weichenandCursor bead03374e Rewind tracked files and fall back before the first token ...

Why: workspace writes had no checkpoint, and a 5xx before any output stopped the turn instead of trying the next configured model.
Evidence: GOWORK=off go test ./internal/runtime/ ./internal/runmgr/ ./internal/tools/ ./internal/settings/ ./internal/server/ ./internal/app/
Impact: models.chat.fallbacks defaults to empty, so existing runs keep their model. Rewind restores only tracked writes and appends a system note. Usage records the model that served.
Refs: feature/durable-rewind
Co-authored-by: Cursor <cursoragent@cursor.com>

2026-10-03 17:31:56 +00:00

..

testdata

Check final replies before the direct run stops

2026-10-01 13:54:15 +00:00

agentwf.py

Run workflow scripts through a capped callback host

2026-10-01 16:18:59 +00:00

compose_test.go

Keep artifact ids and byte counts out of the final reply

2026-10-02 14:02:19 +00:00

compose.go

Keep artifact ids and byte counts out of the final reply

2026-10-02 14:02:19 +00:00

hostbridge.go

Route conversations through a squad entry when selected

2026-10-01 09:34:53 +00:00

llm_direct.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

llm_test.go

Compose a separate final reply after the work loop

2026-10-02 13:37:54 +00:00

llm_think_test.go

Return deliverable generation to the agent and fix the artifact-card root cause

2026-10-01 03:32:30 +00:00

llm_verify_test.go

Compose a separate final reply after the work loop

2026-10-02 13:37:54 +00:00

llm.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

mock.go

Add a mock workflow script and load the example plugin

2026-10-01 16:21:50 +00:00

model_test.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

model.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

review_test.go

Let subagents run in the background and be reviewed

2026-10-01 15:29:01 +00:00

review.go

Let subagents run in the background and be reviewed

2026-10-01 15:29:01 +00:00

runner.go

Unify artifact context backfill and facade cards (CF-A)

2026-09-30 18:40:50 +00:00

squad_runner_test.go

Route conversations through a squad entry when selected

2026-10-01 09:34:53 +00:00

squad_runner.go

Wire the squad native adapter instead of the core registration

2026-10-03 13:42:04 +00:00

sub_loop_test.go

Stream tool progress and drop hard agent limits

2026-10-02 02:17:02 +00:00

sub_loop.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

toolselect_test.go

Cap tool results by character and gate stale file writes

2026-10-03 16:21:02 +00:00

verify.go

Cap tool results by character and gate stale file writes

2026-10-03 16:21:02 +00:00

workflow_exec_test.go

Send step critic calls to the configured model

2026-10-01 16:28:12 +00:00

workflow_script_test.go

Run tool-started workflows with the script copy for that call

2026-10-01 16:36:54 +00:00

workflow_script.go

Run tool-started workflows with the script copy for that call

2026-10-01 16:36:54 +00:00

workflow.go

Stream tool progress and drop hard agent limits

2026-10-02 02:17:02 +00:00