- Migrated global service tier settings to a per-model-family architecture (OpenAI, Anthropic, Google).
- Implemented `ServiceTierByFamily` mapping to allow independent configuration and resolution per provider.
- Added automatic migration logic for legacy service tier and fast-mode application settings.
- Updated telemetry, session management, and task execution to support provider-specific tier resolution.
- Introduced `serviceTierSubagent` and `serviceTierAdvisor` settings to allow independent service tier control for subagents and the advisor model.
- Enabled `"inherit"` mode for these settings, allowing subagents and the advisor to track the main session's live effective service tier, including dynamic toggles like `/fast`.
- Added a resolution layer to ensure service tier propagation from parent sessions to spawned task agents and evaluators.
The eval agent() helper used `agent_type`/`return_handle` (snake_case) in
Python/Ruby/Julia and `agentType`/`returnHandle` (camelCase) in JS, forcing
the prelude docs to repeat every option twice ("JS same but camelcased").
Both are now single lowercase words identical across all four runtimes, and
`agent` matches the `task` tool's existing agent-selection parameter.
- Renamed across py/js/rb/jl preludes (signatures, forwarding, docstrings).
- Renamed the `__agent__` bridge wire protocol + `EvalAgentArgs` (`agentType`
→ `agent`, `returnHandle` → `handle`) so no prelude-side remap is needed.
- Updated prompt docs (workflow-notice.md, tools/eval.md), repo docs
(docs/tools/eval.md, docs/python-repl.md), and all bridge/prelude tests.
- CHANGELOG: Breaking Changes entry under [Unreleased].
Two Codex P2 findings landed against 978d2a76d0 that were not in the previously delivered review event:
1) prepareIsolationContext() (which runs captureBaseline → walks nested repos and untracked diffs) was running OUTSIDE withBridgeTimeoutPause; on dirty/large repos the baseline walk can exceed the eval idle timeout while the runtime is blocked. Moved the prep call into the pause closure so the watchdog is suspended for the whole bridge call from prep through cleanup.
2) applyNestedPatches() swallowed git stash pop failures with only a logger.warn, so a stash-pop conflict after a successful agent commit was invisible to the workflow. Changed the helper to return Promise<string[]> of warnings; applyEligibleNestedPatches now wraps them in a <system-notification> appended to the merge summary so the caller actually sees the partial-success case.
Added regression tests:
- bridge: prepare fires after timeout-pause and before timeout-resume.
- runner: applyEligibleNestedPatches surfaces stash-restore warnings as a system-notification.
- worktree (real git): a pre-existing dirty edit on the same file the agent patches causes stash pop to conflict; the helper returns a warning naming the nested repo and the stash entry is preserved for manual recovery.
Fixes#3196
TaskTool and the eval agent() bridge each held a private copy of the nested-repo patch eligibility gate and the AI commit-message factory; isolation policy could drift between the two callers.
Moved both into task/isolation-runner.ts:
- applyEligibleNestedPatches(opts) — single nested-patch gate (skip on patch-mode parent failure, skip on branch-mode unmerged root, fail non-fatally with a system-notification suffix).
- makeIsolationCommitMessage(session) — single factory that yields the AI commit-message callback when task.isolation.commits === "ai" and a model registry is wired, undefined otherwise.
Both call sites now invoke the helpers; behavior is unchanged. Removed the now-dead generateCommitMessage/applyNestedPatches imports from each caller.
Added unit tests for the new helper covering the skip-on-patch-failure, skip-on-unmerged-branch, success, and failure-suffix paths.
Fixes#3196
Previously withBridgeTimeoutPause only wrapped the subagent subprocess; mergeIsolatedChanges, applyNestedPatches, nested commit-message generation, and artifact cleanup ran with the eval watchdog re-armed. A cherry-pick or large patch apply could trip the cell timeout and abort successful post-processing.
Moved the entire bridge work (subprocess + merge + nested apply + cleanup + usage recording) inside one withBridgeTimeoutPause block. The pause helper still resumes via its finally on success and on throw, so existing failure paths are unchanged.
Added a regression that captures the emitted op order and asserts merge fires after timeout-pause and before timeout-resume.
Fixes#3196
Per maintainer ruling on #3196, eval agent() now defaults to non-isolated regardless of task.isolation.mode, mirroring the task tool. isolated=true is the only way to turn it on; isolated=true while task.isolation.mode === "none" still throws the same clear error.
Updated tests, workflow-notice.md, and Python agent() docstring to reflect the strict opt-in contract. Existing isolation tests now pass isolated:true explicitly; the inherit-from-settings assertion is replaced with a default-off + isolated=true opt-in regression.
Fixes#3196
When an isolated apply fails the bridge throws a ToolError and never returns details, so the nested-patch payload that previously lived in details.nestedPatches was unrecoverable after the isolation worktree was torn down.
The bridge now writes each captured nested patch to a file under the per-call artifacts dir (e.g. <agentId>.nested-<index>-<slug>.patch) before throwing and includes the resolved paths in the error message so the caller can apply them manually.
Added a regression test verifying the persisted file exists with the original patch contents and that the path is surfaced in the thrown error.
Fixes#3196
A failed isolated apply (changesApplied === false) previously only set details.isolationSummary and returned the subagent text. Schema-backed agent() calls then parsed the JSON and returned the object, so workflows saw a successful structured result while none of the edits had landed.
Throw a ToolError when mergeIsolatedChanges reports a failed apply, with the merge summary plus a recovery hint pointing at the preserved patch/branch/nested artifacts so the caller can apply manually.
Added regression tests for the schema and non-schema apply-failure paths.
Fixes#3196
Branch-mode isolation can capture nested repository changes without creating a root branch. Eval agent() with apply=false previously treated that shape as no captured changes and returned no recoverable nested patch payload after the isolation worktree was removed.
Expose captured nested patches in EvalAgentResult details and copy them onto JS/Python returnHandle nodes (nestedPatches / nested_patches). Document the return_handle escape hatch and add regression coverage for branch-mode nested-only apply=false runs.
Fixes#3196
Eval preludes now forward returnHandle to the bridge so no-session eval runs can preserve the temp artifacts backing returned agent:// handles. The bridge keeps those temporary artifact directories whenever returnHandle is requested, including non-isolated runs and successful isolated applies.
Branch-mode isolation now treats nested-only changes as merge-eligible even when no root branch was produced, letting callers apply nested patches instead of dropping them when the root repo had no diff.
Added regression coverage for returnHandle artifact preservation and nested-only branch isolation.
Fixes#3196
The cleanup gate was treating changesApplied===null (apply=false) the same as a clean apply, deleting the temp artifacts dir before returning details.patchPath. Sessions without a session file (which fall back to a per-call tmp dir) ended up with a patchPath pointing at a removed file, defeating the documented manual-apply path.
Tightened the cleanup condition to remove the temp dir only on a confirmed clean apply (changesApplied===true); apply=false and failed applies both keep the artifact for the caller.
Added regression tests for the apply=false preserve case and the apply-succeeds cleanup case.
Fixes#3196
Kept isolation merge/apply summaries out of agent() text when a schema is supplied so Python and JS eval helpers can still parse the JSON payload. The summary now lands in details.isolationSummary for callers that need the human-readable apply state.
Added a regression test that exercises an isolated schema-backed eval agent with a merge summary.
Fixes#3196
The workflowz eval path bypasses the task tool's isolation wrapper and
calls runSubprocess() directly, so parallel agent() fan-outs that edit
overlapping files all land in the parent worktree.
Extends the eval agent bridge schema with isolated/apply/merge, forwards
them through the Python and JS preludes, and adds a shared
task/isolation-runner.ts so the lifecycle (prepare context → run in
worktree → capture patch/branch → merge → cleanup) is implemented once
for both TaskTool and the bridge.
Default mirrors task.isolation.mode: isolated by default when settings
allow it, off when mode === 'none'. isolated=False explicitly disables;
isolated=True with mode === 'none' errors out to match the task tool.
apply=false keeps captured changes inside the worktree and surfaces the
patch path / branch name in details. merge=false forces patch mode even
when task.isolation.merge === 'branch'.
Fixes#3196
- Migrated all wire protocol, schema definitions, and tools validation from Zod to ArkType across multiple packages.
- Updated extension runtimes, custom tools loader, and TypeBox compatibility shim to expose and use ArkType instances.
- Added a comprehensive ArkType migration guide, validation parity tests, and helper utilities.
- Removed redundant PDF asset routing and parsing implementations from the read tool.
- Forwarded `parentAgentId` through task and eval launch paths when spawning subagents.
- Mapped `parentAgentId` to `parentId` in `createAgentSession`.
- Passed each caller's session `getAgentId` (or `MAIN_AGENT_ID`) as the parent for spawned agents.
- 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.
Shared background now 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 prompt instead of a context string forwarded into the subagent's system prompt. The JS and Python preludes drop the context kwarg from agent(), the subagent system prompt drops the {{#if context}} block and the conversation-context file pointer, and runEvalAgent no longer writes a per-call conversation context file. AgentSession sheds the now-unused formatCompactContext() helper that supplied the file's body, and ToolSession.getCompactContext is removed alongside it.
- Changed runEvalAgent to always pass enableLsp: false when launching bridge subagents.
- Added a regression test asserting runSubprocess received enableLsp as false even when LSP is enabled by default.
- 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.
Python eval agent() collapsed every subagent runtime-limit abort into a
generic 'RuntimeError: bridge call __agent__ failed' instead of the real
reason. runEvalAgent built its failure message with:
result.error ?? result.stderr ?? result.abortReason ?? <default>
? is nullish-coalescing, so result.stderr = "" (the executor's value for
a runtime-limit abort) short-circuited the chain and never reached
abortReason. The host bridge then shipped {ok: false, error: ""}, and
prelude.py's '<msg> or <fallback>' picked the named-bridge fallback.
Extracted buildSubagentFailureMessage(): aborted subagents prefer the
trimmed abortReason; otherwise fall through error, stderr (trimmed),
abortReason, and the named-bridge default. Empty/whitespace strings no
longer mask anything. The failure-detection condition also accepts
result.aborted so an abort with exitCode 0 (theoretically) still flows
the abort reason out.
Added a regression test asserting that runtime-limit aborts, whitespace
stderr/error, and totally blank aborts all produce non-empty messages
matching the executor's abortReason text.
Fixes#2006
- Stopped sharing parentEvalSessionId with bridge-spawned subagents.
- Sharing it deadlocked since the parent's kernel blocks on the bridge call.
- Each subagent now gets its own eval session with an independent kernel.
- Added timeout pause/resume control ops and helper to suspend idle timers during bridge work.
- Fixed TimeoutError on long delegated agent()/llm() calls by pausing timeout while silent.
- Updated IdleTimeout with reference-counted pauses, ignored checks while paused, and resumed fresh.
- Replaced heartbeat keepalives with timeout-control events in bridge paths and status routing.
The per-cell `timeout` is an inactivity budget that only re-arms on status
events, but host-side bridge calls can run long stretches with no
intermediate status (a subagent's time-to-first-token on a reasoning
model, a long quiet nested tool, or an entire oneshot llm() request).
The watchdog mistook that for a stall and aborted working subagents
mid-flight.
Pump a lightweight heartbeat while a bridge call awaits, re-arming the
watchdog through the existing emitStatus -> onStatus channel. The
heartbeat is a pure keepalive: forwarded to bump the timer but never
stored or rendered, so a genuinely stalled cell is still interrupted
once the call settles.
- eval/heartbeat.ts: withBridgeHeartbeat() + EVAL_HEARTBEAT_OP
- agent-bridge/llm-bridge: wrap runSubprocess / completeSimple
- js+py executors: forward heartbeat to onStatus, drop from displayOutputs
- tools/eval.ts: bump on heartbeat, skip persist/render
- Added optional `onStatus` callback wiring across eval backends and JS/Python executors for live status streams.
- Added collectDisplay-based forwarding so `emitStatus` and `onDisplay` route status outputs consistently.
- Expanded agent status payloads with preview/model/token-cost context and kept completion updates single-pass.
- Added status upsert and render adjustments in `tools/eval.ts` to coalesce agent events with progress stats.
- Added status/progress test coverage for running/completed agent events, final metric retention, and parallel placement.
- Updated CHANGELOG Unreleased notes to record live progress updates and completion-status metric fixes.
- Added +Nk/+Nm turn-budget parsing with whitespace-boundary matching, multipliers, and hard `!` indicator.
- Added per-turn budget lifecycle plus APIs (`getTurnBudget`, `recordEvalSubagentUsage`) and hard-cap checks in eval runs.
- Added hard budget observability in eval preludes and docs by exposing `budget.hard` and documenting ceiling modes.
- Fixed streaming preview stutter with max-row tracking and padding, with tests for preview height and budget parsing.
- Added `agent()` in JS/Python preludes to call host bridge and parse returned text when schema is set.
- Added JS `parallel()` and `pipeline()` with bounded `__pool()` pools and concurrency normalization.
- Added `runEvalAgent` bridge logic with argument parsing plus plan-mode, allowlist, depth, and artifacts checks.
- Added tool routing and tests documenting new `agent/parallel/pipeline` behavior, defaults, and validation failures.
can1357