- Updated plan-mode-active instructions to require `find`, `search`, and `read` only when exploring.
- Adjusted the system-prompt guidance for the `read` tool to disallow `ls` and explain that `read` on a directory path lists entries.
- 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.
- Added guidance in the system prompt to aggressively delegate oversized plans to parallel work instead of dropping phases or narrowing scope.
- This update instructed agents not to abandon or silently trim work when a plan becomes large.
- 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.
- Updated bash tool guidance to require specialized helpers for file, directory, and search operations instead of shell commands.
- Added find tool guidance requiring file-name lookups to use the built-in Find tool.
- Revised read guidance to require path arguments and use sel for specific line ranges while forbidding cat/head/tail-style reads.
- Added a structural-only-line check that routes whitespace-and-brace lines to a dedicated hash path.
- Introduced structuralBigram to convert line numbers into ordinal suffix tokens and return them for those lines.
- Kept non-alphanumeric-line handling using line-number seeding for all other punctuation-heavy lines.
- Increased the default `read.defaultLimit` configuration from 300 to 500.
- Computed a dynamic read byte budget in `ReadTool` as `max(50KB, maxLinesToCollect * 512)` so larger line limits are not clipped by the fixed 50KB cap.
- Updated truncation and hashline checks to compare against the new dynamic budget instead of `DEFAULT_MAX_BYTES`.
- Added agent identity and registry fields to session configuration and session creation, enabling relay routing metadata for agent sessions.
- Implemented non-persistent IRC relay emission to forward incoming and reply observations from non-main agents into the main session UI.
- Updated IRC UI rendering to support `irc:relay` messages with participant-aware arrow formatting and body display.
- update BUG 3 regex to match "splice locator" warning text
- drop the "rejects mixing splice_block with other anchor edits" test;
splice_block intentionally coexists with other anchor edits
When plan-mode persists the plan file at the synthetic local://PLAN.md
URL, an Edit tool call would crash the entire session. The streaming-edit
pre-cache called resolveToCwd on the path unconditionally; that helper
asserts internal-scheme URLs cannot be resolved as filesystem paths and
threw synchronously inside the assistant-message-event interceptor. The
throw escaped as an Unhandled Rejection, killing the session.
Add an isInternalUrlPath() early-return guard at the top of:
- #getStreamingEditToolCall — returns undefined so the caller skips
pre-cache and the auto-generated guard for internal URLs entirely.
- #invalidateFileCacheForPath — early-returns; nothing to invalidate
for paths that were never cached.
Internal-scheme URLs don't have a stable filesystem path; the actual
Edit tool dispatches through its protocol handler (the same path Write
uses via resolvePlanPath), so the edit still applies — only the on-disk
pre-cache (Morph fast-apply optimization) is skipped.
Add a regression test in streaming-edit-abort.test.ts that drives a
streaming Edit toolcall with path: 'local://PLAN.md'. Without this fix
the test reproduces the original panic stack:
assertNotInternalUrl → resolveToCwd → #getStreamingEditToolCall
→ #preCacheStreamingEditFile → assistant message interceptor.
- Added an `irc_message` session event carrying custom IRC messages and emitted it when IRC records are created.
- Registered an IRC message handler in EventController that skips duplicate messages by role, custom type, and timestamp.
- The handler now appends IRC messages to chat, resets read grouping, and triggers a UI render.
- Removed the `F` sed flag and `literal` field, keeping only `pat`, `rep`, and `g`, and dropped the obsolete `F` test.
- Updated sed parsing, serialization, and error text to remove `splice_block` exclusivity and explain regex escaping.
- Reworked atom prompt format to `<ops>/<splice>/<sed>`, with shared `{path, edits}` calls and strict one-loc/one-verb rules.
- Updated docs (`read.md` and `CHANGELOG.md`) to remove `F:true` anti-patterns and add current `line+hash` and sed behavior guidance.
- Updated the atom tool prompt to clarify that bracketed `[A]` replacements span the opener and closer lines and must include matching trailing closers.
- Added constraints to avoid bracketed splices on unparsable files, to anchor block edits on body lines, and to reread files after large bracketed edits.
- Documented indentation expectations for bracketed splice re-indentation, warning against mixed-space style in replacement bodies.
- Added Fireworks provider onboarding with API-key login and credential storage.
- Added Fireworks provider registrations across stream, types, descriptors, and OAuth registries.
- Mapped Fireworks public model IDs to wire IDs for OpenAI-completion requests.
- Extended OpenAI-compatible detection to treat api.fireworks.ai as supported for streaming and max_tokens.
- Updated model catalog handling with Fireworks models plus context-window/max-token inheritance and metadata updates.
- Added Fireworks model reference loading and fallback logic to preserve best context and token caps.
- 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.
- Removed `i` and `m` from the Atom sed schema and docs, so sed now accepts only `pat`, `rep`, `g`, and `F` options.
- Updated `SedSpec` parsing and serialization to drop ignore-case and multiline handling.
- Adjusted regex construction to apply sed replacements using only global and literal flags.
- Replaced `AgentTool` `nointent` and `deriveIntent` with a unified `intent` option that supports `omit`, `optional`, `require`, or a callback function.
- Updated agent tool schema injection and execution paths to inject `_i` as required/optional/omitted and to derive intent through the new `intent` callback.
- Aligned atom-edit tests with the updated default sed behavior (`g` now off by default and explicit `g: true` for global replacement).
- Updated the atom sed schema and parser to accept an optional `m` multiline flag and pass it through as a new `multiline` field.
- Adjusted flag handling so `g` now defaults to false, with formatting and regex construction emitting `g`/`m` only when enabled.
- Kept user guidance aligned by updating atom tool prompt docs with the revised sed defaults and the new multiline option.
- Replaced `atom.sed` string syntax with `{pat,rep,g?,F?,i?}` objects in schema, prompts, and tests.
- Changed sed validation defaults so `pat` is regex, `g` defaults to global replacement, and `F:true` forces literal matching.
- Fixed `sed` edge cases by allowing sequential same-anchor edits, handling zero-length matches, and preserving chaining.
- Updated native build flow to local `--profile` defaults, refactored enum generation, and switched totals to `total_ms`.
- Added `nointent` and `deriveIntent` to `AgentTool`, and made intent-schema injection honor `PI_NO_INTENT` plus per-tool opt-outs.
- Updated tool execution and streaming UI handling to derive a fallback intent when `_i` is absent, without aborting on derivation failures.
- Marked several coding tools as `nointent` and added `deriveIntent` callbacks where needed, then relaxed prompt language to indicate intent is present on most tools.
Drop three pieces of well-intentioned-but-fragile string mangling that
were quietly mutating model edit content:
- `maybeAutocorrectEscapedTabIndentation` in both hashline and atom edit
modes (plus the `PI_HASHLINE_AUTOCORRECT_ESCAPED_TABS` env toggle and
`isEscapedTabAutocorrectEnabled` helper). Literal `\\t` in edit content
is now preserved verbatim.
- `maybeWarnSuspiciousUnicodeEscapePlaceholder` and the
`runHashlinePreflightSanitizers` wrapper. The warning was misleading:
it flagged `\\uDDDD` as suspicious without distinguishing intentional
literal text from a likely-malformed escape, and it was the only
remaining caller.
- The hand-rolled JSON-unescape fallback in
`decodePartialJsonStringFragment` (renderer.ts). The fallback used
`String.fromCharCode` (mishandling lone surrogates) and only covered a
subset of JSON escapes, so the same fragment decoded one way mid-stream
and a different way after `JSON.parse` succeeded. Now we trim a
trailing partial `\\u`/odd-backslash escape and surface the raw
fragment if `JSON.parse` still fails.
- Added sanitizeText to edit renderer previews and diff rendering before line processing.
- Passed filePath into replaceTabs calls across edit previews, errors, and diff visualization paths.
- Updated the ZAI provider constant to use the `web_search_prime` tool name.
- This aligned the search provider configuration with the expected MCP endpoint identifier.
- Added a guard in applySedToLine that probes matches and rejects sed patterns that match empty strings.
- Updated atom edit error handling to label invalid sed expressions as rejected rather than failed to compile.
- Adjusted sed tests to expect the new rejection wording and added coverage for zero-length pattern `s/()/X/`.
- Replaced Puppeteer imports and package references with puppeteer-core, adding @puppeteer/browsers where needed for explicit browser management.
- Updated the browser tool to prefer a detected system Chrome/Chromium executable and respect PUPPETEER_EXECUTABLE_PATH before launch.
- Implemented lazy, on-demand Chromium download via @puppeteer/browsers with cached executable resolution and fallback error handling.
Fixes#797
- Updated the root `fix:ts` script to run `bun run --workspaces --if-present fix` after `fix:tools`.
- Updated `fix:ts:all` to run `fix:tools:all` followed by workspace-wide `fix` tasks.
- Applied minor SearXNG request cleanup, including direct `Authorization` header assignment and formatting-only formatting changes.
- Updated `read` selector parsing for file and URL reads to accept optional leading `L` and `+` count-style ranges.
- Adjusted truncation notices and schema/help text to emit and suggest `sel` offsets without the `L` prefix, including continuation and suggestion messages.
- Updated hashline/output parsing and related tests to recognize the new `sel` formatting in truncation notices.
- Updated atom tool docs to clarify that `pre` inserts before the anchor and `post` inserts after it.
- Simplified the `F` flag description in the sed guidance from a detailed phrase to the concise term `literal`.
- Renamed atom tool schema fields and internal `AtomEdit` operation from `set` to `splice` in edit parsing and application.
- Adjusted resolver and conflict checks to use `splice` semantics, including file-loc rejection, blank-line deletion handling, and sed precedence.
- Updated atom edit documentation and tests to describe and verify the new `splice`-based API.
- Updated `formatMatchLine` to emit `*` for matched lines, a leading space for context, and a `|` anchor/content separator.
- Revised grep/hashline mismatch messages and prompts to describe the new marker and separator format.
- Aligned affected atom and hashline tests with the updated match-line prefixes and separators.
- dropSession: close persist writer before deletion to prevent EPERM
on Windows where an open file handle blocks unlink
- #runNewSessionFlow: guard UI reset on newSession return value;
session_before_switch hook cancellation now prevents chat state
being cleared and success banner being shown
