Commit Graph
639 Commits
Author SHA1 Message Date
weichenandCursor 88d5787f29 Compare pin trees offline and archive finished task cards
ci / test (pull_request) Failing after 1m0s
Why: Merge commits share a tree with the pinned feature commit, the import ratchet downloaded modules during CI, and task sync wrote the checkpoint onto the wrong card.
Evidence: check-pins accepts 6c0f1e8 (same tree as Backend squad 8e987bf) and rejects empty-tree 8db069d; both objects stayed local. An empty GOMODCACHE run of lint-boundaries matches the cached go list, 14 pairs. bash -n scripts/task.sh.
Impact: make pin no longer checks out Backend nested core or agent-command, and a failing pin check does not fail the target. task sync writes the branch card or warns. precheck reports completed-but-unarchived cards and card-close branches older than 24 hours.
Refs: feature/agent-stack-r0-r1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 10:19:06 +00:00
weichenandCursor 0f8660bf40 Record the five unmerged pull request links
ci / test (pull_request) Failing after 1m29s
Why: the task card is the record of where review happens, and the links did not exist until the pull requests were opened.
Evidence: Gitea returned Intent #3, Native #8, Squad #7, Backend #50, and Dev #152. None were merged.
Impact: task card only.
Refs: R0 R1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 02:23:03 +00:00
weichenandCursor aa7089ab5f Record the stack repair evidence on the task card
ci / test (pull_request) Failing after 1m26s
Why: task-sync appended this branch's checkpoint to another open card, and the acceptance evidence belongs on this task.
Evidence: make test and make build exited 0; check-pins failed on the temporary squad pin 5cbac00 and passed after restore.
Impact: task cards only. The other card loses the misplaced sync row.
Refs: R0 R1
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 02:20:15 +00:00
weichen 314f798725 Record the sync checkpoint 2026-10-03 02:10:29 +00:00
weichenandCursor 978bf8bdae Check nested library pins and test the three agent libraries
Why: Dev could ship a combination whose nested gitlinks differed from the top-level pins, and make test never ran the three agent libraries.
Evidence: A go.work was measured and not adopted: workspace MVS selected newer golang.org/x crypto, exp, net, term, and text than backend with GOWORK=off. check-pins passes on the new pins and fails when backend's squad pin is 5cbac00.
Impact: make test adds pin checks and GOWORK=off vet/test for intent, native, and squad. make build still compiles inside backend; the pin check requires those gitlinks to match Dev.
Refs: R0
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 02:10:00 +00:00
weichenandCursor 33b545326e Record the R0 and R1 authorization on the task card
Why: the task card must state the allowed endpoint before library edits begin.
Evidence: plan authorizes five unmerged PRs and forbids merge, release, and history rewrite.
Impact: task card only; no code or gitlink change.
Refs: .task/feature-agent-stack-r0-r1.md
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 00:34:18 +00:00
weichen 44415a35c2 Record the task card for feature-agent-stack-r0-r1 2026-10-03 00:27:10 +00:00
weichen f4aa0348d7 Merge pull request 'Close merged task cards (feature/card-close-20261002-141819Z)' (#150) from feature/card-close-20261002-141819Z into main
ci / test (push) Failing after 1m34s
2026-10-02 14:18:39 +00:00
weichen 0b93af6b0b Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 7m1s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-final-reply-compose.md(PR#149) — 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)
2026-10-02 14:18:19 +00:00
weichen d825067a57 Merge pull request 'Pin the final-reply compose across core, backend, and UI' (#149) from feature/final-reply-compose into main
ci / test (push) Failing after 1m36s
2026-10-02 14:15:27 +00:00
weichenandCursor 4a72af56a9 Move the sync checkpoint onto its own task card
ci / test (pull_request) Failing after 1m34s
Why: task-sync appends the checkpoint to the first card by filename.
Evidence: make task-sync printed tested_head 5072554b09
Impact: The checkpoint stays on feature-final-reply-compose. The other card is unchanged.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 14:08:30 +00:00
weichen 14a3c66d8f Record the sync checkpoint 2026-10-02 14:07:55 +00:00
weichenandCursor 5072554b09 Record the browser replay of the composed reply
Why: The task card still said the meeting-minutes replay was pending.
Evidence: make test; browser run_102f0c09ff32
Impact: Documents the final reply, the check row, and the card appearing after the reply.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 14:07:40 +00:00
weichenandCursor deec291e18 Pin the compose step that drops internal refs
ci / test (pull_request) Failing after 1m38s
Why: The final reply still printed the artifact id and byte count.
Evidence: go test ./internal/runtime/ -run TestComposeReplyDropsInternalRefs
Impact: Backend gitlink moves to 46d5f7b.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 14:02:28 +00:00
weichenandCursor c118dc4cc2 Pin the compose step that hides model reasoning
ci / test (pull_request) Failing after 1m36s
Why: The first composed reply still included the model's think block and the internal quality score.
Evidence: go test ./internal/runtime/ -run TestCompose
Impact: Backend gitlink moves to 1512ae5. No other module changes.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 13:54:10 +00:00
weichenandCursor 544f71f23b Record final-reply verification on its own task card
ci / test (pull_request) Failing after 1m37s
Why: task-sync appends the checkpoint to the first card in .task, which belonged to another task.
Evidence: make test at tested_head c7932dd
Impact: The sync row and the test note sit on feature-final-reply-compose. The other card is unchanged from before this sync.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 13:45:34 +00:00
weichen f6e56910d2 Record the sync checkpoint 2026-10-02 13:43:37 +00:00
weichenandCursor c7932dd0a5 Pin the final-reply compose across core, backend, and UI
Why: The work timeline was being shown as the answer, and file cards appeared before the run had a finished reply.
Evidence: make test
Impact: Gitlinks move to the final-reply branches. The timeline spec now includes the finalizing phase and delays deliverable cards until the reply is done.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 13:43:10 +00:00
weichen 35eeed27ad Record the task card for feature-final-reply-compose 2026-10-02 13:23:29 +00:00
weichen ad17b78fda Merge pull request 'Close merged task cards (feature/card-close-20261002-050707Z)' (#148) from feature/card-close-20261002-050707Z into main
ci / test (push) Failing after 1m37s
2026-10-02 06:19:47 +00:00
weichen 4e313b51f9 Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 1m37s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-stream-display-overhaul.md(PR#147) — 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)
2026-10-02 05:07:07 +00:00
weichen bb4c167c71 Merge pull request 'Pin streaming display changes across the five modules' (#147) from feature/stream-display-overhaul into main
ci / test (push) Failing after 1m37s
2026-10-02 05:05:12 +00:00
weichen 20b5fd01a3 Record the sync checkpoint
ci / test (pull_request) Failing after 4m57s
2026-10-02 05:03:41 +00:00
weichenandCursor f43aec709d Record the streaming display pull request on the task card
ci / test (pull_request) Failing after 1m30s
Why: The task card is the review record, and it still pointed at a placeholder after the pull request existed.
Evidence: Dev pull request 147 is open.
Impact: The card status stays in progress until merge.
Refs: feature/stream-display-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 02:38:16 +00:00
weichen 42fe314b88 Record the sync checkpoint
ci / test (pull_request) Failing after 1m39s
2026-10-02 02:36:24 +00:00
weichenandCursor 83881c1320 Pin streaming display changes across the five modules
Why: Tool calls stayed invisible while arguments streamed, and a failed run hid the only reply inside the collapsed process block.
Evidence: make test in the worktree passed: boundaries, core, backend, frontend vitest 66, ui vitest 79, agent-command. Mock browser check showed the Chinese process summary, the reply outside the fold, a humanized error with 继续执行, and the back-to-bottom button.
Impact: Dev gitlinks move to the feature commits for core, agent-native, backend, ui, and frontend. DESIGN.md §9.6 describes individual tool blocks for exec, write, and delegate.
Refs: feature/stream-display-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 02:36:10 +00:00
weichen 087b328d48 Record the task card for feature-stream-display-overhaul 2026-10-02 02:03:12 +00:00
weichen 08ef71661d Merge pull request 'Close merged task cards (feature/card-close-20261002-010745Z)' (#146) from feature/card-close-20261002-010745Z into main
ci / test (push) Failing after 31s
2026-10-02 01:07:54 +00:00
weichen a313ed3e05 Close 2 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-p4.md(PR#144) feature-s4-shell-overhaul.md(PR#145) — 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)
2026-10-02 01:07:45 +00:00
weichen 31639b1e48 Merge pull request 'Advance UI and frontend for the S4 shell overhaul' (#145) from feature/s4-shell-overhaul into main
ci / test (push) Failing after 30s
2026-10-02 01:06:34 +00:00
weichenandCursor c591c63a9a Merge main and pin the combined submodule tips
ci / test (pull_request) Failing after 1m50s
Why: P4 is on main, and the shell pull request has to record UI and frontend commits that contain both the workflow contracts and the shell.
Evidence: submodule trees match the merged mains for core, backend, documents, ui, and frontend.
Impact: the shell branch now contains P4's example workflows and the combined pins.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-02 01:05:31 +00:00
weichen 3ba104c721 Merge pull request 'Add intent-to-workflow execution' (#144) from feature/agent-harness-p4 into main
ci / test (push) Failing after 30s
2026-10-02 01:04:03 +00:00
weichen 0a908b9aa9 Record the sync checkpoint
ci / test (pull_request) Failing after 1m34s
2026-10-01 23:48:16 +00:00
weichenandCursor 0f3ea6c8b5 Record the shell overhaul verification and pin the frontend fix
Why: The confirm card only folds after the client refetches the decision, so the parent pin has to include that frontend commit.
Evidence: make test passed; mock browser checked the shell, the pending filter, the blocked card, the folded row, and the molv theme.
Impact: task card records the result; modules/frontend moves to the refetch commit.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 23:48:09 +00:00
weichen 1f43457836 Record the sync checkpoint 2026-10-01 23:33:48 +00:00
weichenandCursor 6705d521f4 Advance UI and frontend for the S4 shell overhaul
Why: The molv theme and the rebuilt shell land together, so the design doc and the submodule pins stay in one change.
Evidence: UI npm test 79 passed; frontend tsc -b and npm test 61 passed.
Impact: DESIGN.md records the molv token table; modules/ui and modules/frontend point at the shell branches.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 23:33:42 +00:00
weichen 259c628f59 Record the task card for feature-s4-shell-overhaul 2026-10-01 22:59:58 +00:00
weichenandCursor cd984219da Record P4 test evidence and the live workflow check
ci / test (pull_request) Failing after 1m37s
Why: Acceptance needs the precheck, task-sync, and make test evidence on the card, plus what the three live conversations actually did.
Evidence: make test passed at 5f872f3. The sync row is in the table. The p4 service produced the slot question, one critic rejection, a confirmed plan, and the plugin script artifact.
Impact: Documentation only. The six pull requests stay unmerged.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:38:51 +00:00
weichen 0cdc2d2405 Record the sync checkpoint 2026-10-01 16:38:23 +00:00
weichenandCursor 5f872f3b7f Pin the script copy fix for tool-started workflows
Why: Dev should record the backend commit that runs a registered script from the launch of that call.
Evidence: go test ./internal/runtime/ -run TestRegisteredWorkflowUsesItsOwnScriptCopy passed.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:36:59 +00:00
weichenandCursor 9de01d69e6 Pin the planner and critic prompt fix
Why: Dev should record the backend commit that makes planning return JSON and makes the critic reject a missing line.
Evidence: go test ./internal/runtime/ ./internal/prompts/ passed on that commit.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:32:09 +00:00
weichenandCursor f125ebd68d Pin the critic model fix
Why: The step critic has to call the configured model, and Dev should record that backend commit.
Evidence: go test ./internal/runtime/ -run TestJudgeUsesConfiguredModel passed in the backend repo.
Impact: Only the backend pointer moves.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:28:18 +00:00
weichenandCursor 4836fee08f Require a marker so the example critic can reject once
Why: The live check needs the first draft to miss a line the critic can name, then the retry can add it.
Evidence: The prompt does not mention the marker. maxRetries stays 1.
Impact: demo.brief drafts are rejected until they contain 核对标记:P4.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:25:04 +00:00
weichenandCursor 54f5a33454 Pin the P4 workflow modules
Why: Dev has to record the Core, Backend, Frontend, UI, and Documents commits that implement intent-to-workflow.
Evidence: make test passed, including boundary lint, core, backend, frontend vitest, UI tsc and vitest, and agent-command.
Impact: agent-native stays at a34689c. The example plugin is already on this branch.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:24:37 +00:00
weichenandCursor ef590bd0c3 Add example brief and script workflows
Why: The example plugin needs a bound intent and a plugin-shipped script so the three P4 paths can be checked against a real plugin.
Evidence: TestRepoExamplePluginLoads accepts the plugin, asks 主题是什么?, and keeps the topic slot.
Impact: demo.brief starts the five-step workflow. demo.script stays unbound and needs runtime.workflowScripts.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 16:22:14 +00:00
weichenandCursor 191d2de809 Record P4 authorization and workflow rulings
Why: The task card is the authorization record for intent-to-workflow work, and the routing, retry, and script rulings have to be fixed before code changes.
Evidence: precheck READY at 959179f88f; core/baseline.md and workflows/delivery.md section 1 were read.
Impact: No product code. Six pull requests are the delivery end, and merging them is not authorized.
Refs: feature/agent-harness-p4
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-01 15:54:37 +00:00
weichen 723c2508a2 Record the task card for feature-agent-harness-p4 2026-10-01 15:53:54 +00:00
weichen 959179f88f Merge pull request 'Close merged task cards (feature/card-close-20261001-155214Z)' (#143) from feature/card-close-20261001-155214Z into main
ci / test (push) Failing after 31s
2026-10-01 15:52:43 +00:00
weichen e7eef7d869 Close 1 merged task card(s) and archive them
ci / test (pull_request) Failing after 1m31s
Why: branches merged into main had left their task cards open; backfill status and archive to prevent bookkeeping debt.
Evidence: feature-agent-harness-p3b.md(PR#142) — 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 15:52:14 +00:00
weichen ec4614322e Merge pull request 'Pin P3b background subagents, review, and profile overrides' (#142) from feature/agent-harness-p3b into main
ci / test (push) Failing after 1m34s
2026-10-01 15:51:57 +00:00