- New agent-plugins provider discovers packages with a root plugin.json
targeting the canonical schema (agent-plugins.org) from marketplace
installs, --plugin-dir, and configured extension roots; skills/ and
mcp.json load per spec with closed-schema validation,
${PLUGIN_ROOT}/${PLUGIN_DATA} expansion, reserved subprocess
environment, instance-keyed data dirs, and per-component isolation.
- Package-boundary containment (spec §4.1) is enforced before every
read via the new contained-path helpers, including skill:// resource
access from the read tool and bash; plugin skill files must
realpath-resolve inside the plugin root (skills carry containRoot).
- Legacy claude-plugins/omp-plugins providers yield skills and MCP
surfaces of standard-targeting roots to the new provider and skip
fatally invalid packages.
- Client-generated HTTP/MCP/authorization headers win over configured
headers case-insensitively (Agent Plugins §7.2.1) via the new
header-policy fetch wrapper used by the HTTP and legacy SSE transports.
- headerPolicy: "origin-locked" pins configured headers to the configured
URL's origin: never forwarded across cross-origin redirects, and
method-changing redirects of JSON-RPC POSTs are refused.
- envPolicy: "literal" exempts stdio env values (and origin-locked
headers) from config-value resolution: no ambient env-name lookup, no
__omp_shell("command execution, empty values preserved.")
- Change the default MCP JSON-RPC request ID format from snowflake strings to sequential integers.
- Update server configuration schema, connection equivalence checks, and tests to reflect the new integer default.
Discovery collapses differently-named MCP entries that point at the same
command/args/env/cwd (or url/headers) into one connection, keeping whichever
loaded first and dropping the rest as aliases. requestIdFormat changes the bytes
sent on the wire, same as auth/oauth which the comparator already covers, so a
higher-priority alias lacking the field could shadow a lower-priority entry that
set it, silently falling back to string ids for a server that needs numbers.
Add requestIdFormat to isSameMCPConnection, normalized against its own default so
an explicit "string" is not treated as a different connection than leaving it
unset. timeout stays excluded, since it is a client-side knob that never touches
the wire.
The option was only present on the transport-facing `MCPServerConfig`, so a
value written in `.omp/mcp.json` or a standalone `.mcp.json` never reached the
transports: discovery normalizes config into the canonical `MCPServer` shape and
`convertToLegacyConfig()` rebuilds the transport config from it, and neither step
knew about the field. Setting `"number"` in the documented config path silently
kept the snowflake-string default, which is the hang the option exists to avoid.
Wire it through the same four places `timeout` already uses: the canonical
`MCPServer` shape, the two OMP-native loaders (with validate-and-warn on an
unrecognized value), and the legacy conversion. Foreign-format providers are
untouched, since the key is OMP-specific.
Also point the `MCPServerConfigBase` doc comment at `RequestIdAllocator` rather
than a helper name that never existed.
- Added a suppress load option so disabled servers still claim their
capability key: a project foo with enabled:false shadows a same-named
enabled user foo again, while scope-removed entries drop fully.
- Tool-name collisions now resolve by stable server+tool origin key
instead of manager array order, so reconnect re-appends cannot flip
the routed implementation.
- Review follow-up for PR #6787.
Applied the denylist and per-server enabled:false exclusions before connection-equivalence deduplication, alongside project scope, so a disabled higher-priority server can no longer shadow a differently-named equivalent enabled server and leave no connection. Parameterized LoadOptions<T> so the pre-dedup filter sees the typed item.
Fixes#6786
Applied the project-scope filter before connection-equivalence deduplication so a project server can no longer shadow a differently-named but equivalent user server and then be dropped, leaving none.
Fixes#6786
Deduplicated semantically identical MCP endpoints across provider-specific names while preserving provider priority and canonical direct names.
Kept the first registration on sanitized tool-name collisions and logged both origins.
Fixes#6786
Rules whose condition led with a PCRE-style inline flag group (e.g.
`(?i)`) never registered: `new RegExp("(?i)...")` throws in Bun/JS, so
the condition failed to compile and `TtsrManager.addRule` dropped the
rule as having zero usable conditions.
- Add `compileRuleCondition` in capability/rule.ts translating a leading
`(?i)`/`(?m)`/`(?s)` group into native RegExp flags; wire it into the
TtsrManager and both ttsr-cli compile sites.
- Strip surrounding quotes from scope tokens so a malformed
`scope: "text","thinking"` recovers to canonical `text`/`thinking`.
- Reparse each value in parseFrontmatter's YAML fallback so one bad line
can't leave sibling values wrapped in literal quotes.
Fixes#4796
Store MCP OAuth credentials under deterministic mcp_oauth:<url> ids in each
profile's agent.db with refresh material embedded, so a definition-only entry
in a shared project mcp.json resolves each profile's own credential instead
of profiles clobbering each other's auth.credentialId pointer.
- Refresh material is single-source: embedded credential fields win over the
config auth block (which may belong to another profile); legacy rows fall
back to the auth block wholesale
- Wire the 401 refresh hook off the resolvable credential, not the auth
block, so definition-only bindings refresh mid-session too
- The url-keyed fallback never overrides a pinned Authorization header
- Send prompt=consent by default (oauth.prompt to override, "" to omit) so
reauth can switch accounts past an active browser session
- /mcp reauth fails fast on stdio transports (with an mcp-remote ~/.mcp-auth
hint), probes http/sse without OAuth injection, GCs the superseded legacy
row only after the flow succeeds, and leaves definition-only entries
untouched on disk
- DCR-issued client secrets stay embedded in the stored credential and are
never written into config files; user-supplied secrets survive reauth
- Fixed help rendering so `--help` no longer triggers unrelated command loaders.
- Fixed startup span logging to emit markers only with PI_DEBUG_STARTUP set.
- Fixed logger startup trace behavior for `:start`, `:done`, and `:fail` phases.
- Fixed prompt template processing with cached raw-template compilation and safer formatting.
- Optimized symbol and tag parsing in prompt templates via manual parsers.
- Fixed help rendering so `--help` no longer triggers unrelated command loaders.
- Fixed startup span logging to emit markers only with PI_DEBUG_STARTUP set.
- Fixed logger startup trace behavior for `:start`, `:done`, and `:fail` phases.
- Fixed prompt template processing with cached raw-template compilation and safer formatting.
- Optimized symbol and tag parsing in prompt templates via manual parsers.
- Added astCondition to rule frontmatter parsing and rule metadata, with AST-grep normalization.
- Updated TTSR bucketing so astCondition-only rules are treated as interruptible matches.
- Added ts-redundant-clear-guard as a built-in JS/TS tool rule for guarded clear* calls.
- Added AST snapshot matching in agent sessions with per-stream cache throttling and cleanup.
The Agent Skills standard (agentskills.io/specification) uses
`disable-model-invocation: true` to hide skills from auto-discovery.
OMP only recognized `hide: true`. This patch treats both as equivalent,
improving compatibility with skills authored for Pi, Claude Code, and
other harnesses following the standard.
Changes:
- Check `disableModelInvocation` (camelCase after frontmatter parsing)
in all 3 skill-loading paths
- Add `disableModelInvocation` to SkillFrontmatter type with JSDoc
- Add regression test for disable-model-invocation frontmatter
- Add changelog entry
Ref: https://agentskills.io/specification#frontmatter-required
- 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.
- Added optional `hide` metadata to skill capabilities so `SKILL.md` frontmatter intent is preserved when skills are loaded.
- Filtered system prompt skill rendering to exclude `hide: true` skills from the `<skills>` listing while keeping them loadable.
- Added process-wide singleton instances for InternalUrlRouter, AsyncJobManager, and MCPManager.
- Changed internal URL protocols to resolve through registered sessions and scan all active roots/datasets for matches.
- Refactored agent, artifact, memory, rule, skill, jobs, and mcp handlers to use shared manager and rule/skill state.
- Removed per-session protocol/tool wiring and switched tests to initialize and reset global singleton state.
- Refactored logger.time() API to accept function references and arguments separately instead of wrapped callbacks.
- Replaced RingBuffer-based timing with wall-clock markers and async span tracking for improved timing accuracy.
- Updated 20+ call sites across executor, kernel, main, and tools modules to use new logger.time() signature.
- Removed parsePath() helper function and inlined path.split() calls in settings module.
- Added test case verifying model selection without auth validation during startup.
- Added `toExtensionId()` method to all capability types for granular extension identification and disabling.
- Added `disabledExtensions` and `includeDisabled` options to LoadOptions for filtering disabled capabilities by extension ID.
- Added plugin manifest support for `extensions` entry points with automatic discovery from installed plugins.
- Fixed skill loading to properly respect disabled skill names from custom directories.
- Improved cross-platform path handling by using `path.basename()` instead of string splitting in context file and state manager.
- Refactored capability index loading to validate source metadata and filter disabled extensions before processing.
- Added per-rule `interruptMode` override capability to TTSR interrupt logic via optional frontmatter field.
- Changed interrupt behavior to respect per-rule `interruptMode` settings with fallback to global `ttsr.interruptMode` configuration.
- Extended `Rule` and `RuleConfig` interfaces with optional `interruptMode` property for granular control.
- Updated rule discovery to extract and validate `interruptMode` from frontmatter with proper enum type checking.
- Removed complex fuzzy matching logic including Levenshtein distance calculation and similarity scoring in favor of a simpler glob-based suffix pattern approach. Replaced findReadPathSuggestions with findUniqueSuffixMatch that returns a path only when exactly one candidate matches, eliminating ambiguous suggestions. Removed legacy ttsr_trigger and ttsrTrigger fields from RuleFrontmatter interface.
* feat: monorepo-friendly discovery for AGENTS.md and skills
Support hierarchical config discovery in monorepos by walking up from
cwd through ancestor directories, combining files from all levels
instead of only checking the immediate working directory.
AGENTS.md context files:
- Change dedup key from file.level to file.level + depth, so context
files at different directory levels coexist instead of shadowing
- Root AGENTS.md and sub-project AGENTS.md are both included in the
system prompt, ordered from least specific to most specific
Skills:
- Modify all 4 providers with project-level skill directories (native,
claude, codex, opencode) to walk up from cwd through ancestors,
scanning for skills at each level
- Skills at closer directories win on name conflicts via existing
name-based dedup
Repo root boundary:
- Add findRepoRoot() utility that detects .git to identify repo root
- Add repoRoot field to LoadContext, computed once in loadCapability()
- All walk-up traversals (AGENTS.md, skills, nearest config dir) stop
at the repo root, preventing discovery from leaking outside the repo
- When not in a git repo, falls back to walking to filesystem root
Files changed:
- capability/fs.ts: add findRepoRoot()
- capability/types.ts: add repoRoot to LoadContext
- capability/index.ts: compute repoRoot in loadCapability()
- capability/context-file.ts: depth-aware dedup key
- discovery/agents-md.ts: bound walk-up at repo root
- discovery/builtin.ts: getAncestorDirs stopAt param, skill walk-up
- discovery/claude.ts: skill walk-up with repo root bound
- discovery/codex.ts: skill walk-up with repo root bound
- discovery/opencode.ts: skill walk-up with repo root bound
- extensibility/skills.ts: add repoRoot to inline LoadContext
* feat(agents-provider): add project-level discovery with ancestor walk-up for all capability types
The agents provider (.agent/.agents directories) previously only loaded
capabilities from the user home directory (~/.agent/, ~/.agents/). This
meant project-level .agents/ directories in monorepo roots were not
discovered when sessions started from subdirectories.
Add getProjectPathCandidates() helper that walks from cwd up to repoRoot,
scanning both .agent/ and .agents/ at each ancestor level. Apply this to
all six capability types: skills, rules, prompts, commands, context files
(AGENTS.md), and system prompts (SYSTEM.md). This matches the ancestor
walk-up behavior already present in the builtin (.omp), claude, codex,
and opencode providers.
All loaders now parallelize project-level and user-level scans via
Promise.all. Project-level results appear closest-first so dedup at the
capability layer picks the nearest override.
* fix(discovery): remove hard cap of 20 on ancestor directory walking
All walk-up loops already terminate naturally at repoRoot or filesystem
root. The depth < 20 / .slice(0, 20) / MAX_DEPTH caps were redundant
safety guards that would silently stop discovery in deeply nested
projects.
Removed from: agents.ts, agents-md.ts, builtin.ts, claude.ts, codex.ts,
opencode.ts, and corresponding test files.
* fix(agents-provider): set depth on project-level ContextFile entries for correct dedup
loadContextFiles was creating project-level ContextFile entries without
a depth field. Since contextFileCapability.key uses
`project:${file.depth ?? 0}`, all ancestor-level AGENTS.md files
collapsed to the same key and only the first survived dedup.
Compute depth via calculateDepth(cwd, ancestorDir) where ancestorDir is
two levels up from the file path (past the .agent/.agents config dir).
This gives each ancestor level a distinct dedup key.
* fix(discovery): stop ancestor walk-up at $HOME when not in a git repo
When repoRoot is null (no .git found), walk-up loops traversed all the
way to filesystem root. This caused $HOME to be scanned as a project-
level directory and then again as user-level, producing duplicates.
All providers now use `ctx.repoRoot ?? ctx.home` as the stop boundary:
stop at repoRoot if in a repo, otherwise stop at home. Applied to
agents.ts, agents-md.ts, builtin.ts, claude.ts, codex.ts, and
opencode.ts.
* fix(context-files): clamp depth >= 0 in dedup key and fix provider depth computations
The dedup key `project:${file.depth}` used raw depth, which could be
negative when providers computed it from config subdirectories (e.g.
.claude/, .github/, .gemini/) rather than the ancestor directory. This
caused same-scope cwd-level files to get distinct keys like project:-1
and project:0, bypassing dedup and injecting conflicting instructions.
Two-layer fix:
1. Key function: clamp to Math.max(0, depth) so any file at or below
cwd is treated as cwd-scope (depth 0). Defensive against future
providers.
2. Providers: fix root cause in claude.ts, gemini.ts, github.ts to
compute depth from the ancestor directory (parent of the config
subdir), not the config subdir itself.
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
Add an optional `oauth` config block on MCP server entries in mcp.json,
allowing explicit `clientId` and `callbackPort` values for servers that
don't expose these through auto-discovery (e.g. Slack).
The `oauth.clientId` is used as a fallback — if the server's error
response or well-known metadata includes a client_id, that takes
precedence. The `callbackPort` defaults to 3000 when not specified.
- 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.
- Added fallback empty string for undefined tool descriptions across all AI providers to prevent runtime errors.
- Made `description` field required in CustomTool interface and normalized tool descriptions in agent-loop.
- Refactored tool normalization in agent-loop by renaming `injectIntentIntoTools()` to `normalizeTools()` with conditional intent injection.
- Added comprehensive description metadata to todo-write tool schema fields for improved clarity.
- Migrated timing instrumentation from custom utils/timings module to centralized logger.time() and logger.timeAsync() methods across coding-agent and natives packages.
- Removed PI_DEBUG_STARTUP environment variable and debugStartup() function, consolidating debug output to logger.debug() for conditional logging.
- Replaced custom TextDecoder buffer decoding with native toString('utf-8') method in natives package for simplified string conversion.
- Added RingBuffer<T> circular buffer implementation to pi-utils with comprehensive test coverage for efficient queue operations.
- Enhanced logger interface with time() and timeAsync() methods providing unified operation timing and performance tracking across packages.
- 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.
- Replaced all direct `process.cwd()` calls with `getProjectDir()` utility function across 40+ files to centralize project directory resolution logic.
- Added `getProjectDir()` and `setProjectDir()` functions to `@oh-my-pi/pi-utils/dirs` module to provide abstracted project directory management.
- Made `SessionManager.list()` method asynchronous to support asynchronous session discovery operations.
- Updated default working directory resolution throughout codebase to use `getProjectDir()` instead of `process.cwd()` for improved project directory detection.
- Added `temperature` configuration setting to control LLM sampling temperature with values from 0 (deterministic) to 1 (creative) to -1 (provider default).
- Added temperature option selector in settings UI with preset values: Default, 0, 0.2, 0.5, 0.7, 1.
- Renamed `settingsInstance` parameter to `settings` in `CreateAgentSessionOptions` for consistency.
- Updated all internal references from `settingsInstance` to `settings` throughout SDK and components.
- Integrated temperature setting into agent configuration and selector controller.
* + /mcp
- Reloads MCP manager in runtime state (no restart needed) and syncs with mcp.json.
- Handles OAuth discovery/auth flow automatically for auth-required servers.
- Validates server names and config shape before saving.
- Persists OAuth credentials in auth storage and links them to MCP config.
- Provides immediate connection checks and clear status messages.
- Supports enable/disable, reauth, and unauth flows that are easy to get wrong by hand.
* active agent tool registry runtime reload + token support for bearer auth http based transport
* +session rebind on succesful connection
* fix(coding-agent): address /mcp check failures
---------
Co-authored-by: can1357 <me@can.ac>
- Migrated environment variable access from function-based `getEnv()` API to object property-based `$env` API across 43 files in the monorepo.
- Simplified `packages/utils/src/env.ts` by removing scoped environment variable logic (EnvScope, getEnvMap, getEnv functions) and replacing with direct `process.env` reference exported as `$env`.
- Updated `packages/ai/src/stream.ts` to remove environment parameter from KeyResolver functions and use global `$env` object instead of passed-in env parameter.
- Migrated environment variable access from direct process.env to centralized getEnv() utility function across all packages.
- Renamed environment variable prefix from OMP_ to PI_ throughout codebase (e.g., OMP_CODING_AGENT_DIR -> PI_CODING_AGENT_DIR).
- Removed automatic environment variable migration from PI_ to OMP_ prefixes via migrate-env.ts module.
- Removed env setting from configuration schema and applyEnvironmentVariables() method from settings.
- Updated CI/CD build configuration to use PI_COMPILED flag instead of OMP_COMPILED.
- Changed venvPath property in PythonRuntime from nullable (string | null) to optional (string | undefined).
- Added Python prelude caching to improve startup performance by caching helper functions and module discovery results.
- Added OMP_DEBUG_STARTUP environment variable for detailed startup stage tracing across initialization pipeline.
- Changed Python kernel initialization to require shared gateway mode, removing support for local kernel gateway startup.
- Improved error handling in shared gateway acquisition with automatic retries on 5xx status codes.
- Added repro-stuck.ts script for reproducing and debugging rare CLI hang issues with Chrome DevTools integration.
- Added trace-loader.ts preload script for tracing module resolution during startup diagnostics.
- 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.
- 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.
- Converted named imports from node modules (fs, path, os) to namespace imports across all packages.
- Extended extension loader error handling with isEacces and hasFsCode type guards.
- 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.
- Converted SettingsManager.create(), loadSettings(), discoverSkills(), loadSlashCommands(), buildSystemPrompt(), loadSkills(), loadProjectContextFiles(), and getShellConfig() from synchronous to asynchronous APIs.
- Changed capability provider load() method from supporting both sync and async to async-only by removing loadSync().
- Removed fs property from LoadContext interface in capability types.
- Added new fs.ts module with caching layer for filesystem operations using readFile, readDirEntries, readDir, walkUp, and cache management functions.
- Refactored all discovery providers (builtin, claude, cline, codex, cursor, gemini, github, mcp-json, ssh, vscode, windsurf) to use async file operations with Promise.all for parallel loading.
- Added automatic remote host OS and shell detection with disk-based caching.
- Added compat mode option for SSH hosts to use POSIX shell compatibility wrapping.
- Added Windows shell support with PowerShell and CMD path escaping functions.
- Updated SSH tool description to display detected shell type per host.
- Simplified SSH tool documentation by removing OS-specific command examples.
- Added SSH tool for executing commands on remote hosts with project config discovery from ssh.json files.
- Added persistent SSH connection manager with master socket support and automatic cleanup.
- Added SSHFS mount utilities for mounting remote filesystems with automatic unmount on session end.
- Added SSH capability definition with host validation and discovery provider registration.
- Added Time Traveling Streamed Rules (TTSR) feature for real-time pattern matching and rule injection during streaming.
- Added TtsrManager with configurable settings for context mode, repeat mode, and repeat gap.
- Added TTSR trigger support across all rule discovery sources (builtin, cline, cursor, windsurf).
- Added abort signal handling in agent loop to support stream interruption for TTSR.
- Added TtsrNotificationComponent for displaying rule violation notifications in interactive mode.
- Added unified capability-based discovery system for loading configuration from 8 AI coding tools (Cursor, Windsurf, Cline, GitHub Copilot, Gemini, Codex, Claude, VS Code).
- Added Discovery settings tab in interactive mode for enabling/disabling configuration providers.
- Added provider source attribution showing which tool contributed each configuration item.
- Added support for tool-specific rule formats including Cursor MDC, Windsurf global_rules, and Cline .clinerules.
- Changed MCP tool name parsing to use last underscore separator for improved server name handling.
- Refactored core loaders (skills, hooks, custom tools, slash commands) to use capability API instead of manual directory scanning.
can1357