Commit Graph

4 Commits

Author SHA1 Message Date
Tianyi Cui
7a35afa6fe Merge branch 'structured-output-subagent-seam' into worktree-dynamic-workflows
Restack on the carved-out foundation (#192), per review feedback on #170.
The seam files resolve to the carve-out's revision — its prompt-order
neutrality fix (backends no longer inject 'tools'; the structured runtime
gates its own capture-tool registration) restores the subagent tools to
master's front position, so every recorded fixture is re-recorded on the
stacked tree and the authored error-finish/cancel headers re-patched to the
stacked tool list ([subagent, subagent_fork, workflow, todo_write, ...]).
2026-07-06 23:43:13 +08:00
Tianyi Cui
ea58bdf1e8 Merge remote-tracking branch 'origin/master' into worktree-dynamic-workflows
Master's reconstructable-requests overhaul (#179) meets the workflow tool:
- subagent-inprocess structured-output nudge becomes a system-prompt section
  plus logged context (the injected-request waterfall shape is gone upstream)
- snapshot fixtures re-recorded on the merged tree so every request/header
  carries the workflow tool; authored error-finish/cancel headers patched to
  the merged tool list and system text
- architecture.md condensed back under its word ceiling; module graph regenerated
2026-07-06 22:28:57 +08:00
Tianyi Cui
7376346246 test: re-record snapshot goldens — every transcript gains its request/header event
One re-record after the header events landed: recorded scenarios
re-harvested against the live API; the three fs-writing fixtures are
relativized (this recording's model happened to emit absolute
file_path arguments, which only round-trip through replay when the
path is cwd-independent) and, with the two never-re-recorded authored
scenarios (error-finish, cancel), rewritten in the normalized
authored-fixture form the harness documents — each now carrying the
request/header snapshot the loop logs before its first dispatch.
Keyless replay verified green across all 35 scenarios.
2026-07-06 03:39:48 +08:00
Tianyi Cui
78d60366ec Record fork and mixed spawn+fork snapshot scenarios
The seed-boundary change made fork-child replay route correctly but shipped
with no recorded fork scenario — the seedLength slice was exercised only by
llm-replay unit tests and a persistence round-trip, never by the full-transcript
snapshot tier. Add two recorded scenarios that drive a real fork child through
it:

- subagent-fork: parent completes a turn, then forks one child (child fixture
  carries a non-zero seedLength, the boundary the replay slice consumes).
- subagent-mixed: parent completes a turn, then delegates once via spawn
  (seedLength 0) and once via fork (non-zero seedLength) in one transcript —
  the first scenario to drive two subagent backends at once, exercising both
  branches of the slice.

Both need a completed turn-1 so the fork seed is a non-empty completed-turn
prefix (a turn-1 fork seeds empty = spawn, which would not exercise the slice).
Removing the slice turns both scenarios red (the fork child receives the
parent's recorded chunks), proving the guard bites.

ACP (out-of-process) subagent replay remains a different shape, still tracked
as TODO(acp-subagent-replay).
2026-06-22 21:20:54 +08:00