- Simplified chunk path parsing to extract selector separately from CRC field.
- Refactored chunk edit operations to conditionally strip CRC for auto-accepted batch operations.
- Enhanced chunk edit preview formatting to display operation types with target and line ranges.
- Improved chunk state rendering with clamped visible range and unified notice message format.
- Refactored error handling in chunk resolution from map_err to let-else pattern.
- Added MacOSPowerAssertion native module to prevent idle-sleep on macOS during active sessions.
- Integrated power assertion lifecycle management into coding-agent session with automatic start/stop.
- Implemented N-API bindings for macOS IOKit power assertions with RAII cleanup and cross-platform no-op fallback.
- Reformatted indentation from spaces to tabs across Rust chunk module for consistency.
- Refactored chunk selector resolution to extract and preserve raw selector strings separately from parsed CRC checksums.
- Reorganized chunk state lookup infrastructure with dedicated maps for checksum, leaf, and suffix-based chunk resolution.
- Simplified batch operation CRC validation to auto-accept stale checksums for subsequent operations on the same chunk.
- Unified TypeScript interface and Nix attrset chunk classification with consistent naming and nested expression handling.
- Extracted clipboard utility functions to dedicated module with improved OSC 52 and Termux support.
- Updated chunk read formatting with anchorStyle parameter and ellipsis standardization for improved consistency.
- Removed error on stale CRC when a chunk was already modified by an earlier batch op; the model can only know the pre-batch checksum.
- `ensure_batch_operation_target_current` now returns `Ok(true)` to signal auto-accept, skipping redundant CRC validation.
- Updated prompt to clarify batched line-scoped edits are supported and to require fully qualified chunk paths.
- Replaced nested operation objects with a flat edit schema using a single `target` field.
- Merged `sel` and `crc` into a unified `target: "chunk#CRC"` string copied from read output.
- Replaced `operations` array with `edits` and added `append`, `prepend`, `after`, `before` fields for insert positioning.
- Removed `defaultSelector` and `defaultCrc` top-level params; CRC is now always explicit per-edit.
- Fixed chunk edit operations to extract and use embedded CRC checksums from selectors as fallback validation.
- Refactored patch operations to parse selectors and strip CRC suffix before processing insert, replace, and delete commands.
- Extended parseChunkSelector to return optional CRC field extracted from selector suffix for validation.
- Improved operator precedence clarity in read tool by adding parentheses around nullish coalescing expression.
- Migrated native bindings from TypeScript wrappers to NAPI-RS generated modules with auto-generated type definitions and runtime enums.
- Replaced chunk tree API with stateful ChunkState class supporting render, edit, and resolve operations with improved error handling.
- Converted callback signatures to error-first pattern (error, result) for shell, PTY, glob, and grep operations.
- Introduced type-safe enums for MacOSAppearance, GrepOutputMode, KeyEventType, ImageFormat, and AstMatchStrictness replacing string literals.
- Refactored chunk tree implementation with dedicated modules for edit, indent, resolve, and state management with comprehensive validation.
- Moved clipboard utilities from native bindings to coding-agent package with improved OSC 52 and Termux compatibility.
- Added `anchorStyle` setting ("full", "kind", "bare") to control anchor name verbosity in chunk output.
- Changed anchor tag delimiters from `` to `[…]` and gutter separator from `│` to `|`.
- Changed edit response to render only changed hunks with context instead of the full chunk tree.
- Added `read.prosechunks` setting to enable chunk rendering for prose files (markdown, text, log, asciidoc, restructuredtext) in chunk edit mode.
- Added `read.explorechunks` setting to show chunk tree without checksums for read-only agents like explore.
- Implemented prose language detection and conditional chunk skipping logic based on file type and agent capabilities.
- Fixed zero-width insert detection to derive target indent from neighboring lines instead of replaced range.
- Improved indent selection for body-level insertions by picking deeper indent between two neighbors.
- Updated error messages to clarify insert vs splice operations and line range validation.
- Modified assertChecksum() return type to handle cases with default CRC and no explicit selector.
- Distributed language-specific AST classification logic from defaults module to individual language modules for 15+ languages.
- Simplified defaults module to minimal catch-all fallbacks, removing 341 lines of match-based classification logic.
- Consolidated chunk edit operations by removing splice operation and unifying with line-scoped replace parameters.
- Simplified chunk rendering output format by reducing thresholds and changing line count display from 'lines' to 'ln' suffix.
- Removed PI_CHUNK_SPLICES environment variable and chunkSplicesEnabled conditional logic throughout codebase.
- Changed chunk edit operation format from flat `op` field to nested keyed union structure with operation name as object key.
- Added parseKeyedChunkOp() function to normalize both keyed and legacy flat operation formats for backward compatibility.
- Enhanced chunk selector sanitization with filename prefix stripping and case-insensitive CRC checksum matching.
- Updated chunk edit prompt documentation and test suite to reflect new nested operation JSON structure.
- Added `new_segment` parameter to `init_experiment` to force new segment creation when contract fields match.
- Added `skip_restore` parameter to `log_experiment` to preserve working tree state and pre-existing uncommitted changes.
- Changed `log_experiment` to revert only run-modified files instead of entire working tree, preserving user changes.
- Changed `init_experiment` to detect matching contract fields and skip re-initialization unless `new_segment=true`.
- Added git status parsing utilities to track pre-run dirty paths and distinguish tracked vs untracked modifications.
- Removed secondary metrics validation requirement, making secondary metrics informational only.
- Fixed indentation and formatting across multiple files for consistency.
- Reformatted code blocks to use tabs instead of spaces and improved line breaks for readability.
- Added connection timeout configuration to benchmark runner for early abort on no events.
- Implemented two-phase timeout strategy in benchmark runner with connection and activity phases.
- Migrated react-edit-benchmark package to typescript-edit-benchmark with pi-mono source repository.
- Added InProcessClient implementation to eliminate subprocess spawning overhead in benchmark runs.
- Extended benchmark configuration with chunk edit variant, retry limits, and conversation dump support.
- Refactored runner.ts to support both RPC and in-process client modes with improved error telemetry.
- Cleaned up 129 benchmark report files from react-edit-benchmark/runs directory.
- Added LSP diagnostic versioning support to track document versions and suppress stale diagnostics.
- Added options parameter to `waitForDiagnostics` and `getDiagnosticsForFile` with version filtering capabilities.
- Enabled `versionSupport` in LSP client capabilities to receive diagnostic version information from servers.
- Added test coverage for stale diagnostic suppression scenarios in LSP diagnostic freshness.
The agent had no way to infer the mcp:// prefix needed to read MCP
server resources. Attempting <server>://<resource> directly fails.
All other internal URL schemes (skill, rule, memory, agent, etc.) are
already listed in the Internal URLs section of the system prompt.
Added mcp://<resource-uri>. URI resolution: exact resource listings
first, then RFC 6570 URI templates advertised by connected servers.
- Fixed memory leak by cancelling idle compaction timer on event controller disposal.
- Fixed session resumption to preserve last non-empty session when starting fresh.
- Fixed stash detection to use git ref resolution instead of output parsing for reliability.
- Fixed secret obfuscation to deobfuscate restored session messages locally while keeping LLM messages obfuscated.
- Fixed stash pop operation to preserve staged changes with --index flag after task branch merges.
- Changed idle compaction settings from enum to numeric type for flexible configuration.
Ensures exit_plan_mode waits for all previous tools to complete
before checking if the plan file exists. Prevents race condition
when LLM calls exit_plan_mode before write completes.
- Fixed PR checkout tool to resolve worktree paths to canonical form using fs.realpath().
- Refactored test mocks to use vi.spyOn for git module functions instead of inline implementations.
- Updated test setup to pass Settings.isolated() with edit.manageImports enabled to EditTool.
- Added afterEach hooks across test suites to restore mocks after each test execution.
Compaction and tool-output pruning can rewrite the session JSONL in
place, shrinking the file. When stat.size < bytesRead, the cache is
now invalidated and the file is re-read from scratch, preventing the
observer from getting stuck on a stale transcript.
can1357