The shipped subagent example could say a child was done while it was
still working, lose the useful part of process failures, and return a
normal-looking tool result when the delegated work had actually failed.
Single and chain output could also exceed the normal tool limit.
This also adds a dedicated regression suite covering progress state,
cancellation, process failures, output limits, cwd-based agent
selection, and persisted tool-result error state.
After this change:
- queued, running, completed, failed, and aborted work stay distinct
throughout the run;
- interrupting the parent run preserves partial child results, stops
queued work from starting, and escalates when a child ignores SIGTERM;
- signal exits, spawn failures, provider errors, stderr, and assistant
output remain visible instead of collapsing to `(no output)`;
- failed subagents become failed tool results, so the parent model can
react instead of treating them as successful calls;
- single and chain results stay within the normal 50 KB / 2,000-line
limit;
- project agents are selected and confirmed from each task's actual
working directory rather than the dispatcher's directory.
## Further potential improvements
These are useful follow-ups, but they are separate product and storage
decisions rather than part of the failure-handling fixes in this PR.
<details>
<summary>Potential follow-ups</summary>
### Keep persisted transcripts bounded
Subagent tool results persist the full child message history in
`details`, which can make parent session files large and slow to reload.
A follow-up could compact that history or spill it to disk.
### Define an aggregate parallel-output budget
Parallel mode still gives every task its own 50 KB budget. A follow-up
could keep every task represented while enforcing one overall
tool-result limit.
### Report child usage to the calling session
Per-child token and cost usage is visible in result cards but is not
added to the calling session's totals.
### Isolate malformed agent definitions
One malformed YAML agent can still break discovery for every valid agent
in the same directory.
### Limit subagent recursion
A nesting limit would prevent accidental process and paid-request
multiplication when subagents can invoke the subagent tool again.
* https://github.com/earendil-works/pi/issues/8195
### Add a configurable timeout
Unattended runs would benefit from a generous opt-in timeout for
children that never complete.
</details>
## Related issues
### Spawn failures lose their diagnostics
This directly addresses the reported case where a nonexistent child
working directory produces `(no output)` instead of the actual spawn
error. The regression suite includes that same reproduction.
* https://github.com/earendil-works/pi/issues/8129
### Persisted child history can bloat sessions
This PR intentionally keeps full child history in tool-result details,
so session compaction or spill-to-disk remains follow-up work rather
than something fixed here.
* https://github.com/earendil-works/pi/issues/7452
Deletes packages/client, packages/protocol (CBOR codec), packages/server, coding-agent's
src/experimental (except source-resolver.ts, which source runs still preload), src/cli/experimental,
src/client, the example plugin, and their tests. coding-agent no longer depends on @earendil-works/chord.
The installer lock drops esbuild, so its platform-package sanity check goes too.
Session workers now host a durable Harness over a per-session sqlite storage.
The server keeps each session in <sessionDir>/<id>/ with meta.json and
session.sqlite and never opens the storage itself. Workers hold retirement
while the Harness task graph has live tasks and resume interrupted work on
open.
Transcript serves the root conversation's durable view directly, Models
follows the conversation's agent document, and AgentController maps prompt,
steer, follow-up, queue cancellation, abort, and compaction onto the root
conversation, plus waitForPrompt. navigate, nextRun, and resume are dropped
(see experimental/services/README.md TODO). The durable TUI and the worker
share harness-setup.ts.
pi-server exports its own SessionMetadata and no longer depends on
pi-agent-core. Chord accepts readonly JSON types in service contracts without
walking them, which recursive JSON types like pi-ai's made too deep.
Deliver observed services as ordinary typed proxies, expose optional instance-key lookup, and rename the deferred multi-instance capability to ServiceSpawner.
Move service, replicated-state, facet host, and loader ownership into the standalone Chord package. Migrate consumers and leave runtime JSON enforcement to serializers.
Replace ad hoc service assembly with atomic local and remote facet generations. Gate service proxy access by lifecycle and move the experimental Session worker and TUI onto facets.
Keep the stable socket in an opaque detached coordinator while server processes own detached worker discovery and lifecycle. Remove the public drain RPC in favor of server replacement through coordinator routing.
When set to true, the skill is hidden from the system prompt, preventing
agentic invocation. Users can still invoke explicitly via /skill:name.
Also fixes pre-existing test bug where source expectation was wrong.
Fixes#927
- Add progress callbacks to PackageManager for TUI status during install/remove/update
- Add extension conflict detection (tools, commands, flags with same names)
- Accept raw GitHub/GitLab URLs without git: prefix
- Add tests for package-manager.ts and resource-loader.ts
- Add empty fixture directories for skills tests
Implement Agent Skills standard (https://agentskills.io/specification):
- Validate name (must match parent dir, lowercase, max 64 chars)
- Validate description (required, max 1024 chars)
- Warn on unknown frontmatter fields
- Warn on name collisions (keep first)
- Change prompt format to XML structure
- Remove {baseDir} placeholder (use relative paths)
- Add tests and update documentation
fixes#231
- Add CompactionEntry type with firstKeptEntryIndex
- Add loadSessionFromEntries() for compaction-aware loading
- Add compact() function that returns CompactionEntry
- Add token calculation and cut point detection
- Add tests with real session fixture and LLM integration
Still TODO: settings, /compact and /autocompact commands, auto-trigger in TUI, /branch rework
