Commit Graph

39 Commits

Author SHA1 Message Date
can1357 caeaf4e4d2 feat(coding-agent): added builtin default rules and disable controls
- Added 14 bundled TTSR rules (TypeScript and Rust conventions) embedded into the binary via the lowest-priority `builtin-defaults` provider.
- Extracted rule bucketing into `bucketRules` with support for `disabledRules` and `builtinRules` settings.
- Added `ttsr.builtinRules` and `ttsr.disabledRules` settings to control which rules are active per session.
2026-05-31 02:09:55 +02:00
can1357 dfa6007f36 feat(coding-agent): removed recipe tool and all runner implementations
- Deleted RecipeTool, runner logic, and all task runner backends (just, make, cargo, pkg, task).
- Removed recipe from BUILTIN_TOOLS, auto-injection in createTools, and HTML export renderer.
- Deleted recipe tool prompt template and runner module exports.
2026-05-31 01:42:47 +02:00
can1357 9ce250eb99 chore: remove deprecated calc tool as it is completely useless with eval 2026-05-30 04:05:26 +02:00
can1357 ef5cbef51f feat(coding-agent): added resolve-based plan approval flow in coding-agent
- Removed ExitPlanModeTool and deleted exit-plan-mode docs/tests, dropping the old approval contract outputs.
- Replaced plan-mode approval flow from exit_plan_mode to resolve across session, SDK, controllers, and discovery.
- Added standing resolve handler accessors and updated resolve routing for queued or standing approval handlers.
- Added PlanApprovalDetails and enforced normalized, validated approval titles with readable plan-file requirements.
- Extended resolve schema and invocation signatures with optional extra metadata and reason trimming behavior updates.
- Updated plan and resolve prompts and changelog guidance to require resolve action, reason, and extra.title for apply/discard.
2026-05-14 05:33:30 +02:00
can1357 075e2f47ad fix(coding-agent/export): prevented HTML template $ substitution expansions
- Switched template CSS/JS inlining replacements to callback form in generation scripts to avoid `$` replacement expansion semantics.
- Updated HTML export generation to use callback-based replacements for theme variables and session data injection to prevent accidental `$` substitution parsing.
- Added regression tests for the inlined script ensuring literal `$'` regex tokens remain intact, no closing HTML tags are injected, and the script parses via `new Function`.
2026-05-12 11:15:38 +02:00
can1357 028a442f18 feat(coding-agent): added parser support for t/rst in Cell eval
- Introduced canonical `*** Cell` headers with `t:` and `rst` attributes in eval prompts, schema, and docs.
- Updated parser and grammar to parse `*** Cell` blocks, stop on `*** End`/next header/EOF, and handle invalid `rst` with errors.
- Added quote-aware attribute tokenizers and split HTML eval parsing into `Cell` and legacy `Begin` handlers with `py` defaults.
- Expanded parsing behavior and tests for `rst` booleans, title aliases, abort boundaries, and stray-line skips between cells.
2026-05-12 10:01:56 +02:00
David Marshall c8d4f22b59 fix(coding-agent): render developer-role messages in /export and /tree
The HTML export feed, sidebar tree, and TUI session tree did not handle
the developer role, so plan content injected after /plan approval (and
any other developer messages) was hidden from /export and shown as a
bare [developer] label in /tree.

Renders developer messages in the main feed with a dimmed
.developer-message style, labels them in the sidebar tree, counts them
in header stats, and shows their content in the TUI tree selector so
search matches the body.

Closes #753.

Co-Authored-By: omp <noreply@oh-my-pi.dev>
2026-05-11 10:42:17 -05:00
can1357 8b92ec937e feat: gpt-5 harmony errata fixes
- Replaced `===== ... =====` eval cell headers with `*** Begin ` / `*** End ` markers; legacy format remains renderable in HTML exports.
- Replaced hashline patch grammar with `*** Begin Patch` / `*** End Patch` envelope; old inputs without the envelope are still accepted.
- Extracted `sniffEvalLanguage` into a shared `sniff.ts` module reused by the parser and tool.
- Added `docs/ERRATA-GPT5-HARMONY.md` and `scripts/session-stats/harmony_backtest.py` documenting and backtesting the GPT-5 Harmony-header leak defect.
2026-05-10 19:52:44 +02:00
can1357 1c77a28b85 feat(export): added collapsible HTML tool-header chips for intent metadata
- Added a collapsible tools header with chips and intent metadata styles in HTML exports.
- Added eval tool support with cell-level parsing and inferred language syntax highlighting.
- Added dedicated renderers for search, recipe, and irc tool calls and separated `_i` intent from tool args.
- Enhanced edit, ast_edit, find, search, and gh renderers with richer headers, fields, and option badges.
- Changed power-assertion state so assertions were prompt-scoped and no longer blocked after aborts.
2026-05-10 09:44:17 +02:00
can1357 8c323666be feat: added ordered systemPrompt arrays and normalized context prompts
- Converted systemPrompt APIs and state types to ordered `string[]` across agent, AI, and coding-agent surfaces.
- Added `normalizeSystemPrompts` and applied it to context normalization before building provider request payloads.
- Updated AI providers to emit separate normalized prompt blocks/messages instead of a single merged system prompt.
- Removed dedicated `projectPrompt` state and remapped that context into system-context buckets in session, dump, and token accounting.
- Aligned tests and changelogs to pass and assert `systemPrompt` as arrays with ordered prompt semantics.
2026-05-04 15:20:26 +02:00
can1357 f0e9a830ff refactor(packages/coding-agent): migrated search args to paths arrays
- Switched search/ast_grep/ast_edit/find inputs from scalar path fields to required `paths` arrays.
- Reworked path resolution to normalize and expand each `paths` entry via explicit helpers in `src/tools/path-utils.ts`.
- Updated search and find tool-call rendering to display explicit `paths` values in mode overlays and export views.
- Updated tool prompt docs and examples to document `paths` array inputs for search, grep, find, and AST tools.
- Raised the default search match limit from 20 to 500 and updated limit-reached messaging.
2026-05-02 04:34:39 +02:00
can1357 cf60e6df51 feat(coding-agent): implemented eval framework and replaced python tool
- Added a unified eval framework with parser grammar, backend interfaces, and JS/Python execution result types.
- Added eval tool docs and updated prompts for fenced cells, `eval.py`/`eval.js`, and fallback behavior.
- Replaced the built-in `python` tool with `eval` across registry, rendering, interactive modes, and tool settings.
- Migrated Python execution runtime from `src/ipy` to `src/eval/py`, renamed state fields, and removed legacy introspection.
- Refactored browser tooling from in-process VM helpers to worker-managed tab supervisors and protocol transport.
- Added eval parser fallback and JS tool-bridge tests, updated imports, and removed obsolete python-mode suites.
2026-04-30 18:08:37 +02:00
can1357 537233896a feat(coding-agent/tools): added browser tool open-run-close async flow
- Removed legacy actions and reworked tool schema to open/run/close with required open-before-run async-JS flow.
- Added named tab reuse with browser-kind checks and close options all/kill with ref-counted disposal.
- Implemented launch/CDP hardening by finding free ports, reusing live targets, waiting for readiness, and killing process trees.
- Added readable result extraction, selector and action visibility checks, and screenshot/observation support in run execution.
2026-04-30 13:04:52 +02:00
can1357 5003996a01 feat(coding-agent): added content-based todo matching for write/commands
- 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.
2026-04-30 06:40:53 +02:00
can1357 8e5ad4665c feat(coding-agent/tools): added unified job tool for poll and cancel
- Added a unified `job` prompt and removed `poll` and `cancel-job` prompts, documenting merged async actions.
- Renamed `PollTool` to `JobTool` and replaced `poll`/`cancel_job` tool exports with a unified `job` tool.
- Expanded `JobTool` schema to accept `poll` and `cancel` IDs, adding cancel-first execution for cancel-only requests.
- Consolidated poll/cancel rendering in `renderJob`, mapping `await`, `poll`, and `cancel_job` keys to the unified job renderer with action badges.
- Updated bash/task prompts and tests to use `job` for polling and cancellation flows, including JobTool auto-background checks.
2026-04-26 09:31:57 +02:00
can1357 8321996758 feat(tools): implemented op-based github tool replacing gh_* registrations
- 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.
2026-04-26 05:48:07 +02:00
can1357 ecd1554eba feat: renamed subagent handoff flow to use yield instead of submit_result
- 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.
2026-04-26 00:29:52 +02:00
can1357 d82377cda8 revert: "read-to-open"
This reverts commit c48d2e6080.
2026-04-24 22:36:44 +02:00
can1357 c48d2e6080 feat(coding-agent): implemented read-to-open tool aliasing in runtime
- 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).
2026-04-24 19:13:11 +02:00
can1357 fb59c45439 feat(vim): added escape/CR literal parsing and count-aware G/gg motions
- 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.
2026-04-13 17:01:26 +02:00
can1357 ae85ed4cc7 feat(export): added richer export HTML tool-call rendering to debug calls
- Added richer session-export HTML rendering for tool calls, metadata badges, and todo trees.
- Added a persistent JavaScript execution tool backed by node:vm with cross-session KV/pubsub support.
- Replaced pythonExecution paths with jsExecution handling across tool labels and message rendering.
- Refactored tool-call rendering into dedicated renderers with shared helpers and fallback error handling.
2026-04-11 09:59:07 +02:00
can1357 7fb18faf4c fix(coding-agent): backported pi-mono changes (1feccfed..b21b42d0)
packages/ai:
- feat: expose provider responseId on AssistantMessage
- feat: lazy-load provider modules for faster startup
- fix: hash foreign Responses API tool call IDs exceeding 64-char limit
- fix: ignore null chunks in openai-completions streams
- fix: keep image tool results inline for Gemini 3+ and Antigravity
- fix: correct Bedrock Claude 4.6 context window to 200k
- fix: support prompt caching for Bedrock application inference profiles
- fix: add OpenRouter reasoning payload format
- fix: ignore placeholder Vertex API keys
- fix: skip AJV validation in restricted runtimes
- fix: Anthropic OAuth client injection and responseId extraction
- fix: Codex incomplete/failed response status handling

packages/agent:
- fix: defer steering until after tool execution completes

packages/tui:
- feat: namespaced keybinding IDs with KeybindingsManager conflict detection
- feat: configurable select list column sizing (#2154 by @markusylisiurunen)
- fix: stream truncateToWidth for large strings
- fix: skip Termux height redraws
- fix: stop evicting unrelated default keybindings
- fix: resolve raw backspace ambiguity on Windows Terminal
- fix: clear stale scrollback on session switch (#2155 by @Perlence)
- fix: remove trailing markdown block spacing (#2152 by @markusylisiurunen)

packages/coding-agent:
- feat: add resizable share sidebar (#2435 by @dmmulroy)
- feat: emit OSC 133 command-executed marker
- feat: reload custom themes from disk watcher
- feat: add --fork session flag
- feat: file mutation queue for serialized writes
- feat: initial message consolidation utility
- fix: keybindings migrated to namespaced IDs
- fix: resolve waitForRetry() race when auto-retry produces tool calls
- fix: handle slash-delimited /model refs
- fix: refresh active model after provider updates
- fix: extended transient error patterns for retry
2026-03-22 18:28:40 +01:00
can1357 2d90ed62f3 fix(ai): handle redacted thinking + rebuild export template
- Added RedactedThinkingContent type to support secure encrypted reasoning blocks in Anthropic messages.
- Updated message transformation logic to preserve signed thinking blocks and redacted thinking for latest assistant messages in Anthropic conversations.
- Added handling for redacted_thinking events in Anthropic stream processing with type, data, and index fields.
- Added comprehensive tests validating redacted thinking block preservation and Anthropic thinking immutability during message transformation.
2026-03-05 01:51:46 +01:00
can1357 a83175c94c refactor: migrated imports to unified package root and consolidated skill discovery logic
- Consolidated @oh-my-pi/pi-utils subpath imports into single package root import across 100+ files.
- Moved tryParseJson utility from local web scrapers module to @oh-my-pi/pi-utils package for centralized JSON parsing.
- Renamed loadSkillsFromDir to scanSkillsFromDir and refactored skill discovery to use fs.promises.readdir instead of glob-based approach.
- Replaced custom parseJSON with tryParseJson across discovery modules for consistent error handling.
- Removed emitCustomToolSessionEvent method and cleanupSshResources function, consolidating shutdown logic into dispose method.
- Updated glob pattern construction to use GlobBuilder with literal_separator(true) for improved path handling.
2026-02-23 20:59:17 +01:00
can1357 95c9bc4f52 fix(coding-agent): fixed ttsr injection persistence timing 2026-02-18 02:03:47 +01:00
can1357 2249529e70 feat(coding-agent): added TTSR injection tracking and deduplication
- Added TTSR injection tracking with per-turn recording and deduplication to prevent repeated rule injections within the same turn.
- Changed TTSR message format to use custom message type with metadata fields for improved injection tracking and session persistence.
- Fixed TTSR repeat-after-gap mode to correctly restore injected rules from previous sessions and recalculate gap thresholds.
- Added test suite with 6 test cases covering TTSR repeat modes (once, after-gap, restored) and injection deduplication behavior.
2026-02-18 01:53:02 +01:00
can1357 09f6c5d7bb feat(coding-agent): implemented scoped TTSR rules with interrupt modes and unified discovery
- Added scoped TTSR rule matching with condition and scope fields supporting file globs and tool-specific filtering.
- Added ttsr.interruptMode setting to control when TTSR rules interrupt agent responses (never/prose-only/tool-only/always).
- Added support for loading rules, prompts, and commands from ~/.agent/ directory with fallback to ~/.agents/.
- Refactored rule discovery across all providers to use unified buildRuleFromMarkdown helper and per-stream-key buffering.
- Enhanced TTSR pattern matching to respect tool-specific scope filters and normalize file paths in glob matching.
2026-02-17 23:40:13 +01:00
can1357 fcd7ff4f84 refactor(dirs): centralized directory path utilities into @oh-my-pi/pi-utils/dirs module
- Extracted directory path utilities from multiple packages into a centralized '@oh-my-pi/pi-utils/dirs' module.
- Moved 30+ path helper functions (getAgentDir, getConfigRootDir, getPluginsDir, getMCPConfigPath, etc.) from scattered locations into a single shared utility module.
- Consolidated APP_NAME, CONFIG_DIR_NAME, and VERSION constants into the centralized dirs module for reuse across packages.
- Updated 70+ import statements across packages/ai, packages/coding-agent, packages/stats, and packages/tui to use the new centralized module.
- Removed local path construction logic and replaced with utility function calls for improved maintainability and consistency.
- Deleted packages/coding-agent/src/extensibility/plugins/paths.ts as its functions were moved to the centralized dirs module.
2026-02-13 15:06:05 +01:00
can1357 acf8ab5225 style: stylistic changes 2026-02-10 07:39:39 +01:00
can1357 de397b3b04 feat(coding-agent): restored plan mode on resume from session
- Added ModeChangeEntry type export to public API for tracking agent mode transitions.
- Added mode and modeData fields to SessionContext to track active agent mode state across sessions.
- Added appendModeChange() method to SessionManager for recording mode transition entries.
- Added plan mode state restoration from session entries when resuming interactive mode sessions.
- Updated HTML export filter to treat mode_change entries as settings entries alongside model changes and thinking level changes.
- Added type validation for tool arguments in HTML export template with error handling for invalid values.
2026-02-06 02:55:41 +01:00
can1357 bfe175fc01 feat(natives): backported fixes from pi-mono (82d7da878..9ce00079) 2026-02-06 01:55:42 +01:00
can1357 1f7c4f6f90 refactor(stream-parsing): restructured stream utilities to use Web standard APIs and generic SSE parsing
- Refactored SSE stream parsing to use generic `readSseJson` utility instead of domain-specific handlers across multiple packages.
- Migrated from Node.js Buffer API to Web standard APIs (Uint8Array, TextDecoder, DataView) for cross-platform compatibility.
- Simplified stream transformation pipeline by consolidating multiple stream operations into unified `createTextLineSplitter` utility.
- Refactored `ptree.ts` to remove complex stream pumping infrastructure and simplify stderr handling with direct async iteration.
- Rewrote stream utilities to operate at binary level with byte-level parsing for improved efficiency and reduced string allocations.
- Updated TypeScript configuration to include DOM.AsyncIterable type definitions for async iterable DOM API support.
2026-02-05 10:59:47 +01:00
can1357 ef415e863b feat(coding-agent): refactored settings system with new singleton API and unified schema
- Replaced SettingsManager class with new Settings singleton providing synchronous get/set API and background persistence.
- Introduced settings-schema.ts as single source of truth for all configuration definitions with 100+ settings organized into logical groups.
- Migrated from method-based settings access (getTheme(), setTheme()) to path-based access using dot notation (settings.get('theme'), settings.set('theme', value)).
- Removed 2035-line settings-manager.ts file and replaced with modular settings.ts (693 lines) and settings-schema.ts (836 lines) for improved maintainability.
- Unified settings schema into single source of truth eliminating duplicate definitions across settings-defs.ts and settings-manager.ts.
2026-02-01 08:08:58 +01:00
can1357 57a3650cc6 fix: backport fixes from pi-mono (3635e45f..9f3eef65f)
packages/ai:
- feat: HTTP proxy support via environment variables
- fix: correct provider error message typo
- fix: filter deprecated OpenCode models from generation

packages/tui:
- fix: scrollback overwrite when appending lines past viewport
- fix: keep overlays centered across resizes
- fix: handle multi-line text in insertTextAtCursor()

packages/coding-agent:
- fix: add /model instruction to no models warning
- fix: active path highlighting in HTML exports
2026-01-27 19:47:36 +01:00
can1357 779ca4872b style(deps): migrated from Prettier to Biome and updated formatting rules
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
2026-01-24 04:20:19 +01:00
can1357 e22d123009 refactor(fs): migrated remaining sync file operations to async
- Converted readdirSync, readFileSync, and statSync to async readdir, readFile, stat across skills and agent discovery.
- Made scanDirectoryForSkills async and refactored custom directory scanning to use Promise.all for concurrent processing.
- Updated agent discovery to use fs/promises for async file reading and refactored helper patterns.
- Added AgentParsingError exception class for better error handling during agent parsing.
- Added filesystem error type guards (isEnoent, isEacces, isPerm, etc.) to pi-utils for safe error checking.
- Added color manipulation utilities to pi-utils for accessibility features.
- Added color-blind mode setting to settings manager.
- Migrated plugins, settings, and config modules from sync to async file operations.
- Updated error handling to use new pi-utils type guards for type-safe checking.
2026-01-24 03:18:03 +01:00
can1357 f66e5dba9b build(config): refactored build and TypeScript configuration with Bun loaders
- Removed WASM generation script; use Bun `wasm?raw` loader for imports.
- Added bunfig.toml with loaders for `.md`, `.py`, and `.wasm?raw` text imports.
- Added types/assets/index.d.ts for global TypeScript module declarations.
- Unified TypeScript configuration with tsgo-based checking across monorepo.
- Removed build and WASM steps from install and publish pipelines.
2026-01-24 00:03:52 +01:00
can1357 0fe761dc4b build(deps): refactored TypeScript and package configuration across monorepo
- Added tsconfig.publish.json files to all packages with optimized publish-time configuration.
- Updated all package.json scripts with prepublishOnly hooks for correct type checking during publish.
- Added @oh-my-pi/omp-stats path mappings to root tsconfig.json for consistent imports.
- Added WASM generation script for photon module and integrated into install:dev script.
2026-01-23 13:46:06 +01:00
can1357 cb5bbbf382 refactor(coding-agent): flattened directory structure, eliminated core/ folder
- Eliminated core/ directory (252 files, 23 subdirs → distributed)
- Reduced max nesting from 9 levels to 5 levels
- Promoted tool subdirs to top level: exa/, lsp/, patch/, task/, web/
- Merged web-scrapers/ + web-search/ into web/{scrapers,search}/
- Flattened modes/interactive/ to modes/
- Split execution/ into: ipy/ (python), exec/ (bash), ssh/
- Renamed ipy/python-*.ts to ipy/*.ts (executor, kernel, etc.)
- Flattened cursor/exec-bridge.ts to cursor.ts
- Created logical groupings: config/, session/, extensibility/, export/
- Updated all imports across 500+ files
2026-01-23 12:24:47 +01:00