- 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).
- Updated `chunkReadPathSeparatorIndex` to detect URL schemes and split at the final selector colon only after the URL path.
- Added tests for `parseChunkEditPath` and `parseChunkReadPath` covering local plan URLs with selectors and scheme-only URLs.
The previous mismatch text ('1 line has changed since last read. Use
the updated LINE#ID references shown below.') reads like a successful
edit followed by an informational note. Providers whose tool-result
plumbing does not surface `isError: true` to the model (e.g. Qwen via
the OpenAI-completions shim, where mitmproxy traces show the model only
receives the content text) treat the response as a success and proceed
with stale state.
Reword the message to start with 'Edit rejected:' and explicitly state
'The edit was NOT applied' so the failure is unambiguous in plaintext.
The structural payload (>>> markers, updated LINE#IDs) is unchanged.
Fixes#742
- Reworked #prepareStopOutcome to collect stopped, terminated, and exited event waits before racing them.
- Attached noop rejection handlers to each pending wait promise to prevent unhandled rejection noise after the race settles.
- Returned Promise.race(promises) so stop outcome preparation still waits for the first relevant lifecycle event.
- 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.
- Added a streaming parser path for apply_patch envelopes that tolerates incomplete patch bodies.
- Updated apply patch preview expansion to return best-effort hunks when the renderer is in partial mode.
- Added a renderer test confirming streaming apply_patch input shows file paths without end-marker parse errors.
Slots a new "apply_patch" variant alongside the existing edit modes
(replace, patch, hashline, chunk, vim). The mode accepts a single input
string containing a Codex *** Begin Patch / *** End Patch envelope,
parses it with a new lenient parser (heredoc-tolerant), and fans each
file-op out to the existing executePatchSingle so LSP writethrough,
plan-mode guards, fs-cache invalidation and diagnostics are shared
with the patch mode.
Exposes both tool shapes from the spec: the JSON function-tool variant
(§1.2, {input: string}) and the OpenAI custom-tool / Lark-grammar
"freeform" variant (§1.1, raw patch string). The edit tool advertises
a Lark grammar via customFormat and a wire name via customWireName;
openai-responses emits it as a grammar-constrained custom tool when a
model opts in with applyPatchToolType: "freeform" in models.json.
custom_tool_call / custom_tool_call_output are plumbed end-to-end
through the shared responses code (emission, streaming, history
replay), and the agent-loop dispatcher matches tool calls by either
name or customWireName so returned calls route correctly.
Also threads preview/diff rendering for apply_patch through the TUI
(tool-execution + edit renderer) so streaming patches show per-file
diffs like the other edit modes.
Default edit mode is unchanged (hashline); opt in via edit.mode or
PI_EDIT_VARIANT=apply_patch.
- Standardized missing-file read errors and now return `File not found: <path>` for absent edit targets.
- Centralized AI provider, usage, and OAuth helpers into shared modules to remove duplicated logic.
- Migrated OAuth/API-key login flows to shared factory helpers and removed inline prompt/token-exchange code.
- Reused shared tools and formatter utilities for discovery, stream tails, LSP batching, and source formatting.
- Consolidated repeated test helpers and fixtures into shared modules, replacing inline helper duplicates.
- Updated path resolution to derive a file path from the first edit entry via filePathFromEditEntry when top-level fields are absent.
- Updated single-file result rendering to fall back to first-edit entry values for op and rename metadata before detail-level metadata.
The hashline prefix stripping logic uses an "all-or-nothing" heuristic:
it only strips N#XX: anchors when every non-empty line carries one.
When the Read tool truncation notice (e.g. [Showing lines 1-300 of
332. Use sel=L301 to continue]) is present in content passed to the
Edit or Write tool, that marker line breaks the heuristic, causing ALL
anchors to be written to disk verbatim. On subsequent reads, those
persisted anchors get double-prefixed (1#NX:1#BQ:---), compounding
the corruption.
This can happen when the AI model pastes Read tool output (including
the truncation marker) back into an Edit/Write call. While this is
arguably a model-level issue, the toolchain should be resilient against
it rather than silently corrupting files.
Changes:
- Add READ_TRUNCATION_NOTICE_RE to detect Read tool truncation markers
- Update collectLinePrefixStats to exclude truncation marker lines from
the non-empty line count so they no longer break the stripping heuristic
- Add stripLeadingHashlinePrefixes helper for recursive stripping of
nested/double-prefixed anchors (handles already-corrupted content)
- Add filterTruncationNotices helper to remove truncation marker lines
- Update both stripNewLinePrefixes and stripHashlinePrefixes to filter
truncation markers and use recursive anchor stripping
- Add 5 new test cases covering truncation markers and nested anchors
- Removed the standalone vim tool and normalized built-in/requested tooling to edit.
- Updated session and SDK tool activation to dedupe lowercase names and track edit state via the edit key.
- Added vim-mode argument detection and delegated edit rendering/execution into Vim handlers under edit.
- Updated Vim step handling to auto-reorder numeric-positioned commands, including cc/C/S/s/i/I/A cases.
- Renamed prompt/changelog text and test expectations to reflect edit-only tool naming and usage.
- Added vim tool-call IDs across EventController, UiHelpers, and ToolExecution for per-call preview mapping.
- Extended Vim type and command parsing with update/write, edit, global, yank, and put handling.
- Added Vim engine support for new commands and motions, including gJ, g*, g#, g_, |, and gu/gU/g~.
- Reworked Vim tool flow to cache per-file engine clones, reuse tool details, and stream inserts in chunks.
- Updated vim.md and changelog to document new vim keys, ex aliases, and fixed :global preview behavior.
- Added parser and renderer tests plus a tmp/vim_test.txt fixture for chunked, cursor, and partial-insert cases.
- Normalized chunk write handling for body-region (~) edits by trimming common leading tabs from non-first non-empty lines before applying the content.
- Updated indentation detection to rely on non-empty lines only, preventing blank lines from skewing the minimum-indent calculation.
- Updated the warning text to describe the automatic indentation correction and clarified that ~ body content should be written at column 0.
- Removed `SearchDb` APIs and `searchDb` fields, dropping db-backed state from native and agent sessions.
- Replaced crate export `fff` with `fd`, moving fuzzy-find bindings into `fd.rs`.
- Removed `SearchDb`/picker fast-path logic from `glob` and `grep`, simplifying scan flow and dropping db args.
- Removed `SearchDb`/`getSearchDb` wiring from extension, tool, and task context constructors across coding-agent.
- Added over-indentation validation warnings in chunk-edit normalization for suspicious `~` body line formatting.
- Removed `bytes`, `fff-grep`, `fff-search`, and `blake3` deps, adding `grep-searcher = "0.1"`.
- Changed chunk edit normalization to prefer write operations, then replace, insert, then delete, with empty write values now treated as clear-content writes.
- Allowed space motions in vim input as `<Space>`, handled them as movement and rendered in error output via token display.
- Adjusted benchmark retry flow to reset files on each retry, reduced per-run call limits, and lowered the default per-turn timeout.
- Normalized chunk edit parsing now detected and warned on entries with multiple write/replace/insert operations, selected one operation by precedence, and ignored the rest.
- Execution now appended those normalization warnings and included them when a chunk edit produced no content changes.
- Updated chunk-edit and vim tool guidance plus vim rendering to document stricter edit usage and expose the current cursor position in output.
When models send multiple operation fields (write + replace + insert),
pick the most substantive: insert > replace > write > delete.
This prevents errors for confused models that populate all fields.
Also properly maps write:null to the delete op instead of put-empty,
and adds the missing case-delete handler in toNativeEditOperation
(fixing a pre-existing TS exhaustiveness error).
- Fixed `G`/`gg` motions to distinguish "no count" (go to last/first line) from explicit count.
- Added parsing for literal `\x1b`/`\r` bytes and backslash escape sequences (`\r`, `\e`, `\n`, `\t`).
- Updated `#readCount` to return `hasCount` flag propagated through operator and motion resolution.
- Synced vim buffer fingerprint from disk on reuse to handle LSP writethrough reformats.
- Updated `AgentSession` and `createAgentSession` to resolve active edit tool names via `resolveEditToolName`.
- Filtered inactive edit variants with `filterInactiveEditToolName` so tool listings expose the active edit mode.
- Normalized requested edit-capable tool names with `normalizeToolNamesForEditMode` during activation and startup.
- Synced edit-tool mode after model changes so the active tool swaps between `edit` and `vim` automatically.
- Enabled per-file partial updates by threading `onUpdate` through `EditTool` and `executePerFile`.
- Updated `ToolExecutionComponent` to render multi-file edit `perFileResult` entries as separate boxes with pending state.
- Added `vim` as a supported edit mode and resolved mode-specific active tool names.
- Migrated chunk-edit requests from legacy `op`/`content` to `path` plus `write`, `replace`, and `insert`.
- Replaced chunk-edit internals with `put`/`replace`/`delete` operations and ID-based selection.
- Updated chunk prompts/output docs to document ID-based selectors and `write: null` deletions.
- Switched chunk and grep render output to `@`/dash-style anchors and updated file-count behavior for multi-file edits.
- Updated multi-file result rendering with distinct file counting and pending-file progress indicator.
- Refreshed chunk-mode and chunk-tree tests for the new contract and anchor style.
- Added multi-file edit payload support by requiring per-entry `edits` arrays across patch, hashline, replace, and chunk modes.
- Changed edit schemas and validators to move `path` (and `sel`->`path`) and op data into each edit entry.
- Changed edit execution flow to parse `file:selector` paths, run single-entry executors per file, and return grouped per-file results.
- Updated chunk diff rendering and test expectations to emit consistent anchor gutters with spaced pipes and `^` head-line markers.
- Added hierarchical chunk grep output grouped by directory, file, and chunk with aligned chunk anchors.
- Updated chunk rendering to show clipped head/tail context with explicit truncation and expand markers.
- Changed chunk edit and streaming validation to use chunkToolEditSchema-based checks for safe edit detection.
- Enhanced grep rendering to use structured ChunkedGrepMatch data with displayPath and chunk checksum metadata.
- Added parse_error_lines to ChunkTree and threaded parse-error line metadata through tree creation.
- Changed count_parse_errors to return (count, line numbers) and collect recursive parse-error positions.
- Added hashline edit input resolution so computeHashlineDiff accepts loc/content edits and throws on invalid payloads.
- Fixed apply_edits error rendering to fall back to full-tree context when edited chunks have downstream parse errors.
- Fixed markdown fenced code block rendering to preserve literal indentation instead of normalizing to tabs.
- Added validation to reject chunk selector operations on non-existent files with descriptive error message.
- Fixed chunk deletion to properly derive parent paths and mark ancestors with appropriate focus modes.
- Simplified path segment matching logic by removing unnecessary normalization of requested_segment parameter.
- Added comprehensive test coverage for fenced code block caret reads, indentation preservation, and file-not-found error handling.
- Refactored chunk rendering to compute prologue and body line counts separately via new `chunk_head_body_lines()` function.
- Updated ellipsis marker format from line count to line range selection syntax (e.g., 'to expand above/below').
- Modified `render()` method signature to accept `head_lines` and `body_lines` parameters for precise line count display.
- Simplified no-changes response in chunk edit mode to omit redundant text when content matches.
- Expanded chunk-edit documentation with compound statement examples and region suffix behavior for non-code formats.
- Simplified chunk region notation from @head/@body/@tail/@decl to ^/~ suffix format across all modules.
- Removed ChunkRegion::Tail and ChunkRegion::Decl enum variants and updated region matching logic accordingly.
- Added call-with-callback pattern detection via try_promote_call_with_callback() and trailing_callback_body() functions.
- Updated documentation and test fixtures to reflect new region selector syntax throughout codebase.
- Migrated language classifiers from imperative methods to declarative semantic rule tables with ClassifierTables and StructuralOverrides.
- Extracted node shape analysis into dedicated shape module with field priority constants and helper functions for AST traversal.
- Added schema module with language-aware node metadata and thread-local language context management.
- Centralized environment variable parsing across codebase using $flag(), $envpos(), and isBunTestRuntime() utilities.
- Added PI_CHUNK_AUTOINDENT configuration to control indentation normalization in chunk read/edit operations.
- Enhanced system prompt with instruction priority, output contract, tool persistence, and completeness guidelines.
- Added merge conflict detection and resolution API with hasConflicts() and conflictCount() methods to ChunkState.
- Implemented conflict marker parsing supporting standard and diff3-style formats with accept_ours() resolution.
- Extended ChunkKind enum with Hunk, Conflict, Ours, and Theirs variants for diff and merge conflict representation.
- Added virtual_content field to ChunkNode for rendering conflict branches and improved diff parsing with block-level file chunk handling.
- Implemented conflict metadata tracking across edits with validation preventing direct modifications to virtual conflict branches.
- Extended hashlineParseText to accept undefined in addition to null, preventing type errors when undefined is passed.
- Updated null check to use loose equality (==) to handle both null and undefined cases.
- Added `/force` slash command and `ToolChoiceQueue` system for managing tool-choice directives with lifecycle callbacks and requeue semantics.
- Added `setForcedToolChoice()`, `peekQueueInvoker()`, `buildToolChoice()`, `steer()`, and `getToolChoiceQueue()` methods to AgentSession and ToolSession APIs.
- Refactored tool-choice override mechanism from simple override to queue-based system with generator directives, lifecycle callbacks, and requeue preservation.
- Removed `PendingActionStore` class and replaced with `ToolChoiceQueue`; updated `ResolveTool` and custom tool loader to use queue invokers.
- Fixed tool-choice queue cleanup on agent loop abort and requeue semantics to preserve callbacks across abort cycles.
- Renamed indent normalization functions from tab-based to space-based naming (normalize_to_tabs -> compact_indent, denormalize_from_tabs -> expand_indent).
- Changed canonical indentation representation from tab characters to single leading spaces per indent level across chunk rendering and editing.
- Updated documentation and type annotations to reflect space-based indentation convention in chunk edit tool and native bindings.
- Simplified indent expansion logic to count whitespace characters instead of parsing individual characters.
- Added `@decl` chunk region selector for targeting semantic declarations without leading trivia.
- Updated chunk edit documentation with visual region boundary diagram and critical narrowest-region requirement warning.
- Implemented `Decl` variant across Rust types, NAPI bindings, and TypeScript definitions with full region range logic.
- Added inline hunks emission for effectively-leaf chunks to preserve hunks when children are filtered by focus.
- Improved type safety in LSP startup test by replacing truthy check with explicit function type check.
- Added `onAssistantMessageEvent` callback to Agent API for inspecting and aborting assistant streaming events.
- Added `setAssistantMessageEventInterceptor()` method to dynamically update assistant message event handlers.
- Converted `checkAutoGeneratedFileContent()` from async to synchronous for improved streaming edit abort detection performance.
- Implemented LRU caching in auto-generated file detection with early path-based checks to prevent unnecessary edits.
- Refactored streaming edit pre-caching to use assistant message event interception for real-time abort capability.
- Extracted `peekFile()` utility for efficient file prefix reading with pooled buffer reuse strategy.
- Remove unused ParsedChunkTarget type alias (lint error)
- Increase setImmediate timing in history storage compat test
- Mock warmPythonEnvironment in python tool tests
- Fix tlaplus LSP test to spy on $which instead of Bun.which
- Renamed ChunkRegion::Inner variant to Body across Rust and TypeScript for clearer semantics.
- Renamed chunk edit tool parameter from target to sel and made op required instead of optional.
- Removed region aliases (prologue, epilogue, inner) and simplified region validation to accept only head, body, tail.
- Replaced db.exec() calls with db.run() for SQL execution in auth-storage, agent-storage, and history-storage.
- Enhanced chunk edit documentation with comprehensive examples, indentation rules, and CRC refresh guidance.
- Improved chunk statement merging logic to consolidate leaf statements into parent function bodies by default.
- Renamed chunk region identifiers from Container/Prologue/Body/Epilogue to Head/Inner/Tail with updated semantics.
- Changed default chunk edit region behavior to omit @region suffix for full chunk targeting instead of explicit @container.
- Made trait and interface members addressable by preventing collapsing in chunk resolution logic.
- Updated chunk read and edit documentation with new region names and simplified selector examples.
- Refactored region handling to use Option<ChunkRegion> for optional region targeting across Rust and TypeScript implementations.
- Added ParsedSelector struct and is_known_region_name() validation function for improved region parsing.
- Refactored chunk tree initialization to use explicit prologue/epilogue byte boundaries instead of None values.
- Extracted chunk resolution logic to use split_selector_crc_and_region() helper for improved code reuse.
- Reorganized package.json exports across multiple modules (autoresearch, cli, dap, edit, modes) for better API surface clarity.
- Updated test expectations for Go receiver method rendering and chunk selector formats to match refactored output.
- Consolidated notebook conversion logic and removed unused _createErrorToolResult helper function.
- Improved leading trivia preservation in chunk edits by detecting and maintaining line prefix whitespace.
- Extracted line-hash utilities into dedicated module for improved code organization.
- Moved computeLineHash, formatLineHash, and HASHLINE_NIBBLE_ALPHABET from hashline.ts to new line-hash.ts module.
- Updated import paths across 6 files to reference new line-hash module location.
- Consolidated line-hashing functionality into single-responsibility module without behavior changes.
- Extracted prompt rendering and formatting utilities from coding-agent to centralized pi-utils package with new API surface (prompt.render, prompt.format, prompt.registerHelper).
- Migrated parseFrontmatter utility from coding-agent to pi-utils package; updated 8 files to import from @oh-my-pi/pi-utils.
- Removed 170-line prompt-format.ts module and consolidated 192 lines of Handlebars helper registrations into pi-utils prompt module.
- Updated 60+ files across coding-agent and typescript-edit-benchmark to use new prompt.render() and prompt.format() API from pi-utils.
- Simplified prompt-templates.ts by delegating core functionality to pi-utils while retaining custom helper registrations (jtdToTypeScript, jsonStringify, etc.).
- Added region-based chunk targeting with @container, @prologue, @body, @epilogue selectors for precise edit operations.
- Simplified chunk edit operations from 6 variants to 5 (replace, before, after, prepend, append) with unified region parameter.
- Removed checksum requirement from insert operations; only replace operations require #CRC suffix in selector.
- Added canonical indentation normalization with normalize_indent parameter for consistent tab-based rendering across file types.
- Refactored chunk selector format from separate crc/anchor fields to unified selector#CRC@region syntax for mutations.
- Added UnsupportedRegion status to chunk read operations for explicit handling of region availability per chunk type.
can1357