* feat(mcp): implement roots/list and server-to-client request handling
Add support for MCP server-to-client JSON-RPC requests across both
stdio and HTTP transports, enabling servers to query client capabilities
such as roots/list during initialization.
Transport layer (types.ts, stdio.ts, http.ts):
- Add onRequest callback to MCPTransport interface for server-initiated
requests; add toJsonRpcError helper for error code propagation
- Classify incoming messages by checking method+id (request), id-only
(response), method-only (notification); guard against id:null per
JSON-RPC 2.0 spec
- StdioTransport: detect server requests in #handleMessage, respond via
#sendResponse writing JSON-RPC response to subprocess stdin
- HttpTransport: detect server requests via #dispatchSSEMessage across
all SSE streams (dedicated listener, POST response drain, notify
piggybacking), respond via #sendServerResponse POST with proper
Accept header and session ID
- Refactor startSSEListener to resolve once SSE GET connects (not when
stream ends), enabling await before notifications/initialized; reset
#sseConnection via .finally() for reconnection after transient failure
- #parseSSEResponse continues reading after capturing the primary
response to drain piggybacked server requests/notifications; clears
timeout after capture so drain phase is unbounded
- notify() reads text/event-stream response bodies for piggybacked
messages; cancels non-SSE response bodies to release connections
- #sendServerResponse includes AbortSignal.timeout and cancels response
body; fire-and-forget handlers wrapped in try/catch to prevent
unhandled rejections
Client wiring (client.ts):
- Add onRequest to connectToServer options, wire to transport before
initialization
- Add awaitable onInitialized hook in initializeConnection, called
between initialize response (which sets session ID) and initialized
notification, so SSE stream is open when server sends roots/list
- Pass only signal to transport.request (not full options object)
- Hoist transport ref to outer scope; close on timeout/abort to prevent
orphaned transports when SSE GET hangs
Manager (manager.ts):
- Wire onRequest handler in connectServers for all MCP connections
- Handle roots/list by returning project CWD as file:// URI via
pathToFileURL; return -32601 for unsupported methods
Tests (mcp-roots-list.test.ts):
- toJsonRpcError: code extraction, defaults, non-Error values
- Message classification spec tests: request/response/notification/
unknown dispatch, id:null and id:0 edge cases
- Roots response shape: file:// URI generation, Windows paths, spaces
* fix(mcp): return SSE response immediately instead of blocking on stream drain
The #parseSSEResponse loop continued iterating the SSE stream after
capturing the response for the expected request ID. Since clearTimeout
was called after capture, a server that holds the SSE stream open for
follow-up events (permitted by Streamable HTTP) would block the
request() call indefinitely.
Return the result as soon as it's captured and drain remaining
messages in a detached background task via #readSSEStream, which
already handles dispatch and error swallowing.
* fix(mcp): handle batched JSON-RPC messages in both transports
JSON-RPC 2.0 section 6 allows sending an array of request/notification
objects as a batch. If a server sent a batch, the message classifier
in both transports would fail the 'method in message' check on the
array object and silently drop all contained messages.
Add an Array.isArray guard at the top of #handleMessage (stdio) and
#dispatchSSEMessage (http) that recurses into each element. Defensive
measure — no known MCP server sends batches today, but the guard is
cheap and correct per the JSON-RPC spec.
* fix(mcp): address second Codex review round
- http: break from SSE loop before starting background drain to avoid
ReadableStream locked error (the for-await iterator still holds the
reader when #drainSSEBackground was called inline)
- types: toJsonRpcError now accepts plain { code, message } objects,
not just Error instances, so onRequest handlers can throw structured
JSON-RPC errors without wrapping in Error
- test: relax Windows path name assertion to toBeTruthy since
path.basename is platform-dependent for backslash paths; add tests
for plain-object toJsonRpcError
* fix(mcp): address third Codex review round
- parseSSEResponse: flatten JSON-RPC batch arrays before checking for
the expected response, so a server that batches the primary response
with piggybacked requests/notifications in a single SSE event still
has the response extracted correctly
- sendServerResponse: retry once on 401/403 via onAuthError, matching
the auth-refresh logic in #executeRequest; prevents server-initiated
request replies from failing after token expiry on long-lived SSE
sessions
---------
Co-authored-by: Miroslav Drbal <miroslav.drbal@gendigital.com>
- Added automatic deduplication of identical context files by content, keeping the closest (lowest depth) copy when duplicates are discovered.
- Implemented dedupeExactContextFiles() function to filter duplicate context entries in both explicit and discovered file lists.
- Added 3 test cases covering deduplication of explicit context entries, discovered context entries, and preservation of distinct entries.
- Added `edit.blockAutoGenerated` setting to control enforcement of auto-generated file detection.
- Improved auto-generated file detection to use language-specific comment parsing instead of broad regex patterns, reducing false positives.
- Enhanced marker detection to scan only leading header comments (1024-byte limit) rather than entire file prefix for better accuracy.
- Fixed tool argument validation to properly handle string 'null' values on optional LLM tool arguments.
- Improved type safety by changing validateToolCall and validateToolArguments return types from any to ToolCall["arguments"].
- Extracted OpenAI compatibility detection and resolution logic into dedicated `openai-completions-compat` module.
- Refactored `detectCompat()` and `getCompat()` to delegate to new compat module functions with simplified conditional logic.
- Fixed OAuth redirect URI validation to preserve exact configured values without trailing slash normalization.
- Improved session deletion to return boolean status and display error messages in UI instead of silently failing.
- Added `/session delete` command with Delete key support and confirmation dialogs for session management.
- Extracted environment variable placeholder generation into helper function for test readability.
- Refactored 9 test assertions to use envPlaceholder() helper instead of inline template strings.
- Made sessionDir parameter optional in SessionManager.create(), forkFrom(), continueRecent(), and list() methods with automatic default computation.
- Updated SessionManager.getDefaultSessionDir() to accept optional agentDir parameter for custom sessions root configuration.
- Changed SessionManager.list() signature to require cwd parameter as first argument with sessionDir now optional.
- Implemented multi-root session migration support by replacing global migration state with per-root tracking and extracting session directory encoding logic.
- Added resolveManagedSessionRoot() function to determine if session directory is managed and extract its root.
- Added symlink and path alias resolution to session directory handling for consistent behavior across aliased home and temp directories.
- Improved status line path display to strip display roots using canonical path resolution, correctly handling symlink-equivalent directory aliases.
- Added support for quoted paths in grep, ast_grep, and find tools to properly handle directory names with spaces.
- Improved ast_grep error messaging when no matches found with parse errors to suggest narrowing path/glob or setting language.
- Extracted path utility functions (resolveEquivalentPath, normalizePathForComparison, pathIsWithin, relativePathWithinRoot) to shared utils package.
- Added comprehensive test coverage for symlink alias resolution in status line path rendering and session directory handling.
- Added support for quoted paths in grep, ast_grep, find, and ast_edit tools to handle paths with spaces.
- Introduced normalizePathLikeInput() utility function for consistent path and glob parameter normalization across tools.
- Enhanced ast_grep error messaging to warn about parse issues and suggest narrowing path/glob or setting lang parameter.
- Added comprehensive tests for quoted path handling in grep, ast_grep, and find tools with pattern matching.
* Add MCP tool discovery search and live refresh
* Fix MCP discovery review feedback
* Address remaining MCP discovery review comments
* feat: compact MCP discovery search results
* fix: align MCP discovery search contract
* feat: add MCP server tool counts to discovery hints
* fix(agent): corrected stale toolChoice validation against active tools
- Fixed stale forced toolChoice passed to provider after mid-turn tool refresh by validating against active tools.
- Added refreshToolChoiceForActiveTools() to filter invalid tool choices when available tools change.
- Changed getToolChoice config to use computed function instead of static property for dynamic validation.
- Fixed MCP tool selection tracking in coding-agent to distinguish between discovery-enabled and non-discovery sessions.
- Updated search_tool_bm25 to filter already-selected tools before applying limit parameter.
---------
Co-authored-by: can1357 <me@can.ac>
- Updated llama.cpp model discovery to read context window from the `/props` endpoint's `default_generation_settings.n_ctx` field instead of using hardcoded 128000 default.
- Updated llama.cpp model discovery to detect vision capabilities from the `/props` endpoint's `modalities.vision` field instead of defaulting to text-only input.
- Changed llama.cpp `maxTokens` calculation to respect discovered context window limits, capping at 8192 or the server's context window, whichever is smaller.
- Added `#toLlamaCppNativeBaseUrl()` helper to normalize llama.cpp base URLs by stripping `/v1` suffix for native endpoint access.
- Added 3 test cases to verify context window, vision capability, and authorization header handling in llama.cpp discovery.
- Added automatic Ollama model context window discovery from metadata for accurate token limits.
- Added `attribution` option to `PromptOptions` for explicit billing and initiator attribution control.
- Added automatic clearing of completed and abandoned todo tasks after ~1 minute.
- Changed session directory migration to use `-tmp-` prefix instead of double-dash format.
- Updated Ollama model registration to use discovered context window instead of hardcoded 128000 token default.
Fixes#440
- Added automatic migration of legacy absolute-path session directories with double-dash format to new canonical locations.
- Enhanced session directory encoding to use `-tmp-` prefix for temporary directories instead of legacy double-dash format for improved clarity.
- Extracted session directory migration logic into reusable helper functions for better maintainability.
- Updated test setup to mock home directory and verify session migration behavior with temporary paths.
- Added `attribution` option to `PromptOptions` for controlling billing and initiator attribution.
- Updated subagent prompts to explicitly set `attribution: "agent"` for accurate billing attribution.
- Refactored message attribution logic to use configurable `promptAttribution` with fallback defaults.
- Added test coverage for `attribution` option in subagent reminder prompts.
Fixes#439.
feat(coding-agent): added attribution option and explicit session directory control
- Added `attribution` option to `PromptOptions` for explicit billing and initiator attribution control.
- Updated `SessionManager.create()` to require both `cwd` and `sessionDir` parameters for explicit session directory control.
- Changed session directory naming for temporary working directories from `--` format to `-tmp-` prefix.
- Made `cwd` and `sessionDir` fields mutable in SessionManager to support session relocation.
- Fixed automatic migration of legacy session directories to new `-tmp-` prefixed naming scheme.
- Updated all test fixtures to pass both `cwd` and `sessionDir` parameters to `SessionManager.create()`.
- Updated plugin extension discovery test to use XDG_DATA_HOME instead of HOME for environment isolation.
- Replaced manual path construction with getPluginsDir() utility for consistency.
- Added XDG directory structure setup and path cache rebuild to ensure correct plugin resolution.
- 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 support for move-only file operations that preserve exact bytes including binary content and special characters.
- Added validation to reject move operations where source and destination paths are identical.
- Implemented dedicated move-only handler with parent directory creation and binary-safe file rename operations.
- Added error handling for move operations on non-existent source files.
Two /move bugs on Windows:
1. Quoted absolute paths (e.g. /move "C:\...") were treated as relative
because surrounding quotes weren't stripped before path.isAbsolute().
2. /move before any model response threw ENOENT because the session
.jsonl file hadn't been created on disk yet (lazy-persist).
Changes:
- Extract stripOuterDoubleQuotes() helper in path-utils.ts, use in
handleMoveCommand() with empty-after-strip guard
- Guard session file rename with existsSync in moveTo(), leaving
artifact dir rename independently guarded
- Guard #rewriteFile() with hadSessionFile || hasAssistant to preserve
lazy-persist while still updating header cwd for existing files
- Add comprehensive test suite (13 tests) covering all moveTo() edge
cases including header-only sessions, deferred persistence, and
artifact migration
* feat(utils): full XDG Base Directory support for all path helpers
Implement XDG-first resolution across all omp path helpers, extend the
migration command to cover every data/state/cache location, and fix
five data-safety issues found in review.
dirs.ts:
- Add getXdgCachePath() helper ($XDG_CACHE_HOME/omp/<subpath>)
- Add isDefaultAgentDir() helper: XDG lookup is only valid when the
resolved agentDir equals the process default (~/.omp/agent); custom
profiles set via PI_CODING_AGENT_DIR or setAgentDir() are never
silently redirected to the global XDG database
- Update 15 functions to XDG-first resolution:
data: getPluginsDir, getRemoteDir, getRemoteHostDir, getPythonEnvDir,
getWorktreeBaseDir
state: getReportsDir, getSshControlDir, getCrashLogPath, getDebugLogPath
cache: getPuppeteerDir, getGpuCachePath, getNativesDir
- Guard XDG lookup with isDefaultAgentDir(agentDir ?? getAgentDir()) in
all 9 agent-subdir helpers so that callers passing the global default
agentDir still resolve to the migrated XDG location, while callers
passing a non-default agentDir or running under a custom profile via
setAgentDir() bypass XDG entirely
- Plugin-derived helpers delegate to getPluginsDir() and follow XDG
resolution automatically
migrate-xdg.ts:
- Add getXdgCacheHome() helper
- Extend MigrationItem.category to include 'cache'
- Add 12 new migration entries: reports, plugins, remote, ssh-control,
remote-host, python-env, puppeteer, wt, gpu_cache.json, natives,
omp-crash.log, omp-debug.log
- Refuse to run when PI_CODING_AGENT_DIR points to a non-default
profile: migration only makes sense for the default ~/.omp/agent tree
- copyDirectory returns skipped source paths (target existed, non-force)
- verifyIntegrity: remove size-mismatch early-return that masked stale
targets as successful copies
- executeMigration: delete only entries that were actually copied;
use rmdir on source dir so it is removed only when empty, preserving
any skipped files for a subsequent --force run
- executeMigration: rename partial target to <target>.bak on integrity
failure instead of deleting; preserves pre-existing user data while
preventing getXdgDataPath from treating the partial tree as
authoritative; source remains intact for re-copy on next run
test isolation:
- Set XDG_DATA_HOME/XDG_STATE_HOME to non-existent paths in
memories-runtime.test.ts beforeEach/afterEach to prevent
getXdgDataPath/getXdgStatePath from resolving to real user data
* fix(utils,coding-agent): fix XDG support issues
dirs.ts:
- Refactor path resolution into DirResolver class. XDG base dirs are
resolved once at construction from env vars (Linux only, no
existsSync). setAgentDir creates a fresh instance, naturally
invalidating all cached paths and recomputing isDefaultProfile.
- getRootSubdir/agentSubdir accept optional XdgCategory parameter;
when set, the XDG base replaces the config root. Every accessor
is a one-liner delegate.
- Non-Linux platforms: XDG fields are null, zero overhead. No
filesystem probing, no string comparisons on the hot path.
- Config-only subdirs (themes, tools, commands, prompts, modules)
have no XDG category — they stay under the config root.
- Remove `import { env } from 'bun'`, use process.env consistently.
- Restore JSDoc comments to document actual defaults (~/.omp/...).
migrate-xdg.ts:
- Gate migrateToXdg on Linux — exits with clear error on other
platforms.
- Fix data loss bug: verifyIntegrity now accepts a Set of skipped
paths and skips verification for files that were intentionally not
copied (pre-existing at target in non-force mode).
- Fix nested directory source deletion: recursive removeSourceEntries
walks the tree and only deletes files not in the skipped set.
- Remove dead _sourcePath variable and unused force parameter from
verifyIntegrity.
- Remove `import { env } from 'bun'`, use process.env consistently.
logger.ts:
- Revert JSDoc to document ~/.omp/logs/ as default.
oauth.ts:
- Replace direct getAgentSubdir call with getTestAuthPath().
CHANGELOG.md:
- Merge duplicate section headers under [Unreleased].
- Add missing blank line before [13.11.1].
---------
Co-authored-by: can1357 <me@can.ac>
- Reorganized settings tabs from 12 to 8 focused categories (appearance, model, interaction, context, editing, tools, tasks, providers) with consolidated status line settings.
- Added 15+ new settings for status line customization, sampling parameters, speech-to-text, web search, and edit mode configuration.
- Changed default agent model from `default` to `pi/task` for independent subtask configuration and updated model resolution to support single-pattern inheritance fallback.
- Updated system prompt to use ISO 8601 date format (YYYY-MM-DD) and renamed 25+ UI labels for consistency across settings interface.
- Updated tab icon symbols across unicode, nerd, and ASCII presets to reflect new tab organization.
- Simplified settings definitions and removed unused imports to reduce code complexity.
- Added task model role configuration enabling dedicated subtask execution with independent model selection.
- Changed default agent model from 'default' to 'pi/task' for independent subtask model configuration.
- Added single-pattern inheritance fallback allowing pi/task agents to inherit session model when unconfigured.
- Refactored model resolution logic into resolveAgentModelPatterns() function with structured fallback handling.
- Added resolveConfiguredModelPatterns() and helper functions for improved model pattern resolution.
- Added `moveCursorToMessageStart()` and `moveCursorToMessageEnd()` prompt actions for cursor navigation to message boundaries.
- Exposed editor methods for cursor movement to message start and end positions in InputController keybindings.
- Implemented message boundary navigation in Editor class with private helper methods for cursor positioning.
- Removed remote compaction settings test suite to align with feature deprecation.
- Added support for provider-level OpenAI compatibility configuration enabling reasoning effort mapping and streaming usage fallback across models.
- Added 10 new AI models (DeepSeek V3.2, Llama 3.1 405B, Mistral Large 3, Pixtral Large, and others) with updated pricing and context windows.
- Fixed autocomplete to preserve ./ prefix in relative file/directory path completions and paste marker expansion to handle regex tokens literally.
- Changed system prompt date format to ISO 8601 and tool download timeout from 15s to 120s for improved cross-platform compatibility.
- Refactored OpenAI completions provider to extract token parsing logic and support choice-level usage fallback with improved message serialization.
- Changed abort() method signature to return Promise<void> instead of void, making it async-compatible.
- Added bash executor fallback to one-shot shell execution when persistent sessions fail to respond to cancellation.
- Fixed bash execution timeout handling to prevent subsequent commands from hanging after hard timeouts.
- Extracted abort token management into ShellAbortState for thread-safe cancellation handling across shell sessions.
- Added SessionManager.close() method for proper cleanup of persistent writers and session resources.
- Added `close()` method to SessionManager and AuthStorage for proper resource cleanup and finalization of prepared statements.
- Added `initiatorOverride` option support in OpenAI and Anthropic providers for message attribution control.
- Fixed resource leaks in RpcClient timeout handling by centralizing timeout creation with unref() and adding explicit clearTimeout() calls.
- Fixed AgentSession disposal to call SessionManager's `close()` method for guaranteed resource cleanup instead of fallback flush.
- Updated all test suites to properly dispose AuthStorage instances in cleanup hooks to prevent resource leaks between tests.
* fix(memories): isolate Phase 2 consolidation per project working directory
The global memory consolidation job used a single 'global' job key,
causing all projects to share one Phase 2 slot. Whichever project
claimed it first got every project's stage1 outputs written into its
memory directory — cross-project contamination.
Root cause:
- GLOBAL_KEY = 'global' was a single key shared by all projects
- listStage1OutputsForGlobal() had no cwd filter — returned ALL
stage1 outputs across all projects
- markGlobalPhase2Succeeded/Failed/Unowned all operated on the same
single global job row
Fix:
- Replace GLOBAL_KEY constant with globalJobKey(cwd) function that
namespaces the job key per project: 'global:/path/to/project'
- Add cwd parameter to all Phase 2 storage functions so each project
maintains its own job slot in the jobs table
- Filter listStage1OutputsForGlobal() by t.cwd = ? so each project
only consolidates its own thread outputs
- Thread cwd from session.sessionManager.getCwd() through runPhase2()
to all storage calls
- Add cwd to markStage1SucceededWithOutput/NoOutput so enqueueGlobal
Watermark targets the correct per-project job key
- Add cwd parameter to enqueueMemoryConsolidation() public API and
update its only external caller (command-controller)
Closes#369
* test(memories): add isolation tests for per-project Phase 2 consolidation
Three tests covering the regression fixed in the previous commit:
- listStage1OutputsForGlobal filters outputs by cwd (no cross-project leak)
- enqueueGlobalWatermark creates separate job rows keyed per-project
- tryClaimGlobalPhase2Job claims only the requested project's slot and
leaves the other project's job independently claimable
* docs: add inline comments for memory isolation fix and tests
---------
Co-authored-by: Rens Tillmann <rens@super-forms.com>
* add llama.cpp as local provider
* use responses api instead of messages
* use api-keys correctly for llama.cpp provider
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
- Added line hashes to compact diff preview for unchanged and added lines to enable integrity verification.
- Modified compact diff preview to track line number synchronization between old and new files when processing insertions and deletions.
- Fixed line number parsing in compact diff preview to handle variable-width line number fields with leading whitespace.
- Extracted parsing and formatting logic into dedicated functions (parseNumberedDiffLine, formatCompactHashlineLine, syncOldLineCounters, syncNewLineCounters) for maintainability.
- Updated 4 test cases to verify line hash generation, line number synchronization, and handling of variable-width fields.
can1357