customToolToDefinition rebuilt ToolDefinition without strict, so the
Task proxies' (and startup MCP tools') explicit strict:false was dropped
before RegisteredToolAdapter and the OpenAI-family serializers saw it.
Declare strict on ToolDefinition, copy it in the bridge, and cover the
proxy -> definition -> registered adapter path in the parity test.
Emitted session_shutdown after model rendering and centralized managed timer cleanup across one-shot listings and agent sessions.
Added regression coverage for the extension shutdown lifecycle.
Fixes#6297
Passed the per-request model through SDK payload callbacks and ExtensionRunner context creation.
Added regression coverage for Codex-primary and Anthropic-request contexts.
Fixes#6006
Extension/SDK/RPC registerTool defaulted an omitted loadMode to
"discoverable". A UI-only re-register of an essential built-in
(read/write/bash/edit/glob) then became discoverable and, with tools.xdev
on, was unmounted from the top-level schema. read/write dropping also
broke the xd:// transport (read xd://, write xd://<tool>), leaving the
model with no callable coding essentials.
- Add defaultLoadModeForToolName: omitted loadMode resolves to "essential"
for known essential built-in names, "discoverable" otherwise.
- Apply it at all four adapter boundaries (extension wrapper, custom-tools
wrapper, sdk customToolToDefinition, rpc normalizeHostToolDefinitions).
- Transport invariant: read/write never mount under xdev regardless of
loadMode (they carry the transport).
- Regression test covering the demotion, transport invariant, and a drift
guard tying the essential-name set to the tool classes.
Fixes#5764
Custom tool/extension/hook/plugin modules under ~/.claude/tools are
evaluated with live side effects during createAgentSession. A module that
attaches a stdin consumer at import time — an MCP StdioServerTransport
built at module top level, or a bare process.stdin.resume() — steals
Bun's single stdin reader, so the TUI receives exactly one data event and
goes permanently deaf after the first keypress. Under tmux the terminal's
automatic DA1 reply is that one event, so the first user keystroke is
already dead: the input-deafness reported in #5378/#5618.
Broadened the loader's withExitGuard (renamed withHostGuard) to also
snapshot and restore process.stdin around third-party module evaluation:
any data/readable/end/close/error listener the module adds is removed, and
the stream's paused and raw-mode state is restored to the pre-load
snapshot. The exit guard already fenced process.exit; stdin is the same
class of host-state hijack.
Fixes#5618
Extension-scheduled setInterval/setTimeout/detached callbacks ran outside
the handler-dispatch try/catch, so a throw surfaced as a process-level
uncaughtException and the global postmortem handler tore down the whole
session instead of isolating the misbehaving extension.
- Added ManagedTimers backing sanctioned ctx.setInterval/setTimeout/clearTimer:
callbacks run with handler-dispatch isolation (throw/rejection logged and
routed through onError), handles are unref'd, and all are cleared on
session_shutdown.
- Wired the helpers into ExtensionRunner.createContext and the runner-less
command-context fallback; onSession now inherits the runner context.
- Documented in-process no-isolation behavior and the managed timers in
docs/extensions.md and docs/skills/authoring-extensions.md.
Fixes#5664
- Added the `xd://` virtual device protocol (`internal-urls/xd-protocol.ts`, `tools/xdev.ts`): tools declaring `loadMode: "discoverable"` are unmounted from the request tools array and driven via `read xd://` (list/docs+schema) and `write xd://<tool>` (execute), gated by the `tools.xdev` setting (default on) and inlined into the system prompt.
- Merged the `irc`, `job`, and `launch` tools into a single `hub` tool (`tools/hub/`, `async/job-manager.ts`): messaging keeps `send`/`inbox`/`list`, job control maps to `wait`/`cancel`/`jobs`, process supervision keeps `start`/`logs`/`stop`/`restart`/`describe` with `ps`, and the unified `wait` races background jobs against peer messages; SDK `IrcTool`/`JobTool`/`LaunchTool` are replaced by `HubTool`.
- Removed the hidden `resolve` tool in favor of the `xd://resolve`/`xd://reject`/`xd://propose` resolution devices, auto-including `write` whenever a deferrable tool or plan mode is present.
- Removed the BM25 tool-discovery system: the `search_tool_bm25` tool, the `tool-discovery` module, the `tools.discoveryMode`/`mcp.discoveryMode`/`mcp.discoveryDefaultServers`/`tools.essentialOverride` settings, per-tool MCP selection, and the `mcp_tool_selection` message type.
- Unified tool presentation on `ToolLoadMode` (`essential`|`discoverable`), replacing the custom-tool `xdev?: boolean` opt-out; custom, extension, MCP, RPC host, image-generation, and TTS tools now default to `discoverable`, and added a `satisfies` predicate to `SoftToolRequirement`.
- Removed the standalone `ssh` command tool and `ssh/ssh-executor` (the `ssh://` read/write/search protocol stays), and made `--tools` address hidden built-ins.
- Updated collab-web to render `xd://` dispatches and `hub` op families, dropped the `search_tool_bm25`/`ssh`/`report-finding` renderers, refreshed tool docs and prompts, and migrated the affected tests and changelogs.
ExtensionToolWrapper caught a thrown tool exception, emitted tool_result
with the modifiable result, then rethrew the original executionError whenever
the effective error state stayed true. This discarded any replacement content
or details a handler returned, so an extension could only surface modified
content by returning isError: false, which wrongly converted the failure into
a success.
Return the (possibly modified) result carrying isError instead of rethrowing.
The agent loop already honors AgentToolResult.isError (coerceToolResult) and
surfaces it as a tool error on the wire, so replacement failure content now
reaches the model while the call remains an error. No-modification, error->success, and success->error paths keep their existing semantics.
Fixes#5302
- Replaced legacy `pi/` role alias prefix with canonical `@` syntax across model resolution, documentation, and tests.
- Added support for bare `*` default alias and multiple alias prefix detection with custom role resolution in `resolveConfiguredRolePattern()`.
- Enhanced thinking suffix parsing to accept unambiguous abbreviations (minimum 2 characters) for effort and level selectors.
- Extended `resolveCliModel()` and `filterAvailableModelsByEnabledPatterns()` to accept settings parameter for role alias resolution from `--model` flag.
Added an explicit timeout presentation capability so interactive queued dialogs defer the fallback while older UI implementations still get an immediate tool-owned timeout.
Refs #4995
Reset the ask tool fallback timeout whenever the interactive selector resets its UI countdown, preventing late keypresses from falling back to the original recommended option.
Refs #4995
Routed bundled virtual specifiers through Bun's plugin namespace so compiled-binary extensions can import @oh-my-pi value exports.
Surfaced extension load failures during session startup.
Fixes#4954
- Copied localProtocolOptions through SDK-created custom tool contexts so startup MCP tools resolve '/data/workspaces/can1357__oh-my-pi__4946/.omp-session/2026-07-09T16-06-43-993Z_019f47a1-a619-7000-9062-5f5d863afa45/local' against the active session.
- Exposed localProtocolOptions on extension contexts and covered the runner propagation path.
Fixes#4946
Extensions calling ctx.ui.addAutocompleteProvider (e.g. @ff-labs/pi-fff)
crashed at load with 'TypeError: ... is not a function' because omp's
ExtensionAPI.ui omitted pi's autocomplete-provider API; the throw also
aborted the rest of a try/catch-guarded session_start init.
ExtensionUIContext now declares addAutocompleteProvider(factory).
Interactive mode stacks each factory on the built-in editor provider in
registration order, re-applies the stack on every slash-command refresh,
and skips throwing/malformed factories; RPC, ACP, and headless contexts
accept the factory as a no-op, matching upstream pi's RPC behavior.
Fixes#4919
Extension sendUserMessage() without deliverAs fell through to prompt(),
which throws AgentBusyError during an active stream; the message was
dropped and surfaced as 'Extension sendUserMessage failed'. Route the
omitted-deliverAs path through prompt() with streamingBehavior 'steer'
so streaming queues a steer with normal prompt-flow side effects
(keyword notices, advisor auto-resume reset) and idle still starts a
turn.
ACP skill-command prompts now pass streamingBehavior 'steer'; the RPC
skill fast-path honors the prompt command's streamingBehavior field
(default steer) like the plain-prompt path already did. Documented the
extension-facing delivery semantics.
Synthesized from PR #4942 (prompt-flow steer routing, docs, tests) and
PR #4922 (RPC streamingBehavior threading, steer regression test);
dropped PR #4942's unrelated workflow-notice.md ellipsis churn.
Fixes#4923
Co-authored-by: roboomp <omp@can.ac>
Co-authored-by: metaphorics <metaphorics@users.noreply.github.com>
Op: correct
Restores: review:4375
- Widen ExtensionAskDialogResult to a union with { kind: "chat" } variant
so AskTool can distinguish chat handoff from cancel (undefined).
- AskDialogComponent.#finishChat passes { kind: "chat" } via onChat.
- Controller settles { kind: "chat" } locally and propagates a "chat"
sentinel through the guest/collab path instead of returning undefined.
- AskTool returns a chat-redirect AgentToolResult (chatRedirect details)
instead of aborting with ToolAbortError.
- #promptForNote prefills with the existing note only when editing the
same row (noteRowKey === rowItem.key), preventing cross-row note leaks.
- Add ask-dialog and ask tool tests for chat redirect and row-specific
note prefill.
Plan-approval's 'Approve and compact context' used to pass the rendered
plan-mode-compact-instructions prompt as the first positional argument
to handleCompactCommand -> session.compact(), which landed on the
session_before_compact extension hook as customInstructions. Extensions
treating that field as user focus (e.g. to bias a query-focused summary)
would then see plan-mode boilerplate instead of operator intent and
produce query-biased compactions.
Add CompactOptions.internalGuidance: a private summarizer-only channel.
session.compact() reads it into the fallback-model summarizer while the
session_before_compact hook payload still only carries the public
customInstructions arg (undefined for the plan-compact path). The
snapcompact-disable predicate and the /compact rejectsFocus guard cover
both fields so a directed summary is never silently downgraded.
Extend the interactive-mode handleCompactCommand facade + command
controller with a fourth internalGuidance parameter, and switch the
plan-approval callsite in interactive-mode.ts to route the plan prompt
through it.
Fixes#4359
Adds the rich TUI ask dialog, additive schema fields, ask.enabled tool gating, note/preview/header support, chat redirect, and timeout behavior that defers while nested prompts are active instead of discarding user input.
Op: extend
Normalized extension custom-message payloads before session state or persistence, including bare string sendMessage shorthands. Skipped legacy bare custom_message entries during context rebuilds and dropped malformed custom/hook messages before LLM conversion. Added regression coverage for the poisoned-session resume crash.\n\nFixes #4345
`discoverExtensionPaths` loaded the extension-module capability across all
registered providers (native, claude, codex, gemini, opencode) and then
discarded every item whose `_source.provider !== "native"`. Four foreign
directory walks ran on every session startup only for their results to be
dropped — worst on Windows.
Scope the load to the native provider via the existing `LoadOptions.providers`
filter: `loadCapability(extensionModuleCapability.id, { ...loadOptions,
providers: ["native"] })`. The hook-capability load in the same function is
unchanged (hooks legitimately span providers). Output is identical.
Regression test in `extensions-discovery.test.ts` spies on each extension-module
provider's `load()` and asserts only "native" is invoked.
Fixes#4198
- Removed the canonical model variant indexing, selection, and tracking logic from the model registry and resolver.
- Eliminated the `canonical` sub-command, tab view, search tokens, and equivalence configuration structures from the CLI and model selector components.
- Refined model identification, lookup, and provider fallback resolution to bind exclusively to standard, raw model IDs.
- Relocated the equivalence utility script within the catalog package to support script-only policy generation.
Bun.sleep(timeoutMs).then(...) leaves an uncancellable timer registered
with the event loop, so every successful handler race in the runner
leaked one — a completed tool_call/tool_result handler could delay
non-interactive CLI exit by up to the 30s default cap. Verified with a
subprocess exit-time probe: buggy pattern exits in ~5000ms for a 5s
timeout, setTimeout+clearTimeout pattern exits in ~17ms.
Extract a raceHandlerWithTimeout helper backed by setTimeout with a
finally-scoped clearTimeout, and route both #runHandlerWithTimeout
(pre-existing latent leak) and emitToolCall (introduced in the same PR)
through it. No behavior change on the timeout branch.
Addresses review on #3951 from chatgpt-codex-connector[bot].
emitToolCall awaited each extension handler directly (runner.ts:704-706),
bypassing the #runHandlerWithTimeout wrapper every other subscribed event
routes through. A tool_call handler that never resolves parked
ExtensionToolWrapper.execute indefinitely, freezing tool dispatch even
though the symmetric emitToolResult path has always been timeout-protected.
Race each tool_call handler against Bun.sleep(extensionHandlerTimeoutMs)
inline (the shared wrapper swallows errors, and this callsite is
fail-closed). On timeout: emit an ExtensionError with event: 'tool_call',
log a warning, and return { block: true, reason: 'Extension <path>
timed out after <ms>ms' } — symmetric with the existing per-handler error
branch. Fail-closed is the correct policy for a pre-execution gate: an
unresponsive extension MUST NOT be silent consent to run the tool.
Fixes#3948
- Added `process.reallyExit` to the hard-exit API patch in `withExitGuard` to prevent bypass.
- Integrated `withExitGuard` wrapper into extension and hook factory invocation sites.
- Improved `ExtensionExitError` to provide dynamic reporting of the intercepted exit method.
- Introduced `resolveToolEventInput` to enable mode-specific transformation of editor tool inputs before normalization.
- Updated `ExtensionToolWrapper` and `HookToolWrapper` to utilize the new resolver during tool execution.
- Added support for tracking `reasoningTokens` in `SessionStats` and `AdvisorStats` within the agent session.
Codex discovery surfaced every `~/.codex/hooks/*.{ts,js}` file as an OMP
hook (silently defaulting untyped names to `pre:<basename>`), and
`discoverExtensionPaths` then handed those paths to `loadExtension` for
dynamic import. A standalone Codex hook script with a top-level
`process.exit(0)` terminated the host CLI cleanly — `try/catch` around
`await import()` cannot intercept a synchronous exit, so OMP died at the
`loadExtensions:start` startup marker with no error surface.
Two-layer fix:
- `packages/coding-agent/src/extensibility/utils.ts`: new
`withExitGuard` helper patches `process.exit` for the duration of a
guarded callback so an exit raises `ExtensionExitError` instead of
terminating the process; nested and concurrent guards restore correctly
via depth counter.
- `extensibility/extensions/loader.ts`, `extensibility/hooks/loader.ts`,
and `extensibility/plugins/manager.ts` wrap their dynamic-import sites
in `withExitGuard` so the existing per-module `try/catch` records the
intercepted exit as a load error and OMP keeps starting.
- `discovery/codex.ts:loadHooks` no longer treats arbitrary files as
OMP hooks: only `pre-<tool>.{ts,js}` and `post-<tool>.{ts,js}` are
registered. Files like `memory-bank-reminder.ts` are silently skipped
rather than imported as extension factories.
Adds regression coverage:
- `test/extension-loader-process-exit.test.ts` — `loadExtensions` /
`loadHooks` return errors and leave `process.exit` restored when a
module exits at import time; sibling modules still load.
- `test/discovery/codex-hooks-discovery.test.ts` — codex provider
registers `pre-*` / `post-*` files and drops everything else.
Fixes#3680
- Renamed the `find` and `search` tools to `glob` and `grep` respectively across the codebase to improve command clarity.
- Implemented full-stack support for the renamed tools, including CLI arguments, system prompts, SDK exports, and tool registration.
- Added automated migration logic in `settings` to transform legacy `find` and `search` configuration keys to their new equivalents.
- Updated the `collab-web` renderer registry to ensure backwards compatibility with legacy tool outputs.
- Centralized draft state and image management by migrating fields from context to the CustomEditor component.
- Standardized transcript row construction by introducing shared helpers for background jobs, IRC traffic, and file mentions.
- Refactored redundant UI logic and helper functions into reusable utility modules to streamline message submission and component rendering.
- Standardized event handler types by consolidating lifecycle definitions into a shared module while maintaining public API stability.
- Delay the creation of the extension context until a relevant handler is identified.
- Avoid unnecessary performance overhead for events that have no registered handlers, such as frequent streaming updates.
- Added a `mode` property to `CompactOptions` to allow fine-grained control over compaction strategies.
- Implemented `soft`, `remote`, and `snapcompact` submode overrides for the `/compact` command.
- Integrated `parseCompactArgs` to enable robust subcommand routing and validation, including focus instruction rejection for specific modes.
- Established a `CompactMode` registry to manage compaction strategies and verify remote availability.
- Imported and injected `zod/v4` under `zod` in runtime environments for custom commands, custom tools, extensions, and hooks.
- Added corresponding Type definitions to `CustomCommandAPI`, `CustomToolAPI`, `ExtensionAPI`, and `HookAPI` interfaces.
- Re-exported Zod and its alias from the main package entry point to expand the public API surface.
- Refactored the internal Typebox validation shim to support parsing via standard `.safeParse()` and `.toJSON()` methods.
- Advanced Typebox shim utility capabilities with support for dual-key record validation and enhanced schema structure handling.
- 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.
- Added context snapshot metadata to AssistantMessage for prompt and non-message token history.
- Anchored context usage calculations on assistant snapshots and computed percent numerically.
- Updated status-line, /context, selector, and interactive mode flows to share session usage totals.
- Extended status-line cache fingerprinting and invalidation for assistant usage and prompt/tool/skill changes.
Preserved Settings.disabledExtensions fallback when extension discovery is called without an explicit disabled list and kept hookCapability paths out of extension-module basename filtering.
Fixes#2796
can1357