After the resolve tool became xd:// devices, ToolView.executeXdevDispatch
unwraps xd://resolve/reject/propose writes so the card model lives on the
unwrapped inner details and the device name, but tools/resolve.tsx still
read action/reason from args, rendering a "?"/warn badge. The renderer now
derives the card kind (apply/discard/propose) from inner details first,
falling back to args and to the device-name default for running cards, and
surfaces propose plan metadata. registry.ts also registers reject/propose
and the historical hub-family aliases (irc, job, await, poll, cancel_job)
so those transcript names stop falling back to generic JSON.
Fixes#5640
- An eval-worktree cherry-pick swept 16 packages/*/node_modules symlinks into the index; 'node_modules/' with a trailing slash only matches directories, so symlinked installs bypassed the ignore. Dropped the slash and removed the tracked links.
Aligns the shim's runtime safeParse/__validator with the wire/tool-call
path, so legacy draft-07 documents (tuple items) accept the same values
validateToolArguments does. Adds a regression test.
Both onKeyDown handlers in Composer.tsx committed on Enter without checking
IME composition state, so confirming a Korean/Japanese/Chinese composition
with Enter re-committed the composing character (한글 -> 한글글).
Extract a shouldSubmitOnEnter predicate that returns false while
nativeEvent.isComposing or a composing ref is set, and a useCompositionGuard
hook that tracks compositionstart/compositionend with a deferred reset for
the WebKit case where the confirming Enter keydown fires after
compositionend. Wire both AskEditor and Composer to it.
Fixes#6163
- 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.
- Routed user and custom message text through the sanitized Markdown renderer.
- Increased spacing between adjacent assistant content blocks.
- Added host and guest Markdown regression coverage.
Fixes#5559
- Render deduped active tool cards with the execution args carried by ActiveTool.
- Covered differing raw assistant args and effective active args in the transcript regression test.
Fixes#4948
- Dedup active tools against committed assistant tool calls as well as the stream ghost.
- Hide the working shimmer while active tools are rendering, preserving it for between-tool model work.
- Added focused Transcript regression coverage for duplicate cards and stale shimmer.
Fixes#4948
Updated collab-web package metadata to the current published version and aligned swarm-extension with the matching pi-coding-agent major.
Documented the pi-uu-grep clap-only fields with dead_code allow reasons so the lint exceptions remain intentional.
Fixes#4549
- Added `normalizeSingleStringField` to dynamically map misplaced string inputs to required schema fields for single-argument tools.
- Integrated argument normalization into `validateToolArguments` to handle model-specific variations in JSON payloads during validation passes.
- Updated `coding-agent` streaming and rendering components to recognize `_input` as a legacy alias for `input` across various UI paths and logic flows.
- Refactored `hashlineEditParamsSchema` to strictly enforce the `input` field while maintaining support for legacy aliases via runtime coercion rather than schema definition.
- Corrected unit tests to reflect that `_input` is rejected by the strict schema but handled gracefully by the validation layer.
- Replaced `grep`, `glob`, and `ast_grep` `paths` inputs with optional single `path` strings while preserving default workspace-root behavior.
- Added shared `toPathList` normalization for legacy arrays and JSON-encoded arrays across tool execution and TUI renderers.
- Updated prompts, fixtures, shims, transcript summaries, and tests to send and display the new `path` argument.
- Updated collab-web search tool cards to read `path` while falling back to legacy `paths` for historical transcripts.
- Recorded the contiguous coding-agent changelog run for the tool-path breaking change and adjacent TTS entries.
- Persist signed message blocks (`text`, `thinking`, `toolCall`) and encrypted reasoning payloads verbatim during session serialization instead of clearing or truncating them.
- Preserve signature keys instead of replacing them with empty strings when they exceed persistence size limits.
- Exempt official first-party OpenAI and Anthropic API endpoints from the leaked-thinking stream healing wrapper to prevent misfires on legitimate visible text fences.
- Extracted `AskEditor` into a standalone, key-bound component keyed by `reqId`.
- Preserved user-typed draft state across duplicate incoming host requests of the same ID.
- Reset the editor draft state only when a genuinely new request ID arrives.
- Simplified `Composer` autosizing logic and state orchestration by isolating editor-specific hooks.
- Adjusted integration tests to match HTML structure changes of the submit action.
- Prevents connection hangs during initial join by immediately failing when a host rejects a guest prior to welcome.
- Short-circuits the connection welcome timeout upon receiving a pre-welcome error frame.
- Surfaces exact protocol mismatch and hello rejection reasons directly to the joining guest interface.
- Ensures `CollabGuestLink` and `GuestClient` transition immediately to ended/failed states with host error details.
Dropped trim and empty gating in the collab web composer so custom ask editor responses ship exactly what the user typed, matching HookEditor's local submit.
- Added `rewrite-changelog.ts` and `fix-changelogs.ts` utilities to automate the consolidation of release notes using LLM-assisted processing.
- Updated multiple internal changelog files by consolidating redundant entries and improving phrasing for readability.
- Implemented `previewLine` utility in `coding-agent` to prevent visual spillover in status rows by managing text truncation and whitespace.
- Updated `package.json` with new workflow scripts for managing package-level change histories and documentation indexes.
- 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.
Stripped advisory wrapper tags in the collab web Markdown renderer while preserving escaped advisory content and existing raw HTML escaping.
Added a regression test for assistant advisory blocks in the collab transcript renderer and documented the fix in the collab-web changelog.
Fixes#3559
- Transitioned the eval tool from batch multi-cell execution to a single-step input structure with flat parameters.
- Updated core agent logic, UI components, and documentation to support state persistence across incremental eval calls.
- Restricted bash tool capabilities by requiring explicit use of `read` or `find` instead of `ls` or `find`.
- Added support for Ruby and Julia language runtimes to the eval tool and associated web renderers.
- Refactored `todo` tool to accept a single operation object instead of an `ops` array.
- Implemented parameter normalization to maintain backward compatibility with legacy array-based tool calls.
- Updated tool instructions, documentation, and UI rendering components to reflect the new interface.
- Added compatibility tests to verify rendering and execution for both legacy and current operation formats.
can1357