The childToolOmissions comparison arms ran only through the examples
snapshot suites, which the unit coverage gate does not count. Add an
authored child-omission scenario to the synthetic replay suite: one
scripted child omits the declared tool (header pin minus the omission,
prompt pin skipped), one keeps the full set (pin and prompt compared
verbatim), restoring 100% branch coverage on suite.ts.
An omitted maxDepth meant unbounded recursion, and the shipped examples
shipped that default. maxDepth now defaults to 1; a numeric cap requires
the provider's depthLimit capability (the mount fails loud and points to
the explicit 'provider-managed' opt-out for out-of-process providers),
and a child AT the cap loses the delegating tool from its own schema via
the child toolFilter — prompt-face hiding on top of the execution-face
depth check. Examples pin maxDepth explicitly. The ACP snapshot harness
gains Scenario.childToolOmissions so a child session may legitimately
omit declared delegation tools from its pinned header and prompt;
affected subagent/workflow goldens are re-recorded.
A subagent child's recursion depth lived only in runtime AgentOptions,
so a persisted child came back from resume counted as top-level and
maxDepth stopped binding after every restart. Add
SessionHeader.delegationDepth, round-trip it through the JSONL and
SQLite backends (SQLite schema v5), restore it on agent-loop resume,
and write it when the in-process backends create a child. The seam now
owns the shared depth vocabulary (delegationDepthOf): the persisted
header is authoritative and monotone — runtime options may deepen it
but never lower it.
Adopt initiator-derived private loop and session plumbing while preserving post-step recovery and balanced synthetic tool-call results after cancellation.
Keep the architecture map within its existing budget while documenting ambient Agent ownership and explicit cross-boundary identities.
Combine agent initiator scoping and exact Cordis JSDoc inspection with post-step compaction and bounded request recovery.
Regenerate the Cordis and website API catalogs, and classify the recovery and compaction types required by the current catalog link-coverage gate.
Replace the process-wide adapter-failure WeakSet with a per-call scope bound to the exact AsyncIterable returned by LlmService.stream(). Give every call a unique wrapper so waterfall middleware can reuse an iterable without sharing provenance.
Move agent-loop recovery classification to the model-stream boundary. Only the final adapter behind that exact call can become an agent/request-error; nested llm/stream calls remain ordinary outer middleware failures while preserving the original Error.
Cover nested calls, reused middleware iterables, and end-to-end agent-loop recovery. Update the package and RFC contracts, bilingual pairing record, and generated API and catalog references.
Condense the app-bundle sentence after combining the current-master CLI wiring with the recovery architecture changes. The text still identifies the TUI, line-oriented, headless, and ACP front doors and their output contracts.
This restores the enforced architecture.md word ceiling without raising the budget or relocating an architecture-level seam fact.
Document every context-window path returned by mapStopReason: recognized provider error wording, successful stop usage beyond the resolved window, and zero-output length stops that fill the window.
This keeps the public return contract aligned with usage-based overflow classification without duplicating the provider-specific detection table owned by pi-ai.
Use the repository-mandated 回放 terminology for replayable pressure and replace the literal cancellation-owned rendering with idiomatic Chinese that preserves boundedness, cancellation authority, and monotonic retry behavior.
The corresponding English clauses remain accurate. Re-record the English and Chinese pair after checking the corrected text against the implemented recovery contract.
