- Fixed cold revival flow so parked subagents are restored from persisted sessions at startup.
- Fixed session-init persistence to include spawns and readSummarize fields for replay accuracy.
- Fixed latest-session lookup by adding peekSessionInit for lock-free persisted contract access.
- Added lifecycle and session tests for cold-revive success, decline, and retry paths.
- Passed USER_INTERRUPT_LABEL through abort paths in collab, ACP, RPC, runtime, and SDK flows.
- Added userInitiated to synthetic continue inputs and session prompt calls.
- Suppressed advisor auto-resume during user aborts and preserved queued concerns.
- Cleared suppression on user prompts and reclaimed parked advisor cards on abort settle.
- Added discovery of local, user, and ancestor `WATCHDOG.md` files via `discoverWatchdogFiles`.
- Appended discovered watchdog prompts to advisor system prompts during session setup.
- Added protocol startup defaults that force `advisor.enabled` and `advisor.subagents` false.
- Handled `maintainContext` failures and drained pending updates before token estimation.
- Added a streamingBehavior field to submitted user inputs and threaded it through interactive mode types and controller start-up.
- Updated interactive submission dispatch to default to followUp queueing while preserving explicit steer intent when provided.
- Changed tests to verify followUp and steer queueing behavior, preventing AgentBusyError from race-window busy sessions.
- Added session-domain modules and exports for session-entries, context, listing, loader, and migrations.
- Changed persistence to async append writes plus writeTextAtomic, removing sync line APIs.
- Added compaction-aware session context rebuild with dangling tool-call cleanup.
- Added resumable session resolution with status inference, id/stem/suffix matching, and backup recovery.
Plan approval dispatched the executor's first synthetic prompt without
checking whether the agent was still streaming the post-resolve
continuation (or a turn started by the approve-time compaction/clear),
surfacing "Failed to finalize approved plan: ... Agent is already
processing". Loop auto-submit and goal continuations hit the same throw
via submitInteractiveInput, which always called prompt/promptCustomMessage
without a streamingBehavior.
#approvePlan now aborts any in-flight turn before the synthetic prompt,
and submitInteractiveInput routes submissions through the steer/follow-up
queue (streamingBehavior: "followUp") when the session is streaming.
Non-streaming call shapes are unchanged. Extends the manual-/goal fix
(#2454) to the continuation and plan-approval paths.
Bare `omp --list-models` (or any other stale/typoed --flag) was silently
consumed by `parseArgs` and the agent went on to start a real session,
connect to the configured MCP servers, and hang waiting on the model.
Any positional after the unknown flag was reinterpreted as the initial
prompt, so a documentation drift turned into an unintended LLM invocation.
`parseArgs` now tracks flag-shaped tokens that did not match any built-in
or extension-registered flag in a new `unrecognizedFlags: string[]` field,
and `reportUnrecognizedFlags` prints a clean `Error: unknown flag(s): …`
line plus the `--help` hint. `runRootCommand` invokes the helper right
after the post-extension reparse and `process.exit(2)`s before any
session, MCP, or initial-message work runs.
The validation is gated on the extension-aware reparse, so extension
flags (`--spawn-peer`, `--headless`, `--plan`, …) still pass through
the same way `applyExtensionFlags` already handles them. `-` (stdin
marker) and `--` (POSIX separator) are deliberately allowed through.
Fixes#2459
- Added `omp models` command with `ls`, `find`, `canonical`, and `refresh` actions.
- Removed top-level `--list-models` parsing from CLI args, launch, and main command flow.
- Implemented action-driven model listing with provider filtering, extension loading, and `--json` output.
- Updated unknown provider/model errors and tests to direct users to `omp models` guidance.
- Extended `parseCollabLink` test coverage to reject 16-byte and 40-byte fragments instead of only rejecting short keys.
- Added coverage for full-link fragments to ensure key and write token are parsed when present.
- Updated `GuestClient` test setup so `welcomeFrame` carries a `readOnly` flag into snapshot assertions.
Gated the Model scope banner suffix on the original scope's explicitThinkingLevel flag and switched the display source back to the pre-default ScopedModel[] so non-explicit scope entries no longer render the global default thinking level.
Fixes#2385
Respect startup.quiet when building the interactive model-scope notification so quiet launches do not emit startup chrome for large enabledModels scopes.\n\nFixes #2386
Fixed the interactive Model scope formatter so unset thinking levels omit the suffix and explicit levels render as id:level.
Added regression coverage for the startup banner list formatter.
Fixes#2385
- Replaced task-simple-mode with a `task.batch` setting enabled by default.
- Updated task schema to use batch `{agent, context, tasks[]}` payloads.
- Migrated task execution to spawn one async job per task and merge outputs.
- Removed per-call schema passing while preserving legacy flat task calls.
- Removed `StartupInput` pre-TUI buffering and replay, and read startup input directly each loop.
- Removed pre-startup model/provider/LSP discovery and startup handoff into session setup.
- Updated `WelcomeComponent` to use per-instance tips and show `No recent sessions` when empty.
- Documented task option removals and startup splash/input behavior changes in `CHANGELOG.md`.
The session-observer overlay is gone. The Agent Hub (ctrl+s, alt+a, or double-tap left arrow on an empty editor) presents one overlay with two views: a live registry table (status, unread irc count, current task, last activity; j/k to navigate, r to revive, x to abort/release) and per-agent chat (transcript + input line) — submitting revives a parked agent and steers it via the normal prompt path. Main is the ambient chat and stays out of the table.\n\nrenderInitialMessages no longer takes a prebuilt context: every redraw now reaches for AgentSession.buildTranscriptSessionContext() (full-history transcript with each compaction emitted inline at the point it fired, snapcompact frames re-attached on rebuild). UiHelpers drops the deferred-compaction render and the IRC autoreply branch that the new mailbox bus deprecated. CompactionSummaryMessage renders as a slim divider (── 📷 compacted · ctrl+o ──), expanding to the summary + snapcompact frame count. session-manager.buildSessionContext gains a { transcript: true } mode; an exported buildSessionContextFromFile() reads a session file without taking the writer lock so the hub chat view can tail any agent (parked or live). Theme picks up icon.camera + tool.irc symbol entries.
- Added pre-TUI startup input capture that queued non-empty Enter submissions.
- Replayed queued startup submissions after initialization and injected startup editor text into InteractiveMode.
- Handled startup Ctrl+C to clear typed text and Ctrl+D to exit, with detach restoring terminal state.
- Extended TUI Editor `onSubmit` to accept `void | Promise<void>` for async handlers.
- add discovery of `TITLE_SYSTEM.md` and pass it through interactive startup context
- route custom title prompts to online and local tiny title generators via protocol
- update session-title docs and changelog with override behavior
- add tests for prompt discovery, forwarding, and fallback to bundled title prompts
- Added "available" status so recognized servers show under lazy mode without warmup.
- Rendered full welcome box as pre-TUI splash with fixed slot heights to avoid layout shift.
- Reported lazy servers as available in /status instead of omitting the section.
Move bundled models, model cache/manager, thinking metadata, effort helpers,
provider descriptors/discovery, wire constants, and model identity utilities
into the new @oh-my-pi/pi-catalog package.
Update pi-ai to keep provider runtime/auth concerns, move catalog provider
metadata into CATALOG_PROVIDERS, and migrate coding-agent, agent, stats, docs,
and tests to import catalog values from pi-catalog.
Split coding-agent model registry helpers into discovery, roles, and models
config modules while preserving registry orchestration.
BREAKING CHANGE: @oh-my-pi/pi-ai no longer exports catalog subpaths such as
/models, /model-cache, /model-manager, /model-thinking, /effort,
/provider-models*, discovery helpers, and provider wire constants; use the
matching @oh-my-pi/pi-catalog subpaths instead.
- Added lazy async module loaders for @babel/parser, linkedom, puppeteer/browsers, @mozilla/readability, @xterm/headless, and mnemopi to avoid loading them during cold startup.
- Added an interactive startup splash before session construction and skipped it for resume/fork/continue, quiet mode, timing mode, or non-TTY runs.
- Updated JS import-rewrite and memory tests to match async parser loading and preloaded mnemopi modules for sync state helpers.
- Stored last-seen version in ~/.omp/agent/last-changelog-version so version bumps no longer dirty user configs.
- Migrated the legacy config.yml key into the marker, never clobbering a newer existing marker.
- Added read/write helpers and migration tests.
- 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.
- Defer MCP server discovery off the first-paint critical path for UI
sessions; tools and slash commands stream in through the existing
live-refresh channel once each server connects (non-UI modes keep the
blocking path). ~290ms off first paint with MCP servers configured.
- Build the model catalog's canonical-equivalence index lazily on first
read instead of eagerly in the ModelRegistry constructor. A default
interactive launch never reads it pre-paint, moving the ~210ms build
(over ~3,200 models) off the critical path: ~244ms (~16%) off cold boot.
- Memoize per-session read summaries (tree-sitter parse) on the content
hash of the freshly-read bytes; the file is still read fresh each call
so results stay correct. Repeat same-file summary read 17ms -> 2.4ms.
- Reuse the Markdown subtree across streaming reveal ticks, memoize
grapheme counting, and stop re-highlighting finalized thinking blocks.
- Attribute the previously-unlabeled synchronous boot region in the
PI_TIMING table and add a bench:guard boot-regression target.
`omp --resume <id>` and `omp --fork <id>` previously crashed with
`[Uncaught Exception] Error: Session "..." not found.` followed by a
stack trace whenever the id did not match an existing session. The
throws in `createSessionManager` were never caught by `runRootCommand`,
so they fell through to the global `unhandledRejection` handler in
`postmortem.ts` and printed the raw stack instead of a clean message.
Add `SessionResolutionError` (a dedicated subclass of `Error` with an
optional usage `hint`) and use it for every user-facing resolution
failure: unknown `--resume`/`--fork` id, `--fork` combined with
`--no-session`, and the non-interactive cross-project / moved-cwd
prompts. `runRootCommand` catches it around the `createSessionManager`
call, writes `Error: <msg>` (and the hint when present) to stderr, and
exits with code 1. Other (unexpected) errors still propagate so they
remain visible to the postmortem handler.
Fixes#2084
- Removed `<turn-aborted>` guidance injection from `transformMessages`, deleted `turn-aborted-guidance.md`, and dropped the synthetic abort note path for aborted/error turns.
- Updated `c`/`.` continue shortcuts to submit `manual-continue.md` as a hidden synthetic `developer` message via `session.prompt(..., { synthetic: true })` instead of sending an empty user turn.
- Updated tests and changelog notes in AI and coding-agent to reflect the revised abort-context and continue behavior.
- Added first-party-first provider priority defaults for model ranking.
- Consolidated model resolution to use getModelMatchPreferences from session settings.
- Prioritized providerPriorityRank ahead of usage rank when picking preferred models.
- Added second-pass fallback to default-model or API-key-valid matching order.
- Handled local resumes with missing source CWD by prompting to move and reopening sessions.
- Shared missing-CWD relocation logic between local and global resumes for consistency.
- Added regression test for local explicit-session-dir resumes and session-header cwd updates.
When a session's working directory is moved or renamed (e.g. `git worktree
move`), the session file stays under the old cwd-encoded bucket while the new
directory is empty. Resuming was lossy:
- `--continue` rejected the terminal breadcrumb purely on cwd mismatch and then
found nothing in the new bucket, silently starting a fresh empty session.
- cross-project `--resume <id>` only offered to *fork* (duplicate) the session
into the new directory, forcing manual id selection and leaving a stale copy.
Detect relocation via the strong, low-false-positive signal "recorded cwd no
longer exists on disk" and re-root in place with the existing `moveTo()`:
- `continueRecent` re-roots the terminal's last session into the current
directory when its recorded cwd is gone and the new location has no sessions
of its own (otherwise behavior is unchanged). `readTerminalBreadcrumb` is
refactored into `readTerminalBreadcrumbEntry` returning the raw cwd +
session file so callers can interpret a cwd mismatch.
- cross-project `--resume <id>` offers "Move (re-root)" instead of fork when the
source directory is gone; a still-existing different project still forks.
Tests: continue-relocation (re-root on move, no-hijack on plain cd, prefer
local recent) and cross-project move-vs-fork routing.
- Added a clear-initial-terminal-history flag to interactive mode initialization and passed it from cold-launch startup.
- Extended TUI.start to accept clearScrollback and clear native scrollback on initial full paint for non-multiplexer sessions.
- Preserved ED3 streaming scrollback accounting during capped streaming frames and added tests to prevent committed prefix duplication across terminal history rewrites.
- Lazy-loaded OTEL SDK, HTML export, TTSR, and autoresearch modules.
- Made resolveMemoryBackend async to import backends on demand.
- Replaced backend resolution with direct settings reads for rekey checks.
- Deferred setup wizard import until setup was forced or version stale.
- Dynamically loaded ACP, RPC, and print mode runners only when used.
- Added a marketplace auto-update scheduler with off-mode early exit and non-blocking errors.
- Added setup-version assertions to keep CURRENT_SETUP_VERSION aligned with scenes.
- Cleared native scrollback on `omp`/`omp -c` so the resumed transcript no longer stacks on the prior run's welcome screen.
- Tracked assistant block finalization so aborted streaming messages stay repaintable when status rows land beneath them on ED3-risk terminals.
When OTEL_EXPORTER_OTLP_ENDPOINT (or _TRACES_ENDPOINT) is set, register a
global OTLP/proto TracerProvider and switch on the agent loop's telemetry
so its invoke_agent / chat / execute_tool spans reach a collector instead
of a no-op tracer. Honors the standard OTEL_* env contract
(OTEL_SERVICE_NAME, OTEL_SDK_DISABLED, OTEL_TRACES_EXPORTER=none) and the
OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT capture toggle; no-op
when no endpoint is configured.
Uses the exporter-trace-otlp-proto 2.x line, which exports cleanly under
Bun (the 1.x line deadlocks). Adds a flushTelemetryExport() helper and a
periodic + signal-driven flush so long-lived processes surface spans.
This makes the existing telemetry usable from hosts that spawn omp as a
child process (e.g. an ACP harness), where an in-process provider
registered by the parent can't reach the child process.
can1357