- Added an `interruptible` field to AgentTool and documented when it is honored.
- Updated immediate-mode tool execution to poll steering during in-flight interruptible calls and abort them when steering is queued.
- Marked the coding `job` tool as interruptible and added tests covering mid-wait aborts versus boundary-only steering drain.
- agent-loop: raise repetition-detection floor to 180 chars and clear thinking
replay anchors when collapsing a detected loop.
- providers/google: ignore empty text parts, retain terminal thoughtSignatures,
and stop function-call signatures clobbering the prior block.
- autolearn: capture goal-mode at the turn boundary; harden managed-skill writes
against hard-links/symlinks (O_NOFOLLOW + nlink); refuse minting managed skills
whose name an authored skill already claims.
- eager tasks: thread agentKind through the session so a custom top-level agentId
still gets always-mode delegation; split Eager Tasks prompt into hard vs soft.
- title-generator: race the online title model against a local tiny-model fallback.
- eager-todo: keep the soft reminder aligned with the todo init schema.
- mcp/stdio: keep close() detaching the read loop instead of awaiting it.
- stream loop: fix collapsing and tool-call thought-signature handling.
- Added optional `useless` flags to tool result types and payload builders.
- Added `pruneUseless` and `dropUeless` options to control uneventful result pruning.
- Changed compaction and shake passes to prune or ignore non-error useless tool results.
- Changed conversation serialization to omit useless toolCall/toolResult pairs from output.
- Added coverage for useless tagging, pruning, and serialization behavior.
- Added optional `hasSteeringMessages` config hook and limited steering checks to boundaries.
- Fixed interrupted tool-batch steering by keeping queued messages until boundary handling.
- Added idle text and image submissions to steer queueing when no input waiter exists.
- Auto-continued resumable sessions after queued steering and preserved submit metadata.
- Mapped Codex `end_turn:false` terminal events to `pause_turn` stop details in response stream parsing.
- Updated `agent-loop` to re-sample `pause_turn` turns, reset on tool calls, and cap continuations at 8.
- Added coverage for pause-turn mapping and continuation-capping in agent and AI stream tests.
- Extended `AgentTool.concurrency` to accept per-call resolver functions and resolved concurrency mode from each tool call, falling back to exclusive on resolver errors.
- Updated BashTool to schedule non-PTY calls as shared and PTY calls as exclusive so non-interactive bash calls can run in parallel within one message.
- Tracked in-use persistent shell sessions in the bash executor and routed overlapping calls on the same session key to isolated one-shot shells while preserving owner session availability.
Anthropic rejects tool_result blocks when is_error is true and content is
empty after trimming whitespace. Fill a placeholder at encode time and in
coerceToolResult so wedged sessions recover on the next request.
- Stopped aborted runs from waiting on provider iterator cleanup.
- Ran afterToolCall for completed executions after a run aborts.
- Ignored unknown Anthropic content blocks while preserving known ones.
- Kept sampling params and tool-result caching for disabled thinking.
- Normalized image-content preprocessing in agent sessions now returns early when `content` is missing or not a string/array, avoiding invalid normalization paths.
- Updated agent-loop tests to verify partial tool calls are dropped when an assistant aborts before `toolcall_end`, with run completion reported via an assistant `stopReason` of `aborted`.
- Adjusted Anthropic alignment expectations to reflect a single trailing cache-control breakpoint on the final system block.
- Removed `maxToolCallsPerTurn` from `AgentOptions`, `AgentLoopConfig`, and config serialization.
- Removed stream-loop cap enforcement, including the `toolcall_end` abort path and capped assistant messages.
- Removed Anthropic Opus 4.8 batch-cap resolver and agent-session sync logic from coding-agent.
- Updated tests and changelogs to align with uncapped tool-call behavior and dropped cap-specific cases.
- Introduced `AsideMessage` as a message-or-thunk union so aside providers can defer injection decisions.
- Updated agent loop handling to resolve aside thunks at injection time and skip entries that returned `null`, then switched the session yield queue to `drainLazy` for deferred message building.
- Added tests validating lazy aside evaluation and staleness-aware dropping when everything becomes stale after dequeueing.
- Added an agent loop test proving aside messages are delivered after tool results, before the next model request, without interrupting tool execution.
- Added a yield-queue test confirming stale entries are excluded, the queue is cleared, and re-draining yields no messages.
- Added optional `reason` parameters to `Agent.abort` and `AgentSession.abort` APIs.
- Passed abort reasons through interrupt flows into underlying agent cancellation.
- Replaced hard-coded abort text with `resolveAbortLabel` for streaming and replayed messages.
- Fell back to generic `Request was aborted` text when no abort reason was provided.
When a tool call (most visibly `write` with >~1000 lines of content) is
truncated by `stop_reason: length` — e.g. OpenCode Zen's claude-3-5-haiku
with its 8192 `max_tokens` cap — the agent loop correctly refuses to
execute the call (its streamed arguments are mid-string) but used to
attach the same generic placeholder result it uses for non-runnable
non-tool turns: "Tool call was not executed because the assistant ended
its turn." The auto-continue loop re-prompted, the model re-emitted the
same oversized payload, and the user saw the file write fail again and
again — perceived as a "write tool crash" with the target file lost.
`createAbortedToolResult` now takes a `length` reason that names
`stop_reason: length` and tells the model to split the work into multiple
smaller tool calls (write the first chunk, append the rest with `edit`
insert ops, or break the file into multiple `write` targets). The skip
path in agentLoop forwards the real stop reason so the hint reaches the
model on the very next continuation. Tool execution is still guarded —
the truncated args never run.
Regression test in packages/agent/test/agent-loop.test.ts verifies the
synthetic `write` call is skipped AND the resulting tool-result message
carries the length-specific guidance.
Fixes#1785
- Added T co-signal requirement for tool_arg surface so legitimate edits carrying the marker are never hard-aborted.
- Extended detectHarmonyLeakInAssistantMessage with optional toolArgParseEnd resolver; agent loop omits it, keeping tool_arg inert.
- Updated tests to inject a boundary-at-0 helper for corpus cases and added T-gate unit tests.
- Added `maxToolCallsPerTurn` support to `AgentOptions` and `AgentLoopConfig`, with Agent getter/setter and serialized state wiring.
- Implemented stream-loop cap handling by normalizing bad values and halting after `toolcall_end` reaches the limit.
- Added `ANTHROPIC_TOOL_CALL_BATCH_CAP`=8 and wired session cap sync on init, model changes, and restore.
- Added tests that truncated a 10-call stream to 8 tool calls, and verified non-Claude models resolve no cap.
- Added optional `onBeforeYield` configuration and `setOnBeforeYield` in Agent, executed before follow-up checks.
- Added `YieldQueue` to `AgentSession`, with setup/teardown and streaming/idle flush via `setOnBeforeYield`.
- Replaced immediate async-result follow-up dispatch with queued batch entries, including stale-state suppression.
- Added MCP follow-up queueing in SDK, deduplicating updates by `serverName` and `uri`.
- Added changelog entries for `onBeforeYield`, async-result batching, MCP dedupe, and `display.shimmer` modes.
- Added yield queue unit tests for streaming emission, debounced idle batches, stale filtering, and error isolation.
- Added canonical `pi.zod` schema API exports and removed TypeBox package exports/imports.
- Migrated Tool schema typing from TypeBox to shared `TSchema`/Zod flow with legacy TypeBox compatibility.
- Updated AI provider adapters and MCP/agent builders to convert tool params through `toolWireSchema()`.
- Reworked schema validation from AJV to Zod-safe parsing with `fromTypeBox`, `toolWireSchema`, and meta schema checks.
- Replaced custom MockAssistantStream helpers with createMockModel streams across agent tests.
- Removed manual queueMicrotask stream-event scripting in favor of scripted mock responses.
- Consolidated helper fixtures by deleting local aliases and reusing shared user-message/model helpers.
- Updated test assertions to use mock.calls and mock.model metadata for call and context validation.
Mirrors the pi-mono API surface so apps can preflight tool execution
(block or mutate validated args) and post-process tool results
(override content/details/isError) without wrapping tools.
- `AgentLoopConfig.beforeToolCall` runs after argument validation. Return
`{ block: true, reason }` to short-circuit with a tool-error result.
Mutations to `context.args` are forwarded to `tool.execute` without
revalidation, matching pi-mono semantics.
- `AgentLoopConfig.afterToolCall` runs after execution and before
`tool_execution_end` / tool-result message emission. Returned fields
override the executed result; omitted fields fall through. Hook
exceptions surface as tool errors and do not abort the batch.
- `Agent` exposes both hooks as public, reassignable fields so extension
reloads can swap implementations mid-session.
Compatibility: fully additive. Both hooks default to undefined and the
loop behaves identically when neither is set. The internal
`executeToolCalls` signature was collapsed to `(context, message,
signal, stream, config)` -- it is not exported, so this is not a public
API change. Pi-mono's `terminate` field on `AfterToolCallResult` is
omitted because our `AgentToolResult` has no batch-level early-stop
contract.
- Removed export leakage by demoting many helper and const symbols to module-local scope.
- Renamed underscore-prefixed internals and cache fields, then updated related references and `satisfies never` checks.
- Deleted obsolete logic branches and helpers, including harmony-stream interruption flow and unused benchmark runtime helpers.
- Updated Biome config and manifests by broadening lint coverage and removing an unused `@napi-rs/cli` dev dependency.
- Adjusted tests and utilities to use renamed test helpers and remove redundant private test-only helpers/locals.
- Converted systemPrompt APIs and state types to ordered `string[]` across agent, AI, and coding-agent surfaces.
- Added `normalizeSystemPrompts` and applied it to context normalization before building provider request payloads.
- Updated AI providers to emit separate normalized prompt blocks/messages instead of a single merged system prompt.
- Removed dedicated `projectPrompt` state and remapped that context into system-context buckets in session, dump, and token accounting.
- Aligned tests and changelogs to pass and assert `systemPrompt` as arrays with ordered prompt semantics.
- Fixed abort-source handling so caller aborts always win and local reasons only attach to matching request signals.
- Fixed agent-loop streaming to race event reads against abort signals and emit an aborted assistant message.
- Fixed Anthropic request construction to honor thinkingEnabled=false and omit temperature/top_p/top_k for Opus non-thinking.
- Fixed OpenAI Codex request handling by normalizing response URLs, decoding non-string websocket frames, and cleaning handshake headers.
- Added regression tests for abort precedence, Anthropic alignment cases, and Codex stream/header normalization.
- Documented the cancellation and provider behavior fixes in package changelogs.
- Renamed subagent completion flow from `submit_result` to `yield` across SDK tools, prompts, and docs.
- Updated executor/task handling to require and parse `yield` calls, replacing legacy submit-result extraction and state flags.
- Added `subagent-yield-reminder` and updated system prompts to require `yield` with `result.data` or `result.error`.
- Renamed hidden-tool and registration plumbing to `yield`, including discovery helpers and renderer/test surface.
- Standardized missing-file read errors and now return `File not found: <path>` for absent edit targets.
- Centralized AI provider, usage, and OAuth helpers into shared modules to remove duplicated logic.
- Migrated OAuth/API-key login flows to shared factory helpers and removed inline prompt/token-exchange code.
- Reused shared tools and formatter utilities for discovery, stream tails, LSP batching, and source formatting.
- Consolidated repeated test helpers and fixtures into shared modules, replacing inline helper duplicates.
* Add MCP tool discovery search and live refresh
* Fix MCP discovery review feedback
* Address remaining MCP discovery review comments
* feat: compact MCP discovery search results
* fix: align MCP discovery search contract
* feat: add MCP server tool counts to discovery hints
* fix(agent): corrected stale toolChoice validation against active tools
- Fixed stale forced toolChoice passed to provider after mid-turn tool refresh by validating against active tools.
- Added refreshToolChoiceForActiveTools() to filter invalid tool choices when available tools change.
- Changed getToolChoice config to use computed function instead of static property for dynamic validation.
- Fixed MCP tool selection tracking in coding-agent to distinguish between discovery-enabled and non-discovery sessions.
- Updated search_tool_bm25 to filter already-selected tools before applying limit parameter.
---------
Co-authored-by: can1357 <me@can.ac>
- Extracted tool result emission logic into dedicated emitToolResult function to eliminate duplication.
- Consolidated tool execution result handling to emit results immediately after execution rather than deferring to post-processing loop.
- Simplified post-execution loop by delegating result emission to emitToolResult and removing redundant message construction.
- Exported `finalizeSubprocessOutput()` function and `SubmitResultItem` interface for subprocess output finalization with submit_result validation.
- Added automatic reminders (up to 3) when subagent stops without calling submit_result tool, aborting with exit code 1 after final reminder.
- Extracted subprocess output finalization logic into dedicated `finalizeSubprocessOutput()` function for improved testability and reusability.
- Added comprehensive test coverage for subagent warning injection, reminder behavior, and abort handling in executor module.
- Added streamed tool intent display in working message to show real-time intent tracking during agent execution.
- Changed intent tracing field name from `$intent` to `_intent` across tool schemas and agent core for consistency.
- Added support for file deletion and renaming operations in hashline edit mode.
- Renamed hashline edit operation fields: `set` to `target`/`new_content`, `set_range` to `first`/`last`/`new_content`, `insert` to `inserted_lines`.
- Added optional `intent` field to `ToolCall` interface for capturing harness-level intent metadata.
- Added `intentTracing` configuration option to enable intent goal extraction from tool calls with automatic `$intent` field injection and argument stripping.
- Implemented intent injection and extraction logic in agent-loop to populate tool call intent metadata when intentTracing is enabled.
- Added `tools.intentTracing` setting to coding-agent configuration schema with environment variable override support.
- Migrated timing measurements from `performance.now()` to `Bun.nanoseconds()` for higher precision benchmarking across all benchmark and timing-sensitive code.
- Updated elapsed time calculations to convert nanoseconds to milliseconds using division by 1e6 to maintain consistent time units.
- Increased benchmark precision from 4 to 6 decimal places for per-operation timing measurements.
- Refactored grep benchmark to use averaged timing values instead of storing individual iteration times, reducing memory overhead.
- Added `concurrency` option to `AgentTool` interface supporting 'shared' (default, parallel execution) and 'exclusive' (solo execution) modes.
- Implemented parallel execution of shared tools within a single agent turn with ordered result emission.
- Refactored tool execution to support concurrent scheduling with interrupt handling via steering messages and AbortSignal.
- Added steering message checking mechanism that interrupts tool execution when user messages arrive during tool processing.
- Removed HTTP proxy setup code from stream.ts that was conditionally setting up undici global dispatcher.
- Extracted delta event batching and throttling logic into AssistantMessageEventStream base class to eliminate duplication across test mocks.
- Changed access modifiers from private to protected in EventStream class to allow subclass customization of queue, waiting, and completion handling.
- Simplified MockAssistantStream implementations across five test files by removing custom event handling logic and delegating to AssistantMessageEventStream.
- Added protected methods deliver() and endWaiting() to EventStream to support subclass event delivery patterns.
- Implemented delta event type guard and merging utilities to consolidate event batching logic in one place.
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
- Removed WASM generation script; use Bun `wasm?raw` loader for imports.
- Added bunfig.toml with loaders for `.md`, `.py`, and `.wasm?raw` text imports.
- Added types/assets/index.d.ts for global TypeScript module declarations.
- Unified TypeScript configuration with tsgo-based checking across monorepo.
- Removed build and WASM steps from install and publish pipelines.
- converted relative imports to path aliases ($c/*, $ai/*, $tui/*, etc.) across all packages
- added per-package tsconfig.json with complete path mappings for runtime resolution
- set importModuleSpecifier to non-relative for IDE auto-import preferences
- updated dev script to run from monorepo root for consistent path resolution
- Added ToolCallContext interface with batch execution metadata including batchId, index, and total.
- Enhanced getToolContext() to accept optional ToolCallContext parameter for batch-aware tool execution.
- Implemented LSP batching support to coalesce formatting and diagnostics operations on parallel edits.
- Added comprehensive tests for tool call batch context and LSP writethrough batching functionality.
can1357