- Added `Settings.reloadForCwd` to mutate the live instance in place, so `/move` and cross-project resume pick up the destination project's `.claude/settings.yml` and path-scoped `enabledModels`/`disabledProviders`.
- Wired `reloadForCwd` into `applyCwdChange` (interactive mode) and the `--resume` startup path so settings always follow the active working directory.
- Added tests covering path-scoped re-resolution, no-op on same directory, and disk-backed project layer load/drop.
- Enabled resume picker to preload sessions and toggle folder/all scope with Tab.
- Enabled resume flow to fall back to all-project sessions and switch cwd on resume.
- Added centralized applyCwdChange to refresh caches, commands, and UI after cwd updates.
- Updated session restoration to adopt restored session cwd and sessionDir when present.
Separated the fork prompt result into accepted, declined, and unavailable states.
Interactive declines now return cleanly through runRootCommand, while non-TTY
invocations continue to fail with a diagnostic instead of silently exiting 0.
Updated regression coverage for both branches.
Fixes#1668
createSessionManager threw `Session "X" is in another project (Y).` when
the user answered "n" to the fork prompt, and runRootCommand never caught
it. The throw bubbled up as an Uncaught Exception with a stack trace.
Return undefined from the decline branch instead, and treat
`typeof parsed.resume === "string" && !sessionManager` in runRootCommand
as a user cancellation: print a dimmed "Resume cancelled" message and
return cleanly (exit 0), mirroring how the picker UI handles
"No session selected".
Fixes#1668
Two review fixes for the extension-flag/initial-prompt work:
1. @file ordering — `processFileArguments` runs `process.exit(1)` on a
missing/unreadable file. It had been moved after `createSession`, which
writes the terminal breadcrumb eagerly (SessionManager.create →
#newSessionSync), so `omp @missing.md "x"` left a junk session/breadcrumb
behind before exiting.
Resolve extension-registered CLI flags BEFORE creating the session: load the
session's extensions up front (new `loadSessionExtensions` helper, the single
source of createAgentSession's discovery-branch logic), build an
ExtensionFlagSink straight from the loaded extensions + runtime, re-parse
argv, then process @file args — all before any session exists. The loaded
result is handed back to createAgentSession via `preloadedExtensions` (now
checked before `disableExtensionDiscovery`, so it can't double-load) and the
same EventBus is shared, so no extra work. This keeps the P1#1 fix
(`--flag @value` is the flag's value, not a file) while failing fast with no
session side effects.
2. "Can we avoid the big list of names?" — removed the hand-maintained
`BUILTIN_FLAG_NAMES` set (and its stale "rejected at registration" doc).
`applyExtensionFlags` now always falls back to recovering a flag's value from
argv when parseArgs didn't surface it; the recovery scan mirrors parseArgs's
consumption rules (flag-looking space-form values stay their own flag) and is
a no-op for flags that were absent or already surfaced, so no list of
built-in names is needed.
Adds `ExtensionRunner.aggregateFlags` (static) so getFlags and the CLI's
pre-session sink share one implementation.
Tests: pre-session flag resolution via the exact main.ts sink pattern;
list-free recovery of an arbitrary colliding built-in (`--model`); and the
flag-looking-value rule. Verified typecheck + extension/runner/acp suites.
Three issues from an adversarial review, all rooted in the startup argv parse
running before extensions load:
1. Flag-looking string values (`--name --print`): the extension-aware reparse
consumed the following token as the value, disagreeing with the startup
parse that treated `--print` as the built-in flag — so the reparse could
silently flip command shape. Extension string flags now consume a following
token only in `--flag=value` form or when it is not flag-looking; pass a
flag-looking value as `--flag=value`. Keeps both parses consistent.
2. `@file` string values (`--target @notes.md`): file args were processed from
the startup parse, which misreads the value as a file and reads it into the
prompt. processFileArguments now runs on the extension-aware parse
(initialArgs.fileArgs); pipedInput stays early for mode detection.
3. Built-in collisions: an extension flag named like a built-in (e.g. `model`)
was consumed by the built-in branch and never delivered to the runner.
registerFlag now rejects names in BUILTIN_FLAG_NAMES with a clear error
(isolated per-extension by loadExtension's try/catch).
Adds tests for all three plus the documented startup-parse misclassification.
Addresses review: a string extension flag in equals form (--spawn-peer=reviewer)
was still leaking its value into the initial prompt. Root cause was a second,
hand-rolled argv parser in applyExtensionFlagValues that recognized only
`--flag` and `--flag value`, not `--flag=value`; it looked up the literal name
`spawn-peer=reviewer`, set nothing, and (because the reparse was gated on
"were values set") skipped the reparse entirely, so the extension-unaware
startup parse won — leaving `reviewer` as the first message. The extension
itself also never received the value.
Replace the duplicate parser with a single source of truth: extract
applyExtensionFlags() into cli/extension-flags.ts, which re-parses argv through
the same parseArgs() the startup pass uses (now seeded with the registered
flags) and pushes the resulting values onto the runner. parseArgs already
normalizes `--flag`, `--flag value`, and `--flag=value` identically, so no flag
form can be handled by one parser and missed by the other. The reparse is now
gated on registered-flag presence, not on values having been set.
Wires parseArgs's previously-unused `unknownFlags` output to the runner, and
removes the now-redundant parseArgs import from main.ts. Adds unit tests for
applyExtensionFlags across all flag forms (including equals form) plus the
no-runner / no-flags / no-args-passed gate cases.
The `--option=value` handling splices the value into the argv to reuse the
`args[++i]` path, mutating the caller's array. The post-extension reparse in
runRootCommand then ran on that already-mutated argv, so
omp --model=sonnet --spawn-peer reviewer "review"
re-spliced `sonnet` and leaked it into the initial prompt before "review".
parseArgs now copies its input and never mutates the caller's array, so
launch, acp, and the reparse are all safe. Drops the now-redundant
`[...rawArgs]` copy at the reparse site, and adds regression coverage for the
--option=value + extension-flag combo plus input non-mutation.
The root command parses argv twice — once at startup before extensions
load (so their flag set is unknown) and once after the extension runner
is ready. buildInitialMessage was reading the first, extension-unaware
parse, so a string-valued extension flag's value leaked into the prompt:
omp --spawn-peer reviewer "review the diff"
sent "reviewer" as the first message instead of "review the diff" — the
--spawn-peer token is dropped (it starts with "-"), but its bare value
is mis-read as the first positional message.
Build the initial message from args re-parsed with the extension flag map
(session.extensionRunner.getFlags()) whenever any extension flag was
applied, so the flag and its value are consumed before the prompt is
assembled. Generic across any flag-registering extension; no behavior
change when no extension flags are present.
Adds regression coverage for the parse/build pipeline: string + boolean
extension flags are consumed correctly, and the pre-fix leak the second
parse corrects is pinned.
- Added AUTO_THINKING as a configured thinking level in settings, schema, SDK, and session plumbing.
- Implemented per-turn auto reasoning classification with online/local prompts, effort clamping, and skip guards.
- Updated model selectors, ACP options, footer/status UI, and events to render auto and auto->resolved states.
- Added AUTO_THINKING parse/clamp tests and fixed local-module cycle and hashline preview regressions.
- Added setup wizard with provider login, glyph mode, and theme scenes shown once per setup version.
- Wired `omp setup` (no args) to trigger the wizard in a TTY; `--check`/`--json` still show help.
- Extracted `gradientEscape` and exported `PI_LOGO`/`ShineConfig` from welcome for shared use in splash/outro.
- Fixed race condition in `setSymbolPreset`/`setColorBlindMode` by tracking load request IDs.
Bug 1: capability loaders in src/discovery/builtin.ts only walked
.omp/ and ~/.omp/agent/, so extension packages registered via
extensions: in settings or --extension on the CLI shipped their
skills/, hooks/pre|post/, tools/, commands/, rules/, prompts/, and
.mcp.json silently — the docs at omp.sh/docs/extension-authoring
advertise the opposite. Add a new omp-plugins discovery provider that
scans every configured extension package directory for those
sub-trees, plus a small omp-extension-roots helper that resolves the
union of settings-driven and CLI-injected roots. main.ts injects CLI
extension paths via injectOmpExtensionCliRoots before any capability
load.
Bug 2: install was never registered as a top-level subcommand, so
`omp install ./my-extension` was rewritten to `launch install
./my-extension` and forwarded to the LLM as an initial prompt. Add a
top-level install command that routes local paths to plugin link and
remote specs to plugin install. Extract the command table into
src/cli-commands.ts so tests can introspect registered subcommands
without triggering cli.ts's top-level await.
Fixes#1496
Agent.prompt() has a keepalive (PR #1464) but it disposes before
#waitForPostPromptRecovery() runs. The unresolved Promise.withResolvers
(#retryPromise, #ttsrResumePromise, #postPromptTasksPromise) persist
after Agent.prompt() returns, causing Bun's event loop to busy-wait
in --resume and post-prompt recovery states.
Install EventLoopKeepalive at the caller level (main.ts) so the
keepalive covers the entire session.prompt() lifecycle including
post-prompt recovery. Uses `using` declaration for automatic disposal.
Related: #1384, #1419, #1464
- Replaced the `keepaliveWhile` Promise wrapper with a new `EventLoopKeepalive` class that registers and disposes an interval timer through `Symbol.dispose`.
- Updated `Agent` to instantiate `EventLoopKeepalive` via `using` during prompt execution instead of manually managing an interval.
- Wrapped interactive mode's await path with the new helper and removed redundant `keepaliveWhile` usage from the CLI entrypoint.
Rebase on main accidentally dropped these two code paths that exist
on the current main branch:
- autoApprove field in CreateAgentSessionOptions
- settingsInstance.override('tools.approvalMode', ...) for --approval-mode
Both are now restored to match upstream main.
Root cause: Bun 1.3.x (JavaScriptCore) busy-waits when the only
pending work is an unresolved Promise. A setInterval keepalive
keeps the event loop in epoll_wait instead of userspace spinning.
- EventLoopKeepalive: setInterval-based keepalive (re-arms after each
firing, addressing the bot review concern about setTimeout expiry)
- keepaliveWhile(): wrapper to await a Promise with keepalive active
- Applied to getUserInput() in main.ts
- Retains yieldIfDue() and ExponentialYield from #1396
Idle CPU drops from ~100% to ~0% (wchan=do_epoll_wait).
- Added a new `approvalMode` argument to CLI parsing with validation for `auto`, `prompt`, and `custom` values.
- Registered `--approval-mode` on the launch command so it appears in generated help output.
- Applied the parsed approval mode as a runtime override on `Settings`, ensuring downstream `tools.approvalMode` reads reflect the CLI value.
Re-introduces the per-tool approval system from luzidd's commit 39124f3 (which
is no longer reachable from main) and improves it before re-landing.
What's restored:
- ApprovalPolicy (allow/deny/prompt) plus DEFAULT_APPROVAL_POLICIES.
- ACTION_EXCEPTIONS registry (LSP read-only, bash critical patterns).
- getApprovalPolicy() six-level resolution order.
- ExtensionToolWrapper.execute() gate before extension handlers.
- --auto-approve / --yolo CLI flag and tools.approval.<tool> user config.
- docs/approval-mode.md user guide.
What's improved over the original:
- Replaced unchecked 'as any' casts with typed unknown narrowing helpers.
- Validate userConfig values: invalid strings, numbers, etc. fall through to
the built-in default instead of being silently honoured (typo no longer
locks a tool out or grants implicit approval).
- Expanded CRITICAL_BASH_PATTERNS: chmod -R /, chown -R /, bash <(curl ...),
writes to /etc/passwd|shadow|sudoers, shutdown/reboot/halt/init 0,
kill -9 1, nc -e / nc -c reverse shells. Pattern shapes require a
command-position boundary so 'npm run reboot-tests' and 'echo "shutdown the
queue"' don't false-positive.
- Added DEBUG_READONLY_ACTIONS exception so DAP inspection actions (threads,
stack_trace, variables, scopes, read_memory, …) auto-allow while
execution-side actions (launch, attach, continue, evaluate, write_memory,
set_breakpoint, …) still prompt.
- formatApprovalPrompt: labels mcp__<server>__<tool> calls as MCP server
tools, surfaces ssh host + command, recognises the modern § hashline header
for edit, and truncates >240-char fields so a heredoc-sized body cannot
blow out the confirmation dialog.
- Test suite grown from 40 to 57 cases — new coverage for invalid user
config, the extended critical-bash patterns, benign-keyword negatives,
debug exceptions, MCP/ssh prompt formatting, and command truncation.
Verification:
- bun test packages/coding-agent/test/tools/approval.test.ts -> 57 pass
- bun x biome check . -> clean
- bun run check:ts across all 9 workspaces -> clean
Wire --hide-thinking launch flag that sets hideThinkingBlock before TUI
init. Display-only: does not disable model reasoning, just hides the
thinking output in the terminal.
- Add hideThinking to Args interface and parseArgs
- Add --hide-thinking flag definition in launch command
- Apply setting via settingsInstance.override in main
Closes#1313
Keep chat notifications emitted during session_start visible after the initial transcript render rebuilds the chat container. Add regression coverage for preserving startup notifications during initial render.
Fixes#1316
ACP clients own MCP server configuration via session/new.mcpServers and AcpAgent#configureMcpServers. The ACP session factory previously left enableMCP at its default (true), so createAgentSession ran discoverAndLoadMCPTools on every session/new and the resulting host MCP tools landed in the session tool registry alongside the client-supplied ones. search_tool_bm25 then surfaced only the host tools.
Force enableMCP: false on every session created through createAcpSessionFactory so on-disk discovery is bypassed in ACP mode. Non-ACP modes (omp interactive, print, RPC) keep auto-discovery.
Fixes#1234
- Tracked ACP tool-call inputs per session and replayed them via `toolArgsById`/`getToolArgs` plumbing.
- Merged ACP tool execution end content from start and result events so command output replay preserves original args.
- Scoped ACP async-job draining by session `ownerId` and `agentId` with in-flight tracking and permission-gated deferred turns.
- Refactored compaction telemetry and async tests with per-test telemetry setup and asynchronous teardown resets.
- Wrapped initial and subsequent print-mode prompts with `logger.time` for timing instrumentation.
- Printed collected timings after session run when `PI_TIMING` env var is set.
- Added GoalRuntime with wall-clock and token accounting, budget steering, and lifecycle operations (create, pause, resume, drop, complete).
- Exposed goal tool as a hidden agent tool, activated only when goal mode is enabled.
- Integrated goal continuation loop in InteractiveMode with auto-submit between turns.
- Added status line segment and theme icons for goal mode state.
- Adds omp acp subcommand that launches the agent as an ACP stdio server
- Registers the subcommand in the CLI dispatcher
- Threads terminal-auth args and ACP flags through the launch and main orchestrators
- Exports AgentSession on the public SDK surface
- Updates skills loader to support skill→slash-command conversion and prompt injection
- Updates input-controller to dispatch ACP built-in slash commands
rpc-ui sets hasUI=true which causes the bash tool to take the
runInteractiveBashPty path when pty=true. RpcExtensionUIContext.custom()
is a stub returning undefined, so result.cancelled dereferences undefined
and throws. PTY bash requires a live TUI overlay; rpc-ui only provides
dialog-style UI. Set PI_NO_PTY for rpc-ui so the usePty guard in
bash.ts stays false.
Adds a new `rpc-ui` mode that extends the existing headless RPC mode with
interactive tool support (ask tool, extension UI dialogs, etc.).
In plain `rpc` mode the session has `hasUI=false` and no UI context is
wired, so interactive tools are disabled. `rpc-ui` mode sets `hasUI=true`
and wires a single shared `RpcExtensionUIContext` instance into both the
tool context store and the extension runner. Both consumers share the same
`pendingExtensionRequests` map and output closure, so `extension_ui_response`
messages received on stdin are routed to the correct waiting promise
regardless of which code path (tool or extension) created the request.
Changes:
- `args.ts`: add `rpc-ui` to the `Mode` union and the parse guard
- `launch.ts`: expose `rpc-ui` in the OCLIF flag definition and help text
- `main.ts`: propagate `rpc-ui` through all RPC-mode guard conditions and
pass `setToolUIContext` to `runRpcMode` when the mode is `rpc-ui`
- `rpc-mode.ts`: accept optional `setToolUIContext` callback; create one
shared `RpcExtensionUIContext` instance and pass it to both the tool
context store and the extension runner
- 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.
- Replaced duplicated plugin-registry cache invalidation blocks with clearPluginRootsAndCaches in command and selector setup paths.
- Updated OMP plugin registry path resolution to use getPluginsDir for reads and cache invalidation, matching marketplace write locations.
- Removed a redundant project-scope marketplace test after centralizing cache-root invalidation logic.
- Added memory.backend and memories.enabled to the RPC defaulted settings list.
- Ensured RPC hosts can pick up explicit memory configuration defaults from the settings layer.
The --list-models handler in runRootCommand short-circuited to
listModels() right after Settings.init and modelRegistry.refresh,
exiting before extension loading ran in createAgentSession. As a
result, providers contributed via pi.registerProvider() (from -e
paths or settings.extensions) never appeared in the listing.
Extract a runListModelsCommand entry point in cli/list-models.ts
that loads extensions (CLI -e paths and settings.extensions) into
the supplied ModelRegistry, mirroring sdk.ts's handoff of pending
provider registrations, and then delegates to listModels. The load
is intentionally narrow: no agent loop, no MCP servers, no custom
tools.
Fixes#905
- Consolidated AI provider imports through register-builtins and moved Gemini/Antigravity header helpers to a shared module.
- Added lazy loading for heavy providers and SDK-backed modules with cached initialization to trim startup cost.
- Converted markdown conversion helpers to async and awaited htmlToBasicMarkdown in affected scraper and kernel output paths.
- Parsed bundled agent definitions on-demand and moved BrowserTool prompt rendering behind a memoized getter.
- Added cached validation/error handling paths by replacing AJV runtime checks with Value.Check and trimming validation error output.
- Tracked `models.json` modification time in the registry to skip redundant static model reloads when unchanged.
- Reworked model overlay merges and package-runner detection to use indexed lookups plus parallel file/JSON scans instead of sequential searches.
- Cached compiled prompt templates and reduced startup work by bypassing up-to-date changelog parsing and deferring background model refresh.
- Parallelized startup by deferring plugin preload and running AGENTS.md scan plus context/template/command discovery in parallel.
- Added AgentsMdSearch exports and options so prebuilt search results were passed into system-prompt construction.
- Reworked logger timing to use AsyncLocalStorage-backed nested spans, initialize a root span, and emit hierarchical summaries.
- Added PI_TIMING-gated TS/TSX module-load timing via side-effect module-timer registration and wrapped key init/request paths with logger.time.
- Added task.simple to settings and schema with default, schema-free, and independent modes.
- Added mode-aware task schema and validation to enforce context/schema rules per simple mode.
- Updated prompts and template rendering to tailor headers and guidance for each simple mode.
- Added simple-mode capabilities and updated TaskTool execution for mode-aware context behavior.
- Added tests for independent rendering and mode-specific rejection of invalid context or schema inputs.
- Removed `SearchDb` APIs and `searchDb` fields, dropping db-backed state from native and agent sessions.
- Replaced crate export `fff` with `fd`, moving fuzzy-find bindings into `fd.rs`.
- Removed `SearchDb`/picker fast-path logic from `glob` and `grep`, simplifying scan flow and dropping db args.
- Removed `SearchDb`/`getSearchDb` wiring from extension, tool, and task context constructors across coding-agent.
- Added over-indentation validation warnings in chunk-edit normalization for suspicious `~` body line formatting.
- Removed `bytes`, `fff-grep`, `fff-search`, and `blake3` deps, adding `grep-searcher = "0.1"`.
can1357