- Added plan-mode path resolution that routed bare and cwd-relative PLAN.md targets to the canonical local plan artifact when plan mode was enabled.
- Preserved existing resolution for non-matching basenames and disabled-plan-mode sessions by returning the raw path unchanged.
- Expanded local plan-mode guard tests to cover redirects for PLAN.md and enforcement of non-plan and delete restrictions.
- Updated atom edit prompt guidance to remove obsolete small-drift hash-auto-rebase instructions.
- Removed `id` fields from todo models/fixtures and switched session clones to content-based task identity.
- Replaced `/todo_write` `replace` with `init`, updated setup schemas to `list`/`phase`, and append content-only items.
- Updated `/todo` command flows to match phases and tasks by names/content (exact/prefix/substr, case-insensitive), with no ID targeting.
- Updated rendering/output labels to `# Todos`, `formatPhaseDisplayName`, and Roman-numeral phase headings across todo views.
- Aligned prompts, changelog, and todo tests/fixtures with the new init and content-based todo-write contract.
- Fixed bash interceptor to check both raw and cwd-normalized commands, catching commands hidden behind leading `cd ... &&` wrappers.
- Fixed LSP client shutdown to await graceful shutdown with a 5s timeout before killing the process, and parallelized `shutdownAll` via `Promise.allSettled`.
- Fixed concurrent bash command tracking by replacing a single abort controller with a Set, preventing premature cancellation of parallel commands.
- Removed `./hooks` and `./hooks/*` export entries from the coding-agent package exports map.
- Updated pinned Rust nightly toolchain from `nightly-2026-03-27` to `nightly-2026-04-29` in `rust-toolchain.toml` and CI workflow.
- Replaced custom already-published detection in `ci-release-publish.ts` with `bun publish --tolerate-republish` flag.
- Added support for batch PR operations by accepting `pr` as string or array and dropping `worktree` input.
- Updated `pr_view` and `pr_diff` to normalize PR IDs, process multiple PRs in parallel, and emit combined summaries.
- Refactored checkout into `checkoutPullRequest`, added repo-locking, fixed worktree paths, and summary metadata outputs.
- Updated `remote.add` handling with URL-aware idempotency and per-repo queueing for serialized git mutations.
- Added temp-home test scaffolding and expanded tests for batched PR flows and remote add conflict/no-op cases.
The task description prompt was compressed in c6cab807d — the explicit 'Current input mode' and 'Every assignment must stand on its own.' phrasings are gone. Replace those literal-string assertions with checks against the rendered mode-dependent content that actually differentiates the modes ('context` or `assignment`' for schema-free, 'each `assignment`' for independent). Mode-driven schema differences remain covered by the surrounding parameter-bullet assertions.
- Added `with_text` to keep minimized output byte counters consistent when replacing output text.
- Wrapped successful pipeline and overlay minimizer results with a post-step that emits `OK\n` when the transform empties output on success.
- Added tests to confirm successful empty-output minimization becomes `OK\n` and failures keep empty output.
- Resolved recipe operations now return a command plus optional working directory, and the shell tool path forwards both values when executing.
- Updated the package runner to assign task-local `cwd` entries for workspace scripts instead of embedding workspace command prefixes.
- Adjusted renderer wiring and tests to use the new `cwdFromOp` helper and assert task object shapes with preserved `cwd` values.
- Parsed symbol occurrences inline via a new `name#N` symbol spec and defaulted missing occurrences to 1.
- Updated LSP symbol column resolution to derive occurrence from the symbol spec, removing the separate occurrence argument.
- Synchronized prompts, tool schema rendering, and regression tests to document and verify `#N` occurrence selection instead of a standalone occurrence field.
- Updated the tool configuration key and labels from runCommand to recipe, including its settings UI schema.
- Renamed the run_command tool implementation, prompts, and test wiring to recipe and updated tool registry and renderer registrations.
- Adjusted auto-included tool behavior and availability checks to use the recipe name and recipe.enabled setting.
- Root package tasks were set to use `namespaced: false` when collected.
- Updated the workspace test to expect `root` instead of `root-app/root` in the tool description.
- Added an assertion that executing `op: "root"` returns root output text directly.
- Renamed legacy `just` tool/config wiring to `run_command` and `runCommand.enabled`, replacing the old `just` prompt.
- Added `RunCommandTool` plus prompt and renderer registration so clients use the new `run_command` API.
- Implemented `op`-based runner/task resolution with new runner metadata for Just, Package, Cargo, Make, and Task with error handling.
- Refactored Bash shell rendering helpers and added run-command tests for detection and execution routing behavior.
- Added compact Lark grammar processing and applied it to OpenAI custom-format tools before conversion.
- Reworked atom mode into `---PATH` compact commands with new grammar, parser, and rm/mv file operations.
- Updated `hline`/`href`/`hrefr` helper behavior and hashline mismatch guidance using shared anchor state.
- Standardized path formatting with `formatPathRelativeToCwd` across LSP, prompts, and edit/search/write tools.
- Added benchmark run-path handling, including `.gitignore` runs mapping, absolute reports, and safer snapshot output.
- Added tests for compact grammar payloads, atom parsing/execution, renderer streaming, and path-list outputs.
- Required top-level `path` in edit requests, removed per-entry `path` fields, and updated docs/tests to match.
- Updated patch/hashline/atom streaming preview generation to return a single request-level path diff preview.
- Changed edit execution to route patch/replace/atom/hashline through single-path handlers sharing `path`.
- Added `scripts/analyze-edit-formats` Go CLI with reports to audit edit-tool usage from session JSONL logs.
- Renamed MCP tool IDs from `mcp_<server>_<tool>` to `mcp__<server>_<tool>`, and changed built-in `grep` to `search`.
- Updated `parseMCPToolName()` and bridge helpers to require and trim the `mcp__` prefix.
- Updated cursor, manager, and session discovery flows to require `mcp__`-prefixed tool names.
- Updated MCP tests and assertion fixtures to use `mcp__`-prefixed tool IDs and expected system prompts.
- Renamed the built-in `grep` content-search tool to `search` across settings, schemas, and SDK exports.
- Switched execution wiring so `Task`, `Plan`, cursor, and shell mapping now invoke `search` instead of `grep`.
- Updated prompts, plan-mode docs, and example tool lists to replace `grep`/`ls` references with `search` guidance.
- Aligned `Grep*`/`grep` event, renderer, and hook types to `Search*`/`search` across runtime and tests.
- Documented and fixed `search` result rendering budget behavior and added internal-URL/path-list transcript notes.
Add explicit Basic auth credentials for SearXNG while preserving Bearer token fallback.
Keep optional SearXNG settings out of the TUI and allow empty RFC 7617 username/password fields.
- Simplified diagnostic grouping output in the LSP utility to use plain `## file` headers.
- Adjusted AstEdit, AstGrep, and Grep tools to emit file headings without the `└─` tree prefix.
- Removed the GrepTool context legend text and its related guard variable from output construction.
- Added `AgentRegistry` singleton with session registration/unregistration and IRC routing metadata for peer lookups.
- Added IRC messaging prompts and tooling with `irc.enabled` setting, `list/send` tool paths, and peer roster rendering.
- Changed `/btw` to session-side `runEphemeralTurn`, added background IRC exchange flushing, and fixed empty-input checks.
- Added unit tests for IRC tool and BtwController ephemeral behavior, including disabled, busy, not-found, and abort cases.
- Added `sed` atom editing with `g`, `i`, and `F` flags, path/anchor parsing, and conflict handling updates.
- Changed hashline and grep/read output to `LINE+ID|content` with `>` match prefixes and `:` context prefixes.
- Fixed atom anchor parsing for path-qualified locs, hyphenated single anchors, and content hints after `|` or `:`.
- Updated prompts, changelog, and tests to document and validate the new hashline and `sed` formats.
- Consolidated all former gh_* tools into a single GithubTool that routes execution by a required op field.
- Replaced gh_* tool registrations and render dispatch with `github`, including renderer key and header updates.
- Removed deprecated gh-* tool prompt files and added a unified github.md prompt covering per-op inputs and outputs.
- Updated settings-schema and ci-green prompt guidance to reference the unified github tool and `run_watch` operation.
- Updated tests and tool imports to use `GithubTool`/`githubToolRenderer` with op-based payloads and assertions.
- Added auto-rebasing for stale atom and hashline anchors within ±2 lines, with warning diagnostics.
- Removed atom range-locator support and dropped `between` ops, updating docs/tests for `sub` over `set` nudges.
- Changed no-op handling to track unchanged hashline edits and emit contextual hints for unchanged ranges.
- Expanded Anthropic strict error handling to retry on schema-too-complex and compiled-grammar-too-large errors.
- Added anchor-retargeting warning checks and updated edit tests to expect locator and range-locator rejections.
- Updated python tool-call fixtures by adding `title` to executed-cell payloads and adjusting related test expectations.
- Changed the todo-write parameter schema from a bare operations array to an object containing an `ops` array.
- Updated request parsing and renderer logic to consume `params.ops` and `args.ops` when processing todo operations.
- Updated session and unit tests to invoke todo_write with wrapped `{ ops: [...] }` payloads.
- Adjusted hashline tests to expect colon-prefixed anchors in format, diff preview, and parse assertions.
- Updated ast-edit test regexes and split logic to parse colon-delimited hashline prefixes.
- Changed `todo_write` to an ordered `op`-array model with `replace`, `start`, `done`, `rm`, `drop`, `append`.
- Removed legacy multi-field todo payloads and updated tests/fixtures to use ordered `{op, task?, phase?, items?}[]` args.
- Reworked todo operation execution to apply entries sequentially and validate missing or unknown task/phase IDs.
- Updated todo rendering to use `todo.content` only and changed bash artifact labels from `full result` to `raw output`.
- Consolidated grep, ast-grep, and ast-edit on required `path`, replacing `glob`/`lang`/`sel` with inline file, dir, glob, list, and URL targets.
- Changed ast-grep and grep schemas to require a single `pat` string and use `skip` pagination instead of array patterns or offsets.
- Updated argument validation to reject empty `path` and invalid `skip`, and routed grep context to session settings only.
- Updated tool prompts and tests to reflect new path globbing semantics and `first N` truncation output text.
- Updated generateDiffString to preserve bounded context at both edges of unchanged regions between adjacent changes by adding a middle skip and ellipsis.
- Added a test covering distant edit hunks to verify unchanged lines in the gap are collapsed while change lines remain visible.
- Added an optional strict field to CustomTool definitions to support non-strict execution mode.
- Set strict to false across built-in AgentTool and custom tool registrations, including browser, calculator, GitHub, image generation, and related utilities.
- Updated inspect-image tests to reflect the relaxed strict setting on the tool.
- Added `CodeFrameMarker` and `formatCodeFrameLine()` to centralize code-frame gutter formatting.
- Extended diff rendering to preserve `|` and `│` separators, aligning gutter markers and line numbers.
- Reworked AST, grep, hashline, Vim, and diff renderers to use shared line formatting with computed `lineNumberWidth`.
- Updated atom editing flow and tests, including `resolveAtomEntryPaths` migration and new loc-based/edge-case coverage.
- Adjusted benchmark runner early-stop configuration by passing `buildEarlyStop` through prompt collection.
- Added `openai` and `openai-codex` as image providers and let `providers.image=auto` prefer GPT images.
- Updated settings, selector, and SDK wiring so OpenAI image providers pass through `setPreferredImageProvider`.
- Replaced Gemini-only image tooling with `image-gen` and added OpenAI/Codex hosted-image execution with SSE parsing.
- Added image-gen and handoff tests, including final-yield no-compaction regression and OpenAI payload/header assertions.
- Expanded hashline and chunk bigram tables to 647 entries and moved chunk checksums to a 40-item namespace.
- Changed hashline anchors from `LINE#ID`/`:` to concatenated `LINEID`\t forms across parsing and tool outputs.
- Removed line-number padding and routed diff/read/grep/renderer output through raw numbers, tabs, and `toDisplayLine` formatting.
- Renamed atom ops to `pre`/`post`, removed `ins`, and updated schemas, prompts, and tests for new insertion behavior.
- 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.
- Added raw read output propagation so read/archive commands bypass anchors, line numbers, and chunk formatting.
- Fixed atom/hashline editing by tightening hashline prefixes and applying grouped anchor edits in stable order.
- Hardened chunk parsing and path handling by using `bigram_end` checks and resolving edit paths via shared `args.path` fallback.
- Updated path-related behavior for chunk, replace, patch, and hashline previews to honor optional edit paths.
- Removed mode-level param validators and replaced them with runtime handling, then removed obsolete validation tests.
- Added markdown `Row` chunk support by introducing `ChunkKind::Row`, mapping it to tag `"row"`, and emitting row chunks for table rows.
- Updated Go chunk parsing to support method signatures (`func (recv) Name`), prefer method parsing in signatures, and adjust root rules to classify package/import chunks correctly.
- Changed chunk-edit behavior to add read-only `read:true`, replace `write:null` deletes with explicit `delete`, and require one explicit action per entry.
- Added safer chunk-edit execution with region matching, replacement reindentation, table-row append handling, and stricter warnings/errors for boundary and invalid operations.
- Added helper utilities in the edit renderer to parse partial JSON fragments and extract the `path` field.
- Used the extracted path as a fallback when resolving the edit target file, enabling partial streamed edit calls to show the path.
- Built and stored the render context before call rendering, and added a test covering partial JSON edit path rendering.
- Canonicalized file and CLI defaults from `read` to `open` across tool registration and prompts.
- Added `resolveToolAlias()` and applied alias-normalized tool selection so legacy `read` maps to `open`.
- Updated runtime, UI, and export layers to treat `open` as first-class while preserving `read` compatibility.
- Renamed read prompt docs to `open.md`/`open-chunk.md` and refreshed system guidance to recommend `open`.
- Updated tool-related tests and expectations from `read` to `open` (including test fixtures and aliases).
When the Codex Responses API synthesizes an answer without emitting
url_citation annotations, previously-empty sources made cited results
look ungrounded. Add:
- tool_choice: { type: "web_search" } so Codex must call the tool
- markdown-link + bare-URL extraction from the answer as a fallback
that only runs when no structured citations were returned
The model-resolution path is unchanged; getBundledModels already
returns a usable Codex catalog on main.
Closes#724
The SQLite read helper is documented as a structured selector path
with explicit pagination, while raw SQL already has a separate
q=SELECT escape hatch. This change rejects SQL control syntax outside
quoted strings so helper filters cannot override LIMIT/OFFSET, while
still allowing semicolons inside quoted literals such as LIKE '%;%'.
Constraint: Preserve the documented q=SELECT raw SQL path unchanged
Rejected: Replace where= with a new filter DSL | too broad for a regression fix
Confidence: high
Scope-risk: narrow
Directive: Keep table?where=... as a structured helper; if broader SQL is needed, route it through q=SELECT instead
Tested: bun --cwd=packages/natives run build; bun --cwd=packages/coding-agent run check; bun --cwd=packages/coding-agent test test/tools/sqlite.test.ts
Not-tested: Manual interactive omp read invocation against a live SQLite file
Mirror the existing `commands.enableClaudeUser`/`commands.enableClaudeProject`
schema entries so the OpenCode discovery provider exposes the same
user/project toggle surface as Claude. Default remains true to preserve
current behavior.
Fixes#661
The structured SQLite helper interpolates `where=` directly into SQL.
A crafted clause like `where=1=1 LIMIT 1000000 --` could comment out
the helper's bound `LIMIT ? OFFSET ?`, returning the full table in
violation of the documented pagination contract.
Validate where= at the selector boundary and reject SQL comments,
statement terminators, and pagination/attach/pragma keywords. Raw SQL
remains available via ?q=SELECT... for callers that need it.
Fixes#735
resolveMultiSearchPath now reports `exactFilePaths` when every token
resolves to a plain file (no globs, no suffix glob) and accepts a
single resolvable token so partially-missing lists still search the
resolvable subset. grep iterates those exact files individually
instead of collapsing them into a brace-union glob, which preserves
the user's explicit file set even when siblings share a basename.
Also adds a small `[grep] match lines use ':'; context lines use '-'`
banner when context lines are rendered, and splits the per-file
rendering helpers so files with no remaining matches no longer emit
empty headers.
Apply now recomputes per-file replacement counts from the actual apply
pass and compares them against the preview. If totals or per-file
counts drift (file changed between preview and apply, or apply matched
nothing), the tool returns an isError result explaining that the
preview is stale instead of silently claiming success with mismatched
numbers.
- Queued outbound JSON-RPC messages behind a per-client promise queue to serialize writes.
- Added a project-load gate for project-aware LSP operations before diagnostics and reference lookups.
- Retried declaration-only references with a short delay until project metadata is available, then proceeded with normal results.
- Relaxed chunk-mode parameter validation to accept `{path}`-only edits as valid delete operations.
- Updated the invalid-parameters help text to document accepted chunk delete payloads.
- Added a test that verifies a bare `{path}` edit removes the targeted chunk when null values are stripped.
can1357