Retarget the pruning feature onto the merged compaction foundation.
Adapt content-only tool-result rewrite validation to the session-owned surface manager, migrate the demo wiring to repl-agent, and refresh generated type, catalog, and website contracts while preserving pressure and overflow pruning behavior.
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.
path.resolve('') is the process cwd, so an empty configured cwd would
silently reintroduce the launch-directory fallback the parent-session
cwd resolution removed. Fail at plugin load with an actionable message
instead.
The ACP backend resolved an unset cwd to the harness process's launch
directory, so a delegated child ran — and announced its ACP session —
in the server's cwd instead of the delegating session's workspace.
Resolve the working directory explicitly: the config cwd override
(made absolute and validated at load), else the parent session
header's cwd (validated at start), failing loud before spawning when
neither exists.
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.
Dispatch RequestErrorDecision and CompactionTrigger through explicit discriminant switches. End each closed union with assertNever so new variants fail compilation instead of silently inheriting fail or pressure behavior.
This preserves the current retry, fail, pressure, and overflow semantics while aligning the new recovery seams with the repository closed-union contract.
Contain arbitrary plugin and runtime failures even when a thrown Proxy traps instanceof checks or its string coercion throws. Fall back to a stable diagnostic instead of letting executeCli reject outside its exit-code contract.
Route abort reasons through the same total renderer so cancellation cannot escape containment through an exotic reason value.
Add a focused regression that exercises both hostile inspection paths and verifies stdout remains empty, stderr remains labelled, and the CLI resolves with exit code 1.
Report context-disposal failure as an independent outcome even when argument, boot, task, or output handling has already produced a primary diagnostic.
Keep the primary error first, append the cleanup error, and retain the nonzero exit status so operators can see both the initiating failure and the possibility that teardown or persistence did not complete.
Add a regression that combines an invalid app composition with a failing disposer and asserts both ordered stderr lines.
Align the one-shot app with the shared agent-spine contract that landed on master after this branch began. Expose maxParallelToolCalls, dshHome, toolBash, and toolTasks through the Loader schema and route them with pickSpineConfig().
This restores deployment control over tool-call concurrency, the shared Harness home, background bash, and task_output wait bounds instead of silently retaining owner defaults.
Exercise all four fields through the composed runtime, document the package-level contract, and regenerate the config catalog from the owning interface.
Race Loader startup with the process abort signal so SIGINT and SIGTERM can settle the one-shot CLI even when initialization has not returned a Context.
If boot settles after cancellation, dispose the late context asynchronously instead of recreating the wait. Contain late boot rejection and report a late disposal failure on stderr.
Cover prompt interruption, late context disposal, late boot rejection, and cleanup failure with focused CLI regressions.
The slow-binding test used a 250 ms compute budget, which is below the instrumented worker startup cost seen intermittently in the four-worker Windows coverage job. That startup activity could exhaust the budget before the program settled into the awaited binding, making the timing assertion depend on runner load.
Use a one-second compute budget and a two-second binding delay. The awaited wall time still exceeds the busy-time allowance by a clear factor, so the test continues to prove that binding wait time is not charged while leaving enough headroom for worker initialization under coverage.
The existing /opt footer case reaches the ordinary outside-home return on POSIX, but Windows resolves it on the checkout drive while the user profile is on another drive. That exercises the cross-drive guard instead and leaves the same-volume fallback uncovered in Windows coverage.
Add the resolved parent of the home directory as a platform-neutral outside-home path. The case now covers the fallback on every host while retaining /opt to exercise the Windows cross-drive path, restoring per-file branch, statement, and line coverage without platform-specific expectations.
Tianyi Cui
imccyu
Yichen Jiang