agent-squad (8bbf850, Squad #49 nested native bump); the umbrella
check-pins requires Dev's top-level pins and every container gitlink to
agree, and Dev's agent-command pin must follow backend's EXT-14 lib bump
(5c6dd0c, lib PRs #4/#5).

Evidence: Backend #116 (6337cd8) and #117 (5544a03) vet-and-test CI
success, merged as 8157e68/31965fd; Squad #49 merge 8bbf850 records
deps/agent-native=3b92cb63 (ls-tree verified); umbrella
lint-boundaries pre-verified green at 6337cd8 (77 edges, negative probe
ok); full make test recorded on the task card at the final head.

Impact: gitlink-only changes (modules/backend, deps/agent-squad,
deps/agent-command, deps/agent-native); no source edits in the umbrella.

Refs: Backend #115/#116/#117; Squad #49; agent-command lib #4/#5;
proposal 2026-10-09-ext-g1-b1-b3 (EXT-14).
2026-10-09 16:40:48 +00:00
weichen 124d0f9938 Point agent-squad at the nested native pin merge
Why: Squad #49 aligned its nested agent-native pin with the Dev top-level
pointer; the Dev worktree records the merged head.

Evidence: SELF - gitlink equals Agent-Squad main head.

Impact: Pointer only.
2026-10-09 16:36:54 +00:00
weichen a643be5964 Record the phase02 final make-test evidence 2026-10-09 16:28:21 +00:00
weichen dacdcbd773 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=6c763cc1cf4b3e980835de0ad864220f97f3c93c; candidate=2b46d055a09ae285c9b42cbd6dd97dd21ca448b0.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase02.md
2026-10-09 16:27:54 +00:00
weichen 2b46d055a0 Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=6c763cc1cf4b3e980835de0ad864220f97f3c93c.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-09 16:27:32 +00:00
weichen baaed7c4d0 Point the backend gitlink at the merged I2 head
Why: Backend #115 merged the transcript-authoritative switch; the Dev
combination must test the merged head (with main's concurrent EXT-14).

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

Impact: Pointer only.
2026-10-09 16:27:30 +00:00
weichen 94a4c70804 Record the phase02 final make-test and sync evidence 2026-10-09 16:27:19 +00:00
weichen f2a3d4b3b7 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=6c763cc1cf4b3e980835de0ad864220f97f3c93c; candidate=79c5ffb8538128849e673b82fd1859276725c403.

Impact: task metadata only.

Refs: .task/feature-ext-13-15-shared-runs.md
2026-10-09 16:26:34 +00:00
weichen 79c5ffb853 Merge authoritative main into the task branch
Why: include the current integration baseline before verification.

Evidence: fetched origin/main=6c763cc1cf4b3e980835de0ad864220f97f3c93c.

Impact: integrate upstream changes without rewriting task history.

Refs: task-sync
2026-10-09 16:26:12 +00:00
weichen 0f0cbd9df4 Bump backend to the EXT-14 commands-as-tools merge (Backend #114)
Why: EXT-14 lands commands-as-tools in the base — CommandTool projection
from the command bus (ExposeAsTool+Enabled only) and ExecuteTool dispatch
through DispatchCommand with Entrance=agent, Actor/Owner bound to the
conversation owner and high-risk commands gated by the confirm card.
The Dev umbrella must carry the backend gitlink forward so combined CI
and downstream pins consume it.

Evidence: Backend #114 head 0209262 CI success (vet-and-test), merged as
545dc404e50d2a739ab29d83f320ccf54049e190; go test ./... 32/32 packages
green on the branch; main push CI status checked before this bump.

Impact: umbrella-only gitlink change; no source edits outside
modules/backend; RDM pins unaffected until a separate bump task.

Refs: docs/proposals/2026-10-09-ext-g1-b1-b3-exec-backend.md (EXT-14);
Backend PR #114; agent-command lib PRs #4/#5 (merge 9effe90/5c6dd0c).
2026-10-09 16:25:22 +00:00
weichen 3ca8fc5f4c Record the phase02 I2 live-eval and the three-way comparison 2026-10-09 16:17:46 +00:00
weichen 6c763cc1cf Merge pull request 'Take the EXT-13/15 shared-runs backend (Backend #113)' (#281) from feature/ext-13-15-shared-runs into main
ci / test (push) Successful in 2m46s
2026-10-09 15:59:28 +00:00
weichen 8bdb9c092e Record make test evidence at the synced head
ci / test (pull_request) Successful in 2m30s
2026-10-09 15:54:35 +00:00
weichen 70a3e6bf22 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=bc74b9a0c5ac4f137b00aa53af37ec67e4aeb1cb; candidate=4d7284b529e1689e595adfed9cb5ae4953663558.

Impact: task metadata only.

Refs: .task/feature-ext-13-15-shared-runs.md
2026-10-09 15:53:30 +00:00
weichen 4d7284b529 Record make test evidence row 2026-10-09 15:53:08 +00:00
weichen 2fdc327de0 Bump backend to the EXT-13/15 shared-runs commit
Why: RDM G1 sequence-4 needs the base to share retrieval inside runs and
open project listing/conversations to adapter-authorized members; the
implementation is merged on Backend main and the Dev gitlink is the
delivery vehicle.
Evidence: SELF - Backend PR #113 CI success at the merge head 9fa1787
(run rerun green after an unrelated ordering flake; the full suite passed
locally 32/32 first); Dev composite CI on this PR is the GATE.
Impact: modules/backend gitlink 449d8a6 -> 9fa1787. No other pin changes.
Refs: Backend #113; proposal 2026-10-09-ext-g1-b1-b3-exec-backend (EXT-13/15)
2026-10-09 15:51:05 +00:00
weichen 03283e6425 Point backend and agent-native at the phase02 I2 heads
Why: I2 switches the direct path to the kernel transcript as the authoritative
context; the backend head carries that switch plus the nested kernel pin.

Evidence: SELF - gitlinks equal the pushed branch heads; combined make test
recorded on the task card after this commit.

Impact: Pointer only.
2026-10-09 15:39:25 +00:00
weichen e33d5df31e Record the task card for feature-ext-13-15-shared-runs
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-ext-13-15-shared-runs.md; R0=bc74b9a0c5ac4f137b00aa53af37ec67e4aeb1cb.

Impact: task metadata only; the feature workspace starts at bc74b9a0c5.

Refs: .task/feature-ext-13-15-shared-runs.md
2026-10-09 15:38:30 +00:00
weichen bc74b9a0c5 Merge pull request 'Register the G1 extension applications (EXT-13..16) via the documents pin' (#279) from feature/g1-ext-b1-b3 into main
ci / test (push) Successful in 3m13s
2026-10-09 15:19:57 +00:00
weichen aea9665f73 Nudge CI: the llm lib test timed out (run 1394)
ci / test (pull_request) Successful in 2m48s
2026-10-09 15:14:50 +00:00
weichen f49d272d58 Record make test evidence at the synced head 2026-10-09 15:14:50 +00:00
weichen 3b25d15190 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=2e92b184f3f257bbe9c90fd9e8278c2b6f192251; candidate=cdf4512a226cead580cea674374110e4124b97c1.

Impact: task metadata only.

Refs: .task/feature-g1-ext-b1-b3.md
2026-10-09 15:14:50 +00:00
weichen 8022718c8c Record make test evidence row 2026-10-09 15:14:50 +00:00
weichen 0f83b9c5de Fill the G1 extension package task card 2026-10-09 15:14:50 +00:00
weichen e20d4aa325 Point documents at the G1 extension application package
Why: EXT-13..EXT-16 (shared in-run retrieval, commands-as-tools, shared
project list, exec backend seam) are the base-side prerequisites RDM G1/G2
depend on; the application must live on the base Documents main before
implementation tasks can be opened against it.
Evidence: SELF - Documents #52 merged (3e43193); proposal cites code
locations verified at Dev main; Dev composite CI on this PR is the GATE.
Impact: modules/documents gitlink bump only.
Refs: Documents #52; RDM plan V1.1 sections 3.3/3.4/5.3
2026-10-09 15:14:50 +00:00
weichen e9a23b1425 Record the task card for feature-g1-ext-b1-b3
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-g1-ext-b1-b3.md; R0=2e92b184f3f257bbe9c90fd9e8278c2b6f192251.

Impact: task metadata only; the feature workspace starts at 2e92b184f3.

Refs: .task/feature-g1-ext-b1-b3.md
2026-10-09 15:14:50 +00:00
weichen ccf19803cd Merge pull request 'Quality phase02 I1: context fidelity (Backend #112)' (#280) from feature/agent-quality-phase02 into main
ci / test (push) Successful in 2m40s
2026-10-09 15:12:03 +00:00
weichen 533c8b1a3b Record the phase02 I1 live-eval pair and result summary
ci / test (pull_request) Successful in 2m39s
2026-10-09 15:00:31 +00:00
weichen 11679270ab Repoint the backend gitlink at the tool-dump exclusion head
Why: The gate misfire fix from the live after-run belongs in the same increment.

Evidence: SELF - gitlink equals the backend phase02 head.

Impact: Pointer only.
2026-10-09 14:56:43 +00:00
weichen 926fc631a1 Record the phase02 make-test evidence row 2026-10-09 14:35:33 +00:00
weichen 50d9881ecc Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=2e92b184f3f257bbe9c90fd9e8278c2b6f192251; candidate=76d9b5b262ef80f53cd1af47c28aee555146fdb9.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase02.md
2026-10-09 14:30:20 +00:00
weichen 76d9b5b262 Point the backend gitlink at the phase02 I1 head
Why: The Dev combination must test the context-fidelity increment.

Evidence: SELF - gitlink equals backend feature/agent-quality-phase02 head.

Impact: Pointer only.
2026-10-09 14:28:56 +00:00
weichen 9c4c6e6a5c Fill the phase02 task card scope for increment I1 2026-10-09 14:28:56 +00:00
weichen ad3384a472 Record the task card for feature-agent-quality-phase02
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-agent-quality-phase02.md; R0=2e92b184f3f257bbe9c90fd9e8278c2b6f192251.

Impact: task metadata only; the feature workspace starts at 2e92b184f3.

Refs: .task/feature-agent-quality-phase02.md
2026-10-09 14:24:21 +00:00
weichen 2e92b184f3 Merge pull request 'Close 1 merged task card: feature/agent-quality-phase01' (#278) from feature/card-close-20261009-141722Z into main
ci / test (push) Successful in 8m8s
2026-10-09 14:22:21 +00:00
weichen d6932f8716 Close 1 merged task card(s) and archive them
ci / test (pull_request) Successful in 2m41s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-quality-phase01.md(PR#277) — 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 14:17:22 +00:00
weichen 4deddf458d Merge pull request 'Quality phase01: gate repairs, live eval baseline, policy clause (Backend #111, Documents #51)' (#277) from feature/agent-quality-phase01 into main
ci / test (push) Successful in 2m49s
2026-10-09 14:13:07 +00:00
weichen 80b76e0c68 Record the after-phase01 live eval and the before/after verdict
ci / test (pull_request) Successful in 3m36s
Why: Ruling 6 requires real-model before/after evidence. The after run (fixed
build b68833f, same golden tasks) proves the repairs landed: lint now actually
executes (real layout/lead findings appear vs silent empties before), the
pm-tool readability dead-loop is gone (4/0 -> 0), plan-followup reads original
materials 0 -> 49 times. Remaining failures are the documented P5/P2 scope
(rename-revision loops via scorer semantics, unverified numbers, verifier
parse hiccups), not regressions.

Evidence: SELF - report .task/phase01-eval/after-phase01-b68833f.json +
evidence row (1749s run); comparison table in the card.

Impact: PR #277 now carries the complete before/after pair for review.
2026-10-09 14:04:05 +00:00
weichen e0fc10d829 Fill the phase01 result summary and remaining items
ci / test (pull_request) Successful in 3m51s
2026-10-09 13:29:55 +00:00
weichen 3cbe5dcd3c Record the live-eval evidence row for the before baseline 2026-10-09 13:29:18 +00:00
weichen 61ec1c3b81 Import the make-test evidence receipt for phase01 2026-10-09 13:08:04 +00:00
weichen f6da1d67e5 Record the sync checkpoint
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=1ebd46edc5239d0d87418e9a8dd9aa225955e1dd; candidate=3d9285c1f332d01f48329549359c5c7d231679d8.

Impact: task metadata only.

Refs: .task/feature-agent-quality-phase01.md
2026-10-09 13:05:05 +00:00
weichen 3d9285c1f3 Pin the phase01 heads and record the before-baseline report
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.
2026-10-09 13:04:38 +00:00
weichen bfe77d3505 Repoint the backend gitlink at the lint-wiring fix 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.
2026-10-09 12:55:58 +00:00