- Added `parentToolCallId` and `index` fields to subagent session records and propagated them from task lifecycle and progress events.
- Reworked subagent ordering to sort by parent-group order, spawn index, and stable creation order so out-of-order updates no longer reshuffled active HUD rows.
- Updated task execution to pass spawn indices through sync and async paths, switched the `tool.task` icon to Octicons tasklist, and added a registry test for out-of-order progress ordering.
- Added an anchored Subagents HUD renderer that formats active subagent sessions as `Id: description` rows.
- Integrated a new interactive-mode container and observer-driven render path so the HUD updates with session events and clears when no subagents are active.
- Exported `formatTaskId` for shared HUD formatting and added tests covering active-only filtering, fallback task/progress text, and line truncation.
- Updated task call and result headers to use the dispatch glyph during running async calls instead of spinner-style states.
- Switched running and pending agent rows to a static done-dot marker and reused the dot with foreground color settling when rows complete.
- Updated task rendering tests to validate the new glyphs and ensure running/pending rows do not emit spinner or pending symbols.
- Detached async task progress rows stopped running a redraw driver and task progress rendering switched running/pending rows to static task-icon text.
- Background task snapshots were frozen once blocks left the transcript live region, preventing later partial snapshots from repainting commit-eligible rows.
- Updated task-progress and detached-background-task tests to validate static task rows and the new freeze behavior.
Reorders sections in the streaming call preview to match `renderResult` and the
schema's field order. This prevents visual jumps when the preview transitions
to a result and ensures append-only growth of streamed content.
Additionally, omits the agent-list divider when no agent rows are present.
- Updated TaskTool to skip `session.asyncJobManager` and run `task` spawns inline whenever `async.enabled` is false.
- Set `async.enabled` default to `true` and updated task prompts/settings text to reflect async-versus-sync behavior.
- Adjusted task batching tests to cover both async background execution and synchronous batched execution when async is disabled.
- Replaced task-simple-mode with a `task.batch` setting enabled by default.
- Updated task schema to use batch `{agent, context, tasks[]}` payloads.
- Migrated task execution to spawn one async job per task and merge outputs.
- Removed per-call schema passing while preserving legacy flat task calls.
- Removed `resume` from task params and schema, requiring agent and assignment inputs.
- Dropped resume continuation paths in task execution and call rendering, always spawning a new agent.
- Removed the `irc.enabled` setting and computed IRC availability by task-depth rules.
- Updated task follow-up guidance to use IRC messaging/history links instead of `task(resume:)`.
The task tool now takes a single { agent, assignment, description, ... } and always runs the subagent in the background — the batch tasks[] array and shared context parameter are gone. Fan-out is parallel task calls; shared background flows through a '/Users/can/.omp/agent/sessions/-Projects-.tree-pi-commit/2026-06-10T15-36-32-782Z_019eb22d-970e-7000-8964-72c98becf3e8/local' file referenced in each assignment.\n\nIntroduces a persistent subagent lifecycle: finished subagents stay live as idle, the lifecycle manager parks them to disk after task.agentIdleTtlMs (default 7 minutes; 0 keeps them live until exit), and they revive automatically when prompted from the Agent Hub, messaged on IRC, or resumed via task. New task(resume: "<id>") revives an idle or parked subagent and runs a follow-up assignment in its existing session.\n\nAdds soft request budgets (explore/quick_task 40, others 90, configurable via task.softRequestBudget, 0 disables): crossing the budget injects a one-time wrap-up steer into the child; crossing 1.5× aborts the run gracefully. Cancelled/aborted subagent salvage replaces the old (no output) with the child's last activity snippet plus request/token stats; SingleResult tracks a per-child requests counter (assistant message_end events) used to sort agent lists in runtime-ascending order in both the live progress view (finished agents above pending/running) and the finalized result view, so rows no longer reshuffle on finalize. Adds a task gallery fixture variant for the resume path (renderer key separated from fixture key).\n\nAll task tests are reshaped around the single-call contract; tests for the discarded shared-context flow are removed, and new task-guards/task-resume/task-schema tests pin the new contract surface.
- Added a stable progress-ordering helper that moved pending and running agents below completed and failed ones.
- Applied this ordering to top-level and nested live task-progress rendering so finished entries render first.
- Added a renderer test and changelog note covering the finished-before-unfinished progress ordering.
- Fixed help rendering so `--help` no longer triggers unrelated command loaders.
- Fixed startup span logging to emit markers only with PI_DEBUG_STARTUP set.
- Fixed logger startup trace behavior for `:start`, `:done`, and `:fail` phases.
- Fixed prompt template processing with cached raw-template compilation and safer formatting.
- Optimized symbol and tag parsing in prompt templates via manual parsers.
Stopped task-agent discovery from loading direct .claude/agents roots, while preserving OMP-native .omp agents and Claude marketplace plugin agents. Added a focused regression test for user and project Claude Code custom agent files.\n\nFixes #2209
Same shape of bug the reviewer flagged for custom tools: forwarding
`LoadExtensionsResult` from parent to subagent reused Extension instances
whose factories closed over the parent's `ExtensionAPI` — cwd, eventBus,
and runtime all pointed at the parent. Any tool/handler/command that
referenced `api.exec()`, `api.events`, or `api.runtime` still acted on the
parent session/worktree from inside an isolated subagent.
Forward only the path list; each session rebuilds extensions through
`loadExtensions` so factories see the right `ExtensionAPI`.
- `extensibility/extensions/loader.ts`: extract `discoverExtensionPaths`
(FS scan only) from `discoverAndLoadExtensions`. The combined helper now
composes the two. New export added to the package barrel.
- `sdk.ts`:
- Add `discoverSessionExtensionPaths()` (the `disableExtensionDiscovery`-aware
path-only counterpart of `loadSessionExtensions`).
- Add `preloadedExtensionPaths?: string[]` to `CreateAgentSessionOptions`.
Three loader branches: `preloadedExtensions` (CLI same-process reuse,
still shallow-cloned), `preloadedExtensionPaths` (subagent: skip scan,
reload locally), or full discovery.
- Document `preloadedExtensions` as same-process-only; subagent
forwarding MUST use `preloadedExtensionPaths`.
- `tools/index.ts`: `ToolSession.extensionsResult` → `extensionPaths:
string[]` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `extensionPaths`. Drop
the forward for the isolated `runSubprocess` branch — worktree cwd ≠
parent cwd, so the subagent re-discovers extensions against its own
tree.
- New `test/sdk-extensions-per-session-binding.test.ts` pins the contract:
two `loadExtensions` calls on the same path with different `cwd` and
different `EventBus` instances yield distinct Extension + runtime
objects whose factories close over the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and comment context.
Refs PR review on #2193
Reviewer flagged that forwarding `LoadedCustomTool[]` from a parent session
to a subagent reused tool instances whose factories had closed over the
parent's `CustomToolAPI` — `cwd`, `exec`, `pushPendingAction`, and `ui` all
pointed at the parent. In isolated tasks the tool would `exec` against the
parent worktree and queue pending actions on the parent session.
Forward only the path list; let each session rebuild tools through
`loadCustomTools` so factories see the right `CustomToolAPI`.
- `extensibility/custom-tools/loader.ts`: extract `discoverCustomToolPaths`
(FS scan only) from `discoverAndLoadCustomTools`; export
`ToolPathWithSource`. The combined helper is now `discoverCustomToolPaths`
+ `loadCustomTools`.
- `sdk.ts`: replace `preloadedCustomTools` (`LoadedCustomTool[]`) with
`preloadedCustomToolPaths` (`ToolPathWithSource[]`). The custom-tools
block runs `loadCustomTools` unconditionally; only the path scan is
skipped when the caller pre-discovered it.
- `tools/index.ts`: `ToolSession.loadedCustomTools` →
`ToolSession.customToolPaths` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `customToolPaths`.
Drop the forward for isolated subagents — the worktree shifts `cwd`, so
the subagent re-discovers tools against its own working tree.
- New `test/sdk-custom-tools-per-session-binding.test.ts` pins the contract:
two `loadCustomTools` calls on the same path with different `cwd` and
different `pushPendingAction` callbacks yield distinct tool instances
whose factories see the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and added a `ToolPathWithSource` fixture.
Refs PR review on #2193
Each `runSubprocess` call re-ran `loadCapability<Rule>()`,
`loadSessionExtensions()`, and `discoverAndLoadCustomTools()` because
`ExecutorOptions` and the `createAgentSession()` call inside the executor
omitted three pass-through fields the parent had already paid for. The
already-correct paths (skills, context files, workspace tree, MCP manager)
showed the intended pattern.
- Cache `rules`, `extensionsResult`, and `loadedCustomTools` on the
parent's `ToolSession`.
- Add `rules` / `preloadedExtensions` / `preloadedCustomTools` to
`ExecutorOptions`; forward them from both `runSubprocess` call sites
in `task/index.ts` and into the executor's `createAgentSession()`.
- Add `preloadedCustomTools` to `CreateAgentSessionOptions` and skip
`discoverAndLoadCustomTools()` when it is supplied.
- Shallow-clone `extensionsResult.extensions` when reusing
`preloadedExtensions`, so the per-session autoresearch + custom-tools
inline wrappers never leak back into the caller's array.
Fixes#2190
- Updated `renderResult` to inspect `isError` on detail-less task results and render an error state with the error glyph.
- Replaced success/completed status symbols in agent, review, and result outputs with the shared `status.done` symbol.
- Added tests for detail-less task rendering to verify failed results show error and successful results show the done glyph.
- Added status.done and tool.* symbols to theme mappings and presets.
- Replaced generic success glyphs with contextual +/-, tool icons, and warnings.
- Mapped tool/task/job completions to status.done or status.enabled with icon overrides.
- Triggered runtime provider refresh after extension registration and warned on failure.
- Updated `convertToLlm` logic to emit `developer` role for custom, hook, and file-mention inputs.
- Simplified OpenAI compact output filtering to retain only `user` and `assistant` messages, removing legacy `system-reminder` pattern checks.
- Adjusted compaction and session tests to match the new developer-role mapping and expected compacted content.
- Propagated `schemaOverridden` from `YieldTool` into executor `YieldItem` metadata.
- Bypassed schema validation on override or schema-builder errors and kept payload output with success exit.
- Emitted `SUBAGENT_WARNING_SCHEMA_OVERRIDDEN` so accepted override results no longer surface as `schema_violation`.
- Reworked running-task rendering so shimmer animation is applied to descriptions instead of IDs.
- Added accent coloring for the separator and description text to keep the status line formatting consistent.
`finalizeSubprocessOutput` always spliced collected `report_finding`
entries onto a top-level `findings` array regardless of the active output
schema. A caller-supplied schema with `additionalProperties: false` and
no `findings` property would accept the raw payload in-tool (via the
`yield` validator, which only sees the pre-injection data) but then fail
post-mortem validation — emitting `schema_violation: findings: must not
be present` and propagating as a fatal `RuntimeError` through
`agent-bridge.ts` and the eval Python/JS preludes, collapsing the entire
workflow cell along with any prior successful subagent work.
`normalizeCompleteData` now takes the resolved validator and only
performs the injection when the augmented candidate validates. When the
schema rejects it, the raw payload is returned instead — which the in-
tool yield validator already accepted, so the lockstep guarantee
documented at the top of `output-schema-validator.ts` is honored.
Findings remain visible via the agent progress stream and JSONL
artifact, so no information is dropped when injection is suppressed.
Both finalize call paths (yield-success and no-yield fallback) now share
the single validator build instead of constructing it twice, and the
yield-path schema_violation branch is now reached only via the
explicit malformed-schema check, never via spurious findings rejection.
Fixes#2070
- Reduced shimmer-driven UI animations and borders to a 30fps cadence.
- Collapsed consecutive read tool calls into one finalized transcript block.
- Tracked visible assistant content to finalize and reset read groups correctly.
- Updated running task rows to static bullet markers with shimmer-only subagent labels.
- Updated task call and result rendering to process shared context with the Markdown renderer, so context sections are now displayed with proper Markdown formatting.
- Stopped shimmer animation on pending bash/eval/task blocks once async state is `running`, preventing the committed frame from freezing a transient dark border segment.
- Adjusted rule path display to fall back to a root-relative path when cwd-relative resolution is unavailable.
- Extended `OutputBlock` section metadata with an optional `separator` flag and included it in cache hashing.
- Updated output block rendering to emit an unlabeled section divider when the separator flag is enabled.
- Marked task and result render paths to request separators for non-context content sections to improve output clarity.
- Added `/tan` slash command registration and interactive handling.
- Added TanCommandController validation and async task scheduling for `/tan` dispatch.
- Added session cloning that suppresses breadcrumbs, copies artifacts, and handles abort cleanup.
- Added `promptCacheKey` support in Agent and inherited `providerPromptCacheKey` in session creation.
- Rendered shared `# Goal`/`# Constraints` brief in result frame via buildContextSection helper.
- Undid per-field double-encoding so brief reads cleanly from raw result args.
- Removed header spinner since per-agent body lines already animate.
- Wrapped run summary in bracket glyphs to match bash tool footer.
- Enabled call/result merging by setting mergeCallAndResult on TaskTool.
- Reworked task item lines into bullet lists and removed tree-style prefixes.
- Rendered task calls as framed blocks with isolated headers and pending status metadata.
- Changed result previews to hide task titles and `Tasks` headings when a result is present.
- Used `||` so empty stderr falls through to abortReason in agent bridge.
- Preferred assistant errorMessage over "Cancelled by caller" on internal aborts.
- Forced `maxRuntimeMs: 0` for eval subagents via ExecutorOptions override.
renderAgentResult and the live-progress sibling cast
extractedToolData?.yield to Array<{ data }> and called ?.map without
checking the actual runtime shape. Optional chaining only short-circuits
on null/undefined, so any stray non-array value (a single yield object
landing in the slot) made .map undefined and threw
TypeError: completeData?.map is not a function — taking down every
`review` task render.
Both sites now route through a new normalizeYieldData helper (next to
normalizeReportFindings) that returns an array of yield records: it
preserves arrays unchanged, wraps a single object as a 1-element array
so the verdict still renders, and drops primitives. Added a regression
test exercising the result branch, the progress branch, the primitive
fall-through, and the canonical array shape — all of the failing-branch
ones reproduce the crash on the pre-fix renderer.
Fixes#1987
Previously `getRepoRoot` and `ensureAutoresearchBranch` only consulted `jj.isPureJjRepo` after `git.repo.root` returned null. For a jj workspace nested under an unrelated outer Git checkout, `git.repo.root` walks up and finds the outer .git, so the pure-jj branch never fired and isolation/autoresearch silently mutated the surrounding Git tree behind jj's back.
Both call sites now run the pure-jj guard first, rejecting at the jj workspace's own root regardless of any surrounding Git checkout. Added integration tests for the nested case on both surfaces.
Refs #1935
Worktree setup and autoresearch Git prep silently misbehaved in pure Jujutsu workspaces (`.jj/repo/` present, no colocated `.git/`):
- `task/worktree.ts#getRepoRoot` threw a generic "Git repository not found for isolated task execution.", giving a jj user no hint about what was wrong.
- `autoresearch/git.ts#ensureAutoresearchBranch` returned a soft "Not in a git repository" warning, letting `/autoresearch` proceed with no branch isolation, baseline reset, or auto-commits.
Both paths now detect a pure jj workspace via a new `jj.isPureJjRepo` helper and surface an actionable Jujutsu-specific error pointing at `jj git init --colocate`. Colocated jj-git workspaces (both `.jj/` and `.git/` at the same root) and plain Git checkouts behave exactly as before.
Fixes#1935
- Skipped count/concurrency normalization when --bench is set.
- Errored when no OAuth accounts resolve for the provider.
- Updated flag docs to run one request per OAuth account.
Per PR review on #1926: a secondary in-process top-level createAgentSession() that exposes bash/task/job tools would still call AsyncJobManager.instance() at execute time, register on the primary's manager, and have the primary's onJobComplete enqueue results into the primary's yieldQueue — corrupting the owning session's conversation.
ToolSession now carries an asyncJobManager reference scoped to its session: the constructed manager for top-level sessions, the inherited singleton for subagents (so their bash/task completions still flow into the spawning conversation as before), and undefined for secondary in-process top-level sessions that found a singleton already installed. bash, task, and job tools resolve the manager through ToolSession instead of the process-global singleton, so a secondary session whose tools attempt async work fails fast with the standard "Async job manager unavailable" error instead of contaminating the primary.
When `async.enabled` is true but `AsyncJobManager.instance()` returns
`undefined` (orphaned-session state, host that never wired one up, etc.),
the `task` tool was returning a hard error and was unusable for the rest
of the session — even though the existing sync codepath (`#executeSync`,
which still parallelizes via `mapWithConcurrencyLimit`) was right there.
Fall back to `#executeSync` instead and emit a `logger.warn` so the
missing-manager state stays diagnosable. Background/job-poll semantics
are lost in this degraded mode, but the tool keeps working.
Fixes#1922
- Added `loadOverallPlanReference` to resolve a session plan reference from local storage and skip empty or missing files.
- Updated task execution to read the active plan reference (except in plan mode) and pass it into each spawned subagent.
- Extended the subagent system prompt and session SDK/tools plumbing so subagents receive and render the approved plan path and contents.
can1357