- Normalized agent `setSystemPrompt` to wrap string inputs into one-item arrays.
- Updated session creation to accept string `systemPrompt` values and normalize callback or direct results to string arrays.
- Adjusted extension result handling and test fixtures to accept string `systemPrompt` and missing `assistant_message` fields without crashing.
- Wrapped queue shutdown and cancel test assertions in `try`/`finally` blocks.
- Cancelled and awaited worker and in-flight tasks in finalizers to prevent lingering background tasks.
- Handled expected `CancelledError` exceptions during task cleanup with `suppress`.
- Added event retry settings with parsed delay schedules and jittered delay computation.
- Extended event persistence to persist an `available_at` timestamp, honor it during dequeuing, and clear it when re-queuing.
- Updated worker failure handling to queue bounded retries with backoff and transition to failed only when the retry budget is exhausted.
- Updated `ThinkingConfig` and related types to model effort-based thinking settings with optional defaults and routing metadata.
- Added a dedicated parser for `model.thinking` payloads to validate efforts and normalize new optional thinking fields.
- Extended protocol tests to verify effort-based thinking data is parsed correctly and unknown efforts are rejected.
- Updated `RpcClient` to spawn `omp` in a new session, cache its process group, and terminate descendants on stop.
- Fixed `stop()` to signal the cached process group with SIGTERM then SIGKILL so leaked grandchildren are terminated.
- Moved status-query reads in `create_app` to `asyncio.to_thread`, preventing FastAPI event-loop stalls.
- Added regression coverage for stopping a spawned grandchild process in the client tests.
- Added a new @oh-my-pi/snapcompact package and redirected compaction call sites to it.
- Added provider-aware snapcompact shape resolution for model-specific mixed-frame behavior.
- Added optional image detail support by extending ImageContent and passing hints through OpenAI providers.
- Added native snapcompact render options, including 5x8/8x8 font loading and palette/geometry controls.
- In _run_rpc_blocking, added a check for an assistant_message stopReason after timeout handling.
- When stopReason is "error", the worker now reads errorMessage (or a default message) and raises a RuntimeError.
system_append.md and system_append_pr_review.md hardcoded the literal
'robomp' as the bot persona, so the agent self-mentioned an account
that does not exist when deployments configure ROBOMP_BOT_LOGIN to a
different login. Affected users saw the agent ask for @robomp mentions
that GitHub never resolved to the actual bot.
Thread the configured login through persona.system_append and
persona.system_append_pr_review as a bot_login keyword, render it
via the existing {{bot_login}} placeholder, and pass
settings.bot_login at the worker callsite. Regression test asserts the
templated login lands in both prompts and the legacy literal is gone.
Fixes#1932
Prevented the durable queue from claiming a queued event while another event with the same issue key is still running, so duplicate worker instances cannot resume the same RpcClient session concurrently.
Added regression coverage for blocked same-issue events and for skipping blocked queue heads without stalling unrelated issues.
Fixes#1840
`SandboxManager.ensure_workspace` calls `fetch_base_ref` (then
`worktree add origin/<ref>`) and `fetch_pr_head` (then
`worktree add --detach FETCH_HEAD`). Both used to issue a plain
`git fetch origin <ref>`. On a `--filter=blob:none` pool the fetch
inherits `remote.origin.partialclonefilter` from the pool config and
brings the commit + tree but no blobs. The next `worktree add` runs
in a non-token subprocess, hits a missing blob, and tries a lazy
promisor fetch — which under `ProxyGitTransport` deployments has no
PAT in the orchestrator container and dies with
fatal: could not read Username for 'https://github.com'
fatal: could not fetch <sha> from promisor remote
`git_ops.fetch_ref` and `fetch_pr_head` now pass `--refetch
--no-filter` so the fetch (which already runs through the token-bearing
transport) eagerly materializes every blob reachable from the requested
ref. `--refetch` is required: without it git short-circuits on "we
already have this commit" and the lazy-fetch path stays primed.
`fetch_prune` (the periodic pool refresh) is untouched, so the
partial-clone disk savings are preserved on the steady-state path.
`remote.origin.partialclonefilter` is left intact in the pool config.
Fixes#1818
- Added `is_implementation_authorizer` check requiring OWNER or allowlisted maintainer to authorize implementation work.
- Blocked `gh_push_branch` and `gh_open_pr` for unclassified/enhancement/proposal issues without explicit directive authorization.
- Auto-allowed bug and documentation issues without requiring a directive.
- Propagated `authorizes_impl` flag through events, server, tasks, and worker bindings.
- Added `review_pr` task that checks out PR head in a detached worktree, classifies rank/type/area, and posts a batched GitHub review as `event=COMMENT`.
- Added four new host tools: `fetch_pr`, `classify_pr`, `pr_review_comment`, and `submit_pr_review`; review tools self-gate on `review_mode`, push/open-PR tools refuse when `review_mode` is set.
- Added sqlite staging table `pr_review_comments` with `stage_review_comment`, `list_staged_review_comments`, and `clear_staged_review_comments` DAOs.
- Routed `pull_request.opened/reopened/ready_for_review` to `review_pr` and extended `pull_request.closed` cleanup to any tracked PR regardless of author.
- Upgraded workspace catalog dependencies to newer versions in both package manifests.
- Regenerated bun.lock to align transitive versions, including Vite and ecosystem tooling updates.
- Updated ACP startup tests and transport handling to fail fast on unsupported server transport types.
Fire Pass support:
- New provider with login command 'omp /login firepass'
- Hand-seeded kimi-k2.6-turbo model with Fire Pass router wire id
- pi-ai CLI --help lists firepass
AI provider fixes surfaced during the Fire Pass review:
- service_tier whitelist restored for openai/openai-codex only (was leaking to
Fireworks, Firepass, OpenRouter, Azure OpenAI Responses)
- Anthropic tool schema normalizer collapses {} -> true for additionalProperties
- anthropic.prepareParams fires onPayload after drop helpers so callers see the
real wire body
- isServiceTier type guard narrowed to ResolvedServiceTier
- transformMessages stops dropping orphan tool_result when all pending tool
calls have already resolved
- zodToWireSchema preserves null for non-scalar nullable() inner schemas
- isEmptyObject / isJsonObjectEmpty use Object.keys().length === 0 instead of
prototype-walking for...in
- Telemetry records resolved service_tier (priority) instead of scoped
placeholder (openai-only/claude-only)
- Robomp dirty-state reminder no longer asserts a formatter-failure premise
- Normalized reviewer-bot matching by stripping a trailing `[bot]` suffix when resolving configured bot logins.
- Fetched PR thread history for followup comments without directives and carried it through task execution.
- Updated followup prompt rendering to include prior conversation context for handle_comment tasks.
- Moved issue classification updates to run only after branch rename succeeds, preventing partial labeling or DB writes when rename fails.
- Adjusted workspace ownership normalization to chown workspaces to the active slot or, when slotless, to the current euid/egid, then apply shared permissions.
- Added tests for classify_issue rename-failure rollback and chown_workspace normalization in non-slot mode.
parse_issue_ref now accepts owner/repo#NN or a github issue url (with or without scheme, www., trailing slash, query, fragment). The dashboard trigger, CLI, and replay endpoint pick this up automatically; UI hints updated to match.
- Added `DirtyState` and `inspect_dirty_state` in `git_ops` to report uncommitted, unpushed, and summary state.
- Updated `_drive_turn` to recheck completion each cycle and emit dirty-state reminders or exit when clean.
- Wired `dirty_state_reminder` into persona rendering with `uncommitted`, `unpushed`, and `summary` context.
- Added `dirty_state_reminder.md` guidance for fixing/restoring changes and pushing only after `bun run fix` completes.
- Added worker tests for dirty, clean, and persistent-dirty flows and prompt-count assertions.
- Replaced `oh-my-pi/artifacts:dev` image references with `oh-my-pi/pi:dev`.
- Updated `PI_ARTIFACTS_IMAGE` → `PI_BASE` in compose and script descriptions.
- Replaced `/work/pi/Dockerfile` artifact stage with `/Dockerfile` pi-runtime stages.
- Added `pi:image` and `pi:run` commands to development command reference.
- Replaced the slim artifacts-only image with a full pi-base image (python + bun + rustup + natives + omp_rpc + omp shim).
- Moved robomp Dockerfile to repo root as Dockerfile.robomp, extending pi-base instead of copying from a scratch artifacts image.
- Renamed PI_ARTIFACTS_IMAGE to PI_BASE and updated all npm scripts and compose config accordingly.
- Split .dockerignore into per-Dockerfile shadows (Dockerfile.dockerignore, Dockerfile.robomp.dockerignore).
- Added `python/robomp` as a workspace package alongside its nested `web` sub-package.
- Added `ignoreDependencies` in `.fallowrc.jsonc` for deps used via bin or in nested workspaces.
- Removed unused `clearTriggerStatus` export and unexported `tick` and `ByModelToggle`.
- Added `omp auth-gateway serve/token/status` — a forward-proxy injecting broker credentials for OpenAI Chat, Anthropic Messages, and OpenAI Responses wire formats.
- Added `GET /v1/usage` to auth-broker and auth-gateway; usage cache switched to 5-min per-credential TTL with jitter and last-good fallback on failure.
- Added `AuthStorage.setConfigApiKey/removeConfigApiKey/clearConfigApiKeys` so `models.yml` `apiKey` beats OAuth tokens without overriding `--api-key`.
- Added `omp auth-broker migrate --from-local` for idempotent upload of local SQLite/env credentials to the broker.
- Subtree-merged github.com/can1357/roboomp with full history
- Wired python/robomp/web as a Bun workspace; migrated SolidJS deps to root catalog
- Removed nested bun.lock/bunfig.toml/biome.json; root configs now own them
- Replaced scripts/with-pi-root.sh; default PI_ROOT to ../.. (the monorepo)
- Added root recipes: test:py, lint:py, fix:py (Python opt-in, not folded into bun test)
- Updated .gitignore/.dockerignore for robomp runtime state (data/, cache/, web dist, static bundle)
- Updated README/AGENTS/.env.example to drop ROBOMP_PI_* auto-clone knobs
- Added homepage metadata entries to the Rust and Python package manifests.
- Replaced OpenRouter HTTP-Referer values with https://omp.sh/ in completion and image requests.
- Updated Codex WebSocket typing and construction to use Bun.WebSocket for handshake header capture.
Fixes#1102
- Stop now marks the client as closed via `_mark_closed` with `RpcProcessExitError`, so `_wait_for_agent_end` wakes immediately instead of waiting for a timeout.
- Added a regression test using a hanging server subprocess to verify `stop()` unblocks `prompt_and_wait` promptly and raises `RpcProcessExitError`.
- Updated Kimi compatibility tests to distinguish Moonshot-hosted models from OpenCode-hosted ones for `reasoning_content` and assistant-content tool-call behavior.
- Added user, group, and extra_groups parameters to RpcClient initialization.
- Propagated those parameters through to subprocess startup calls.
- Added tests to verify the new kwargs are passed correctly, including None defaults and empty extra groups.
- Adjusted the test server in test_host_uris.py to re-emit host_uri_result frames as uri_echo notifications.
- Updated test client setup to attach an unknown-notification capture hook for uri_echo frames.
- Changed _await_echo to read captured uri_echo frames from that hook and fail fast if capture is missing.
- Added `_optional_str_list` to normalize `systemPrompt` payloads into a tuple when absent, a bare string, or a string array, and to reject invalid shapes.
- Updated `SessionState` to hold `system_prompt` as a tuple and to parse daemon payloads with the new helper in `parse_session_state`.
- Extended protocol tests to verify array and legacy string parsing, default empty tuple behavior, and invalid `systemPrompt` values.
- Added `toolStrictMode` support with `all_strict`/`none`/`mixed` options to OpenAI compatibility.
- Fixed OpenAI-completion strict-mode flows by capturing failed HTTP responses and retrying once as non-strict.
- Fixed completion error reporting by surfacing captured status, headers, and JSON `type`/`param`/`code` details.
- Improved strict-schema enforcement with WeakMap memoization and circular-schema detection in sanitization.
- Fixed OpenRouter provider lookup by resolving fallback model IDs for suffix and date variants in registry resolution.
- Refactored benchmark tooling and added async RPC error-window tracking for scheduled run execution.
- Added host tool execution framework with HostTool, HostToolContext, and host_tool() factory for custom tool integration.
- Added RpcConcurrencyError exception and _PromptLifecycleCoordinator to enforce single-flight constraint on prompt lifecycle methods.
- Enhanced JSON parsing with 10 validation helpers and enum frozensets for safe field extraction with detailed error messages.
- Replaced manual event/error list management with _BoundedHistory for bounded-size history with offset tracking.
- Added deep JSON cloning to prevent external mutations of stored payloads and improved UTF-8 error handling in subprocess stderr.
- Added custom_tools parameter to RpcClient and set_custom_tools() method for runtime tool registration.
- Added error handling callbacks (on_protocol_error, on_listener_error) and error history tracking (protocol_errors, listener_errors properties) for RPC failures.
- Added max_event_history and max_stderr_chunks parameters to bound retained history in long-lived hosts, preventing unbounded memory growth.
- Added assistant_text_with_thinking() and message_text_with_thinking() helper functions for backward compatibility with thinking block inclusion.
- Improved error correlation for id-less parse/unknown-command failures to waiting requests and changed prompt scheduling failures to raise instead of timing out.
- Refactored event dispatch to _dispatch_listeners() with exception handling and error recording for robust listener failure management.
- Added typed event listeners and granular event handling for all RPC notification types.
- Added set_todos RPC command and todoPhases session state field for todo phase management.
- Added RpcClient initialization parameters (thinking, tools, no_session, rpc_defaults) for startup configuration.
- Added install_headless_ui() method and todo management methods (get_todos, set_todos, clear_todos).
- Added TodoItem and TodoPhase dataclasses with parser functions for structured todo representation.
- Added RPC mode behavior: disables session title generation by default and resets workflow settings to built-in defaults.
- Added RpcClient class with subprocess-based RPC communication, thread-safe request/response handling, and 30+ public methods for agent operations.
- Defined 65+ public API symbols including protocol types, dataclasses, parser functions, and custom exception types for RPC communication.
- Implemented event listener system with on_event, on_ui_request, and on_extension_error callbacks for asynchronous RPC event handling.
- Added comprehensive test suite with integration tests for RpcClient and unit tests for protocol parsing functions.
- Configured Python package with setuptools, PEP 561 type hints support, and documentation for usage and API reference.
lycaon