- 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.
- Renamed the system prompt's project-context section wrapper from `<context>` to `<repo-rules>` in `project-prompt.md`, so it no longer collides with the `task` tool's `context` parameter under in-band XML tool dialects.
- Updated `snapcompact-inline`'s context-section strip pattern to match `<repo-rules>`.
- Updated the `snapcompact-inline` test fixture to the new wrapper.
- Changelog entry for this rename rides with the fused device-migration commit (adjacent changelog lines).
- Added the `enforceSeenLines` option to hashline `PatcherOptions` (defaults `true`); the seen-line guard in `Patcher` now runs only when enabled.
- Added the `edit.enforceSeenLines` coding-agent setting (default off) and wired it through `edit/hashline/execute.ts` into the `Patcher`.
- Stopped `file-snapshot-store` excluding column-clipped (>512-char) lines from a snapshot's seen set, so single-line edits on long lines apply without a full-width re-read.
- Updated `seen-line-guard` tests and the hashline/coding-agent changelogs.
The re-entry system prompt led with "Read the existing plan" and its
"different task -> overwrite it" step contradicted the planExists guidance
("leave that plan in place and start a fresh file"). Weak models fixated on
reconciling the incomplete old plan and dropped the new request entirely.
- Rewrote the Re-entry procedure in plan-mode-active.md to treat the new
request as the primary input and the old plan as reference only, and to
fold corrections for unfinished old work INTO the new plan rather than
substituting them for the new request.
- Aligned the "different task" branch with the planExists section (fresh
file, no overwrite), removing the contradiction.
- Added reentry-prompt.test.ts asserting the anchoring contract and the
absence of the contradiction.
Fixes#5576
- Added `interruptMode: never` to all updated Go, Rust, and TypeScript built-in discovery rule files.
- Changed `ts-no-inline-cast-access.md` from `interruptMode: tool-only` to `interruptMode: never`.
- Added a `plan-mode-active.md` directive barring changelog/release notes, doc updates, formatter/linter runs, and scaffolding removal as plan steps, so plan mode stops enumerating the mechanical cleanup tail that runs automatically after the change works.
- Clarified that behavior-defining tests and the end-to-end proof stay in the **Verification** section rather than being dropped as cleanup.
- Restored the compact two-row `Editor` layout by default and gated the dedicated IME-safe bottom border behind `setImeSafeCursorLayout()`.
- Added `tui.imeSafeCursor` as an opt-in appearance setting and applied it to initial and replacement editors.
- Added regression coverage for compact default rendering while retaining terminal-local IME preedit protection.
- Updated the TUI changelog for the opt-in compatibility layout.
Generated per-module loaders instead of eagerly evaluating the entire bundled compatibility graph during extension bootstrap.
This prevents appserver startup from cycling through its own retained command modules before the Unix socket is created.
Fixes#5568
- Parsed nested marked text tokens through the inline parser.
- Added browser-template regression coverage for ordered, unordered, and nested lists.
Fixes#5567
- Rewrote logical /dev/fd operands to live OS descriptors before invoking in-process uutils.
- Added regression coverage for diff reading two process substitutions.
Fixes#5557
Each tool-result turn now re-arms one text-only continuation while prewalk is pending. Consecutive prose replies without intervening tool progress terminate naturally, preserving multi-step plan detours without restoring the completion loop.
Fixes#5551
A prose plan and a bash-only completion are structurally identical after any pre-implementation tool detour, so the net now stays armed across every such turn and fires exactly once on the first text-only reply. This bridges read/record/bash detours before the plan while bounding a genuine no-edit completion to a single continuation instead of looping.
Fixes#5551
The continuation net now stays armed across a todo-only turn and disarms only when a non-planning tool runs without a prose plan, so the normal plan-nudge to todo to prose to edit flow still reaches implementation while a bash-only completion no longer loops.
Fixes#5551
Limited the hidden continuation safety net to the assistant turn immediately following the plan nudge, so later bash-only completion ends normally.
Added regression coverage for commit-style flows that never call edit or write.
Fixes#5551
- Updated `run_fd_sync` to handle `io::ErrorKind::BrokenPipe` by returning exit code `141` without writing an error message.
- Added a regression test that verifies `fd` exits with `141` and empty stderr when stdout is closed early (e.g. `fd ... | head` scenario).
- Recorded the broken-pipe behavior fix in `packages/coding-agent/CHANGELOG.md`.
The /omfg generated-rule path validated conditions with raw new RegExp in normalizeConditionRegex and isValidRegexCondition, so a generated rule with a leading (?i)/(?m)/(?s) inline flag was rejected as "Invalid condition regex" before reaching TtsrManager.addRule. Route all three validation sites through compileRuleCondition.
Fixes#4796
- Updated prewalk gating in `AgentSession` to key the todo gate on active tools instead of registry presence, so deactivated todo tools no longer block prewalk handoff.
- Changed subprocess tool filtering so `todo` is stripped for normal subagents but retained when prewalk is armed, and propagated the prewalk state through tool-session setup.
- Added regression tests for restricted active-tool slates and prewalk/non-prewalk subagent tool propagation to verify todo is handled correctly in each case.
- Updated system and todo prompt templates to require batching todo tool calls with real action calls instead of sending them alone.
- Passed a new `prewalkArmed` session flag in `createAgentSession`, set from whether `prewalk` was supplied.
- Simplified `bash` guidance to tighten allowed command patterns, pipeline limits, and launch-based process handling.
- Reworked `browser` instructions into grouped helper sections while preserving selector restrictions and key action semantics.
- Harmonized `eval`, `irc`, `read`, and `todo` prompt wording around state reuse, messaging, selector formats, and task operations.
- Added schema and type updates for task-agent fields and model resolver settings.
- Extended discovery helper logic to carry resolved task-agent metadata through execution setup.
- Updated task/agent registration and execution paths to use the new capability/field data.
- Expanded test coverage for agent-field parsing, model resolution, and executor prewalk behavior.
- Removed `selector`/`sel` arguments from read and grep tool schemas and related execution arg handling.
- Reworked read and grep path processing to parse line selectors from `path` suffixes instead of separate fields, including inline range propagation.
- Updated delegation and execution call paths (including JS/Python preludes and executor tests) to pass selectors embedded in `path`.
- Updated read/grep prompt docs and changelog for the breaking inline-selector API, and removed obsolete selector-specific tests and expectations.
- plugin-install-validation mocks now answer the bun pm cache probe that refreshBunGitCache issues before bun update on git re-installs.
- working-accent tests render the loader before asserting accent computation counts: colorizers run lazily at render time since the loader layout cache landed.
- Replaced the advisor turn validation to raise errors only when a turn has no assistant response at all, instead of treating a content-less `stop` as a failure.
- Kept zero-content silent reviews from entering the retry/rollback/warn path by no longer raising "Advisor unavailable" for completed empty-stop turns.
- Updated advisor runtime tests and changelog language to assert and document that consecutive zero-usage silent turns now succeed without notifications.
can1357