Pin the harness proposal and native tool-call replay #134

Merged
weichen merged 4 commits from feature/agent-harness-p0 into main 2026-10-01 12:43:41 +00:00
Owner

Summary

  • Pin the harness proposal (Documents PR 32) and the P0 replay/gate fix (Backend PR 42).
  • Assistant history is replayed as native tool messages. A false deliverable claim is corrected twice, then replaced with a notice.

Test plan

  • make precheck verdict READY at 342efd8e08
  • make task-sync (already up to date, checkpoint recorded)
  • make test: boundaries, core, backend, frontend vitest 51, ui vitest 71, agent-command
  • Owner merges Documents PR 32 and Backend PR 42 before or with this pin
## Summary - Pin the harness proposal (Documents PR 32) and the P0 replay/gate fix (Backend PR 42). - Assistant history is replayed as native tool messages. A false deliverable claim is corrected twice, then replaced with a notice. ## Test plan - [x] make precheck verdict READY at 342efd8e08 - [x] make task-sync (already up to date, checkpoint recorded) - [x] make test: boundaries, core, backend, frontend vitest 51, ui vitest 71, agent-command - [ ] Owner merges Documents PR 32 and Backend PR 42 before or with this pin
weichen added 3 commits 2026-10-01 12:31:45 +00:00
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>
Record the sync checkpoint
ci / test (pull_request) Failing after 1m37s
89a10dc77c
weichen added 1 commit 2026-10-01 12:32:00 +00:00
Record the harness pull request on the task card
ci / test (pull_request) Failing after 1m37s
5e25719201
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>
weichen merged commit 46b9e53f75 into main 2026-10-01 12:43:41 +00:00
Sign in to join this conversation.
No Reviewers
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: weichen/Agent-System-Dev#134