Commit Graph

3 Commits

Author SHA1 Message Date
Patrick Buckley 03f82521d9 fix(cancel): close workstream self-cancel gaps from the completeness review
Follow-up to the cancellation review — harden how cancel interacts with a
workstream's OWN turn and tools, not just its children and agents.

- wait_for_workstream: the wait loop holds no cancel handle and blocks on the
  child-event bus, so a cancelled coordinator parked in a wait stayed pinned
  for up to WAIT_MAX_TIMEOUT (600s). Add a cooperative check to the ~2s
  progress heartbeat — it raises GenerationCancelled, which propagates out of
  the otherwise cancel-blind wait (~2s abort).
- spawn_batch: stop creating the rest of the children once cancel is observed;
  already-spawned children stay recorded (they are live, durably parent-linked
  workstreams), the remainder are marked not-spawned.
- session worker: only clear _worker_running if this thread is still the
  current worker, so a late-finishing abandoned worker (force-cancel) can't
  clobber a live successor's flag — which would let a third send spawn a
  duplicate worker on the same session.
- bash silent-cancel: a SIGKILL'd silent command now records outcome-UNKNOWN
  (is_error, partial output kept) instead of a clean "Cancelled by user." that
  read as a successful empty result on replay.
- wire-repair: the last-resort orphan disposition now reads outcome-UNKNOWN,
  matching the cooperative-cancel message (unknown, never none).

Deferred: MCP / web_fetch / web_search remain uninterruptible mid-call,
bounded by tool_timeout; only bash is truly preemptible.
2026-06-26 03:28:06 -07:00
Patrick Buckley 4ebaeb8f15 test(providers): add native-orphan wire fixture (verbatim-replay baseline)
Freeze the wire payload for an unanswered native tool_use whose id is
mirrored top-level in tool_calls (the P1 invariant).  This pins the
verbatim-replay orphan path each provider repairs today — Anthropic via
the provider_content tool_use synthesis, the OpenAI-compatible lane via
sanitize_messages — as the baseline the repair-unification change is
proven byte-identical against.
2026-06-04 11:03:13 -07:00
Patrick Buckley c9311e32e4 test(providers): freeze per-provider wire payloads as a refactor baseline
Captures the exact request kwargs each provider hands to its SDK seam (Anthropic
messages.stream, OpenAI chat/responses create, Google OpenAI-compat) for a
representative set of trajectories, asserted against committed goldens. This is the
behavior-equivalence net the canonical-trajectory wire-shape refactor is proven
against. Regenerate the baseline with UPDATE_WIRE_GOLDENS=1.
2026-06-04 11:03:13 -07:00