Commit Graph
578 Commits
Author SHA1 Message Date
weichen 5096a052dc Merge pull request 'Pin backend to the depth-one subagent loop' (#140) from feature/agent-harness-p3 into main
ci / test (push) Failing after 1m38s
2026-10-01 14:51:02 +00:00
weichenandCursor 8c43d4b16c Move the merge sync row into the task card table
ci / test (pull_request) Failing after 1m56s
Why: task-sync appended the checkpoint after the test block. The card keeps sync rows in one table.
Evidence: sync_base bc8fef76bb, tested_head 53f8a05, checked_at 2026-10-01T14:50:18Z.
Impact: Task card only.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:50:39 +00:00
weichen 74973fe4d6 Record the sync checkpoint 2026-10-01 14:50:18 +00:00
weichenandCursor 53f8a059bd Record the live subagent conversation check
ci / test (pull_request) Failing after 1m35s
Why: The confirm card on a child run and the history split were only covered by tests. A real conversation had to show they hold before merge.
Evidence: p3a at dev@f823118. explore hid tool names from the next turn, writer pinned artifacts, the inbox showed the child confirm card, and the squad leader wrote output.md.
Impact: Task card only. No code change.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:50:08 +00:00
weichenandCursor f8231182ed Record the harness pull requests on the task card
ci / test (pull_request) Failing after 1m31s
Why: The card is the pull request body, so it has to name the open Backend and Dev requests.
Evidence: Backend pull 45 and Dev pull 140 are open and unmerged.
Impact: Task card only. Neither request is merged.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:15:08 +00:00
weichenandCursor 099bcd5e01 Record the harness P3a verification on the task card
ci / test (pull_request) Failing after 1m31s
Why: Acceptance needs the precheck, task-sync, and test evidence on the same card that will become the pull request.
Evidence: make task-sync at 5ed3649; make test exited 0 (boundaries, core, backend, frontend 51, ui 71, agent-command).
Impact: Task card only. No code or submodule change.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:14:41 +00:00
weichen 0cb89b3a3a Record the sync checkpoint 2026-10-01 14:13:39 +00:00
weichenandCursor 5ed3649b42 Pin backend to the depth-one subagent loop
Why: Subagents now run a profile-scoped tool loop and stay out of the parent history. The Dev checkout has to build that backend.
Evidence: Backend 5051a06; go test ./... and make test passed in this checkout. The three agent-native gitlinks stay a34689c.
Impact: Only modules/backend moves. Squad, core, and the three agent-native pins stay put.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:13:33 +00:00
weichenandCursor dd80c6904d Record the P3a scope on the task card
Why: The subagent runtime task needs an explicit write scope and the two rulings before backend edits.
Evidence: make precheck verdict READY at bc8fef76bb. Required reading baseline.md and delivery.md section 1.
Impact: No code change. Kernel, squad, and core contracts stay as on main.
Refs: feature/agent-harness-p3
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 14:05:49 +00:00
weichen 09a439b33c Record the task card for feature-agent-harness-p3 2026-10-01 14:02:12 +00:00
weichen bc8fef76bb Merge pull request 'Close merged task cards (feature/card-close-20261001-140110Z)' (#139) from feature/card-close-20261001-140110Z into main
ci / test (push) Failing after 30s
2026-10-01 14:01:18 +00:00
weichen 81625a0ece Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 31s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-harness-p2.md(PR#138) — 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)
2026-10-01 14:01:10 +00:00
weichen 1939d50a7f Merge pull request 'Pin backend to the final-turn result checks' (#138) from feature/agent-harness-p2 into main
ci / test (push) Failing after 31s
2026-10-01 14:00:59 +00:00
weichen 7244f8c730 Record the sync checkpoint
ci / test (pull_request) Failing after 1m30s
2026-10-01 14:00:37 +00:00
weichenandCursor 9df951323a Record the harness pull requests on the task card
ci / test (pull_request) Failing after 1m58s
Why: The task card is the PR description, and it needs the Backend and Dev pull request links.
Evidence: Backend pull request 44 and Dev pull request 138 are open. Neither is merged.
Impact: Documentation only.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:55:46 +00:00
weichenandCursor 2af7e07164 Record the harness P2 verification on the task card
ci / test (pull_request) Failing after 1m57s
Why: Acceptance needs the precheck, task-sync, and make test output on the task card before the pull requests.
Evidence: task-sync sync_base=d02fa9c20a tested_head=f9d7bbe9f2. make test exited 0.
Impact: Documentation only. No further code change.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:55:18 +00:00
weichen 86dea13853 Record the sync checkpoint 2026-10-01 13:54:53 +00:00
weichenandCursor f9d7bbe9f2 Pin backend to the final-turn result checks
Why: Direct runs now check artifacts and run a fail-closed verifier before they stop. The Dev checkout has to build that backend.
Evidence: Backend a3ae1b9; go test ./... passed in that checkout. agent-native gitlinks stay a34689c.
Impact: Only modules/backend moves. Squad and the three agent-native pins stay put.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:54:24 +00:00
weichenandCursor 01ea7bdd95 Record the P2 scope on the task card
Why: The harness P2 task needs an explicit write scope before backend edits: direct-path checks and a fail-closed verifier, with PRs as the endpoint.
Evidence: make precheck verdict READY at d02fa9c20a; required reading baseline.md and delivery.md section 1.
Impact: No code change. Backend, squad, and kernel behavior stay as on main until the implementation commits.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:50:51 +00:00
weichen 110bf5fbb8 Record the task card for feature-agent-harness-p2 2026-10-01 13:45:07 +00:00
weichen d02fa9c20a Merge pull request 'Close merged task cards (feature/card-close-20261001-134217Z)' (#137) from feature/card-close-20261001-134217Z into main
ci / test (push) Failing after 1m31s
2026-10-01 13:43:58 +00:00
weichen 719b52a1f5 Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 2m13s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-harness-p1.md(PR#136) — 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)
2026-10-01 13:42:17 +00:00
weichen def110d784 Merge pull request 'Pin the harness turn loop across the three native checkouts' (#136) from feature/agent-harness-p1 into main
ci / test (push) Failing after 1m35s
2026-10-01 13:42:01 +00:00
weichen c5ab4c35e5 Record the sync checkpoint 2026-10-01 13:41:48 +00:00
weichenandCursor 1417fbef9d Record the harness pull request on the task card
ci / test (pull_request) Failing after 1m37s
Why: the task card is the main record, and review needs the Dev pull request link.
Evidence: Dev pull request 136 is open against main.
Impact: task card only.
Refs: feature/agent-harness-p1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:31:08 +00:00
weichenandCursor 87d509a763 Record the harness P1 verification on the task card
ci / test (pull_request) Failing after 1m34s
Why: acceptance needs the precheck, task-sync, and test evidence on the task card before review.
Evidence: task-sync reported already up to date at 701d4ab1e3; make test had already passed on b7631c7.
Impact: task card only.
Refs: feature/agent-harness-p1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:30:36 +00:00
weichen 150480f388 Record the sync checkpoint 2026-10-01 13:30:00 +00:00
weichenandCursor b7631c71a8 Pin the harness turn loop across the three native checkouts
Why: the direct chat path and both consumers must compile the same agent-native commit, or the new loop fields exist in only one replace target.
Evidence: make test passed (boundaries, core, backend, frontend 51, ui 71, agent-command). The three agent-native gitlinks are a34689c.
Impact: Dev pins deps/agent-native, deps/agent-squad, and modules/backend. Squad behavior stays on the zero-value kernel switches.
Refs: feature/agent-harness-p1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 13:29:55 +00:00
weichen 2d489a2780 Record the task card for feature-agent-harness-p1 2026-10-01 12:51:56 +00:00
weichen 701d4ab1e3 Merge pull request 'Close merged task cards (feature/card-close-20261001-124542Z)' (#135) from feature/card-close-20261001-124542Z into main
ci / test (push) Failing after 1m31s
2026-10-01 12:46:19 +00:00
weichen 3e3a038bf4 Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 1m36s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-harness-p0.md(PR#134) — 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)
2026-10-01 12:45:42 +00:00
weichen 46b9e53f75 Merge pull request 'Pin the harness proposal and native tool-call replay' (#134) from feature/agent-harness-p0 into main
ci / test (push) Failing after 1m41s
2026-10-01 12:43:41 +00:00
weichenandCursor 5e25719201 Record the harness pull request on the task card
ci / test (pull_request) Failing after 1m37s
Why: The task card is the main record, and it still said the Dev pull request was pending after the request was opened.
Evidence: Dev pull request 134 is open against main.
Impact: Task card text only. No code or gitlink change.
Refs: feature/agent-harness-p0
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 12:31:59 +00:00
weichen 89a10dc77c Record the sync checkpoint
ci / test (pull_request) Failing after 1m37s
2026-10-01 12:31:33 +00:00
weichenandCursor 897d12d6b5 Pin the harness proposal and native tool-call replay
Why: The model imitated flattened tool-call text and invented artifact ids. P0 stops that replay, and the proposal records the harness work that still sits in later phases.
Evidence: Documents PR 32 and Backend PR 42. Backend go test ./... passed. Dev make test passed (boundaries, core, backend, frontend 51, ui 71, agent-command).
Impact: Gitlinks move to feature/agent-harness-p0 on documents (a3f0b80) and backend (188c633). No other submodule changes. P1-P4 are not implemented.
Refs: feature/agent-harness-p0
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 12:31:27 +00:00
weichen 3c475dae11 Record the task card for feature-agent-harness-p0 2026-10-01 12:23:35 +00:00
weichen 342efd8e08 Archive the base extension roadmap task card
ci / test (push) Failing after 2m35s
Why: PR 132 is on main, but its merge subject is the pull request title, so the automatic card scan did not match it.

Evidence: db9c469047 is a merge of 94b7de3 into 26dfea7 and is origin/main.

Impact: The card moves to .task/archive. No code change.

Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/132
2026-10-01 10:49:11 +00:00
weichenandCursor de932eb7cd Correct the archived merge commit id
ci / test (pull_request) Failing after 1m35s
Why: The first archive note used a shortened id that does not match db9c469047.
Evidence: git rev-parse db9c469 is db9c469047.
Impact: The task card now cites the merge that is on origin/main.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/132
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:49:10 +00:00
weichenandCursor 9d901da5b8 Archive the base extension roadmap task card
Why: PR 132 is on main, but the merge subject is the pull request title, so the automatic card scan did not match it.
Evidence: db9c469 is a merge of 94b7de3 into 26dfea7 and is origin/main.
Impact: The card moves to .task/archive with status completed. No code or submodule change.
Refs: https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/132
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:48:41 +00:00
weichen db9c469047 Pin the extension roadmap and downstream spike
ci / test (push) Failing after 1m54s
Why: Downstream products need a published extension surface, contract checks, and a sample plugin that does not modify the base.

Evidence: Boundary lint passed. examples/downstream-rdm go test passed. Submodule pointers record the core, documents, backend, ui, and frontend commits.

Impact: Merge order is Core, Documents, UI, and Frontend, then Backend, then this PR. Do not squash the submodule PRs. make test runs the boundary lint first. Version tags and the remote downstream repository are not created.

Refs: .task/feature-base-extension-roadmap.md
2026-10-01 10:47:13 +00:00
weichenandCursor 94b7de3a9f Record the extension roadmap pull requests
ci / test (pull_request) Failing after 1m37s
Why: The task card needs the Dev PR and the submodule merge order once the branches are published.
Evidence: Pull requests Core 14, Documents 31, UI 25, Frontend 31, Backend 41, and Dev 132 are open.
Impact: Submodule pulls must be merged without squash before Dev, so the gitlinks stay reachable.
Refs: .task/feature-base-extension-roadmap.md
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:44:58 +00:00
weichenandCursor b8be5b2dd0 Move the sync checkpoint onto this task card
ci / test (pull_request) Failing after 1m56s
Why: task-sync appends its checkpoint to the first file in .task, which was another task's card.
Evidence: The 2026-10-01T10:39:24Z row now sits in feature-base-extension-roadmap.md. The other card matches its previous content.
Impact: The recorded sync base is origin/main 26dfea7ed6 and the tested head is the merge 6d496139b4.
Refs: .task/feature-base-extension-roadmap.md
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:40:08 +00:00
weichen 0a41d72632 Record the sync checkpoint 2026-10-01 10:39:24 +00:00
weichen 6d496139b4 Merge remote-tracking branch 'origin/main' into feature/base-extension-roadmap
Co-authored-by: Cursor <cursoragent@cursor.com>

# Conflicts:
#	modules/backend
2026-10-01 10:36:41 +00:00
weichenandCursor 09964e522b Pin the extension roadmap and downstream spike
Why: Downstream products need a published extension surface, contract checks, and a sample plugin that does not modify the base.
Evidence: scripts/lint-boundaries.sh printed boundaries ok. examples/downstream-rdm go test passed. Submodule pointers record the core, documents, backend, ui, and frontend commits for this roadmap.
Impact: make test runs the boundary lint first. make plugin-new scaffolds a declaration plugin. Version tags and remote downstream repositories are not created.
Refs: .task/feature-base-extension-roadmap.md
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:35:15 +00:00
weichen 26dfea7ed6 Pin the headless runtime and the orchestration platform
ci / test (push) Failing after 1m30s
2026-10-01 10:33:13 +00:00
weichenandCursor 7ec2b3c2b8 Pin the headless runtime and the orchestration platform
ci / test (pull_request) Failing after 1m38s
Why: Dev has to record the library commits the product now builds against.
Evidence: make test
Impact: runtime.entry stays direct. This commit only moves gitlinks.
Refs: feature/native-squad-full-upgrade
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 10:33:03 +00:00
weichen ea0382a28f Record the task card for feature-base-extension-roadmap 2026-10-01 10:10:35 +00:00
weichen a9bb112c91 Record the task card for feature-native-squad-full-upgrade 2026-10-01 10:05:00 +00:00
weichen f8fefa0f88 Pin the quality system and the squad entry
ci / test (push) Failing after 1m33s
2026-10-01 09:35:56 +00:00