`/mcp reauth` and `/mcp add` consume `authResult.oauth` directly when the JSON error body carries endpoints, skipping `discoverOAuthEndpoints`. Leaving `oauth.scopes` empty there meant a challenge-only `scope="…"` still yielded a scope-less grant even though `AuthDetectionResult.scopes` recorded it.
Merge `challengeScopes` into the returned `OAuthEndpoints` inside `analyzeAuthError` so every consumer sees the same scope. Added a regression test where the JSON body advertises endpoints without `scopes` and the challenge is the only source.
Refs #4467
MCP servers such as JIT gateways advertise required scopes via the RFC 6750 `WWW-Authenticate` challenge (`scope="..."`) and via RFC 9728 protected-resource metadata (`scopes_supported` / `scopes` / `scope`), then reject follow-up requests with `insufficient_scope` when a bearer token was issued without them. OMP's discovery only picked up `scopes_supported` from the auth-server metadata document, so `/mcp reauth`, `/mcp add`, and the MCP add wizard silently minted scope-less tokens.
- Extract `scope`/`scopes` from the WWW-Authenticate challenge into a new `AuthDetectionResult.scopes` field via `extractOAuthChallengeScopes`.
- Thread a `protectedScopes` option through `discoverOAuthEndpoints` and its recursion; capture `scopes_supported`/`scopes`/`scope` off resource-metadata documents; use those scopes when the auth-server metadata omits them.
- Pass `authResult.scopes` from `analyzeAuthError` into every discovery call site (`/mcp reauth`, `/mcp add`, MCP add wizard).
- Add regression tests for insufficient_scope + resource_metadata, resource-metadata `scopes_supported` passthrough, and challenge-scope threading.
Fixes#4467
Bridge-backed writes now respect tool timeout/cancel: routeWriteThroughBridge takes an optional AbortSignal and forwards it to notifyWorkspaceWatchedFiles, so a wedged LSP server no longer hangs the bridge path.
Updated write, replace, patch, and hashline callers to pass the tool signal.
Refs #4459
Announced harness-authored create, change, and delete operations to active LSP clients with workspace/didChangeWatchedFiles before edit-time diagnostics are read.
Added regression coverage for non-LSP sibling files in a batched write so diagnostics see the workspace state the harness just produced.
Fixes#4459
Collapsed duplicate byte-identical non-empty LSP text edits before overlap validation so rename_file accepts idempotent server output while still rejecting real conflicts.
Fixes#4458
Recall silently clipped every result to 500 chars mid-word with no marker,
and memory_edit update replaces content wholesale by id. There was no way
for an agent to inspect the full row before overwriting it: Mnemopi.get
existed but nothing surfaced it, and the advertised URI only served the
file-backed memory summary. The natural recall/inspect/update loop had no
inspect step.
Three fixes across mnemopi and coding-agent:
- recall now appends an ellipsis marker when it clips content and reports
truncated=true plus full_length. The cap is exposed as
RecallOptions.contentPreviewChars (default 500, 0 disables). The factLine
200-char clip used by the enhanced-context sandwich gets the same marker.
- Under the mnemopi backend the read-tool URI scheme now routes an id host
to Mnemopi.get() across every session's scoped banks, returning the row
as text/markdown with a YAML-frontmatter header (bank, store, source,
timestamp, importance, veracity). The root namespace remains for the
file-backed summary. Miss errors now name the backend explicitly.
- Updated the recall and memory_edit tool prompts to document the
truncation marker and require reading the full memory before any
wholesale content update.
Fixes#4443
runEvalAgent short-circuits on subagent error before mergeIsolatedChanges runs, so branch-mode transfer failures previously threw with just result.error and the caller never learned where the preserved patch lived. Enrich the pre-merge failure and reuse a shared recovery-hint builder for the apply/nested-patch failure paths so the captured patch path, branch name, and nested-patch artifacts are always surfaced.
Fixes#4437
Capture a patch artifact from the live isolation worktree when branch-mode commit transfer fails, before cleanup can destroy the untransferred objects.
Fixes#4437
An intermediate commit whose net effect is already on HEAD (redundant
change, or 3-way merged to HEAD by "theirs == ours") stopped the
sequencer with "The previous cherry-pick is now empty" and was
treated as a hard conflict. mergeTaskBranches aborted the whole range,
marked the branch failed, and dropped every remaining non-overlapping
commit.
Add cherryPick.skip and cherryPick.isEmptyError to the git namespace,
then in mergeTaskBranches' catch classify the failure before aborting:
loop --skip while the error stderr matches the "now empty" phrase so
consecutive empties advance the sequencer; fall through to abort/fail
on the first non-empty error (genuine conflict with unmerged files).
Fixes#4438
A request the provider rejects (e.g. 413 oversized payload) yields a
synthesized assistant turn with empty content and stopReason 'error'.
That turn is written to session.jsonl, so on reload it replays as an
empty assistant turn and re-sends the same rejected context. Keep the
rejection UI-only (pinned error) and out of persisted history so a
reloaded session resumes from the last good turn.
Under jj the git branch label is unhelpful - a colocated repo parks git
HEAD detached, and a secondary jj workspace has no git at all. The `git`
segment now overlays the jj working-copy label (bookmarks + short
change-id) in both cases, via a read-only `jj log --ignore-working-copy`
query that is throttled and cached (and force-refreshed on a git-HEAD
change). Plain git repos and non-jj dirs are unchanged. Extracted a
testable `jj-info` module (root detection, query, format).
Refs can1357/oh-my-pi#3582
A `blocked` status (plus `block`/`unblock` ops and an optional blocker
note) for tasks that are open but waiting on something the agent can't act
on — a user decision, another agent, or an external action. Blocked tasks
stay in the tracker but are excluded from the stop-time incomplete-todo
reminder (via the existing pending/in_progress allowlist) and from
auto-promotion. Syncs the mode-layer TodoStatus, the ACP status map/guard,
the markdown markers, and the renderers.
Refs can1357/oh-my-pi#3581
Forward unresolved explicit subagent model selectors into child session startup so modelRoles.task cannot disappear during executor preflight and fall through to an unrelated provider default.\n\nFixes #4421
Codex review flagged that advertising `launchUrl`
(http://localhost:<omp-port>/launch) as the visible `Copy URL:` breaks
SSH/WSL/headless users: their local browser resolves the URL against
the local machine (no OMP listening) and fails before ever hitting the
provider. On terminals without OSC 8 support, they lose the manual
`/login <redirect>` path entirely.
Every OAuth-facing surface now shows the full authorization URL as the
primary copy target and offers `launchUrl` as an additional "Local
shortcut (this machine only)" line for wide-terminal local users who
want the truncation-safe convenience:
- MCPAuthorizationLinkPrompt renders `Copy URL:` with the full URL and
appends the local-shortcut row only when `launchUrl` differs. OSC 52
clipboard staging in the MCP onAuth handler switches to the full URL
(OSC 52 is a wire-level protocol — the terminal writes to the
caller's LOCAL clipboard even when OMP is on a remote SSH box).
- LoginDialogComponent.showAuth, selector-controller onAuth,
setup-wizard sign-in, and the auth-broker CLI mirror the pattern:
full URL first, launchUrl as an optional local shortcut.
- Setup wizard uses `wrapTextWithAnsi`, not truncation, so the RFC
7636 §4.3 downgrade bug that motivated launchUrl is unreachable
through it; still surfaces launchUrl for wide-terminal convenience.
Regression tests in
`packages/coding-agent/test/modes/controllers/mcp-authorization-link.test.ts`
now assert:
- Full URL is the primary `Copy URL:` line so SSH sessions can complete.
- launchUrl still appears beneath as `Local shortcut (this machine only): …`
when it differs from the full URL.
- No shortcut row when launchUrl is absent OR equals the full URL.
Codex review flagged two P2s the reporter (@DylanBohlender) confirmed:
1. OAuthCallbackFlow#handleCallback checked LAUNCH_PATH BEFORE the
`pathname !== this.callbackPath` guard, so an OMP config that pinned
the provider callback at `/launch` (via `oauth.callbackPath` or a
matching `oauth.redirectUri`) had the launch route eat its
`/launch?code=...&state=...` redirect and 302 it back to the
authorization URL instead of resolving the callback. Reorder so
`callbackPath` resolution wins the collision, and suppress `launchUrl`
in that case (also when `redirectUri`'s pathname resolves to `/launch`
even without an explicit `callbackPath` override) so UIs never
advertise a self-redirecting copy target.
2. RpcClient.login's `open_url` listener called
`onOpenUrl(req.url, req.instructions)` and dropped `launchUrl`, so SDK
hosts built on the public helper couldn't surface the truncation-safe
copy target. Extend the callback signature to
`(url, instructions?, launchUrl?)` and forward the field — backward
compatible for existing 1-2 arg consumers.
Regression tests in packages/ai/test/callback-server-launch-route.test.ts:
- callbackPath = /launch: launchUrl is undefined AND a
`/launch?code=...&state=...` request resolves via the callback template
(200/HTML), never 302s to the authorize URL.
- redirectUri pathname = /launch (callbackPath default): launchUrl still
suppressed defensively by the parsed-pathname guard so the base class
never advertises a colliding launch route even when callers skip the
MCPOAuthFlow path-derivation.
Two independent defects broke /mcp reauth against S256-only providers on
Windows boxes whose PATH no longer references System32:
1. openPath spawned bare rundll32 and swallowed the
`Executable not found in $PATH` throw with a bare `catch {}`, so the MCP
controller's outer try/catch was dead and the transcript unconditionally
claimed "Opening browser automatically...".
2. TUI#prepareLine silently truncates any composed row wider than the
viewport. MCPAuthorizationLinkPrompt rendered `Copy URL: <full URL>` as a
single ~271-column line whose trailing parameter is
code_challenge_method=S256. On the reporter's 270-col terminal the cut
landed inside that parameter, dropping the method while keeping
code_challenge — which RFC 7636 §4.3 treats as plain PKCE, which Linear
correctly rejects with "The plain PKCE method is not allowed. Use S256
instead."
OAuthCallbackFlow now hosts a `GET /launch` route on the same loopback
callback server it already runs; the route 302-redirects to the pending
authorization URL and is advertised as `OAuthAuthInfo.launchUrl` — a
~30-char copy target no viewport can meaningfully truncate. The MCP OAuth
fallback, /login, setup wizard, auth-broker CLI, and login-dialog all
prefer the launch URL for the visible copy target, keep the full URL in
the OSC 8 hyperlink for click-through, and the MCP flow additionally
stages the copy target on the clipboard via OSC 52 (same pattern the
setup wizard uses).
openPath now resolves rundll32.exe through %SystemRoot%\System32 (with a
C:\Windows fallback when SystemRoot is unset) and logs both synchronous
spawn throws and non-zero exits via the shared logger, so silent
misconfigurations show up in ~/.omp/logs/omp.*.log. The dead try/catch
around openPath in the MCP controller is removed.
Fixes#4418
Documented the 1-3600 second bash timeout clamp in the schema, model-facing prompt, and tool docs, including the async timeout behavior.
Added coverage that the shipped schema and rendered prompt expose the contract.
Fixes#4408
Filtered TypeScript project-resolution diagnostics for files with no root marker ancestor while preserving syntax diagnostics. Added regression coverage for Bun scratch files outside project roots.\n\nFixes #4401
- Omit Next from the guest multi-select ui-request options until at least
one option is checked or a custom answer exists, mirroring the local
dialog's disabled-Next gating. The remote select has no disabled-row
concept, so Next is omitted rather than dimmed (PRRT_kwDOQxs0bc6OFbDW).
- Add the bottomBorder(1) term to the ask dialog's fixed-row budget so the
rendered dialog no longer overflows the viewport by one row
(PRRT_kwDOQxs0bc6OFbDY).
- Add focused tests: guest wire-level Next gating round trip, and dialog
height <= viewport assertion.
Added an embedText projection for remember() so stored transcripts can remain readable while embeddings, FTS indexing, and embedding-model rebuilds use marker-free text. Updated coding-agent retention to pass the marker-free projection and strip retained protocol markers from recall display.
Fixes#4395
Auto-retain now slices the transcript after the last retained user turn before storing an episode, preventing cumulative duplicate session transcripts in mnemopi banks.
Fixes#4396
- Replace #requestGuestUiString's string|"unavailable"|undefined channel
with a tagged GuestUiResult ({answered}|{cancelled}|{unavailable}) so a
guest answer literally equal to "unavailable" no longer collides with
the transport-unavailable sentinel (PRRT_kwDOQxs0bc6OE3gN).
- Cap in-body question header rendering to MAX_HEADER_ROWS with ellipsis
truncation so long/multiline questions cannot push options off-screen
(PRRT_kwDOQxs0bc6OE3gS).
- Guest Other editor cancellation now continues the loop (multi) / re-shows
the select (single) instead of cancelling the whole ask
(PRRT_kwDOQxs0bc6OE3gU).
- Disable the Next row on a single-question multi-select until at least one
option or custom input is chosen, preventing empty-result submission
(PRRT_kwDOQxs0bc6OE3gY).
- Classified OpenAI-compatible custom relays serving OpenAI model ids into the OpenAI service-tier family.
- Passed the model into OpenAI service-tier wire gating so custom relays emit service_tier when eligible.
- Reported /fast on as unavailable when the active model has no service-tier family.
Fixes#4386
- Added collectProviderLimitTemplates to aggregate limit IDs across all reports.
- Updated formatUsageBreakdown to render placeholders for limits missing from specific providers.
- Standardized label widths across sibling providers to align status bars.
Op: correct
Restores: review:4375
- Widen ExtensionAskDialogResult to a union with { kind: "chat" } variant
so AskTool can distinguish chat handoff from cancel (undefined).
- AskDialogComponent.#finishChat passes { kind: "chat" } via onChat.
- Controller settles { kind: "chat" } locally and propagates a "chat"
sentinel through the guest/collab path instead of returning undefined.
- AskTool returns a chat-redirect AgentToolResult (chatRedirect details)
instead of aborting with ToolAbortError.
- #promptForNote prefills with the existing note only when editing the
same row (noteRowKey === rowItem.key), preventing cross-row note leaks.
- Add ask-dialog and ask tool tests for chat redirect and row-specific
note prefill.
- Reset the inactivity countdown in handleInput after the closed/prompt
guard, matching HookSelector/HookInput semantics so a user actively
navigating options/tabs is not auto-submitted by an absolute deadline.
- Add boundPromptTitle helper that flattens whitespace, wraps to the
terminal content width, and caps at 3 rows with ellipsis truncation;
apply it to custom-input and note prompt titles in the rich dialog
and the guest-UI editor path so long/multi-line questions stay usable.
- Drop totalRows from both ScrollView calls so the full allLines array
is sliced via scrollOffset + row; previously totalRows caused render
to read lines[row] instead of lines[scrollOffset + row], leaving the
viewport stuck at the top while the scrollbar thumb moved.
- Add tests for inactivity reset, bounded prompt titles, and scrolling.
Restores: review:4375
Op: correct
Timer-driven reveal and spinner ticks (streaming reveal, tool-args reveal,
tool-execution spinner, todo strike animation) now hand the changed
component to `TUI.requestComponentRender(component)` instead of forcing a
full-tree render at 30fps. Every other root subtree reuses its previous
frame rows, cutting the Box/Container tree walk out of the compose
pipeline while the transcript grows.
Shimmer:
- Intern the working-message palette per accent (WeakMap-keyed) so the
Symbol-slot compiled-ANSI cache in `shimmerSegments.compile` actually
hits between frames — the fresh palette literal in `renderWorkingMessage`
guaranteed a per-tick miss.
- Add an `activeBand` fast-path: outside the sweep window the intensity
is guaranteed zero, so those code points coalesce into a single low-tier
run without running `intensityFn` or `tierFor`. On the typical ~60-char
working message the classic band is 12 cells wide, so ~80% of the per-char
loop disappears.
Widen `ToolExecutionHandle` to extend `Component` (matches every
concrete impl — `ToolExecutionComponent`, `ReadToolGroupComponent` —
which already extend `Container`) so the reveal controller callback
sites are type-checked.
Fixes#4377
Sizing `maxTokens` off the static `model.reasoning` catalog flag cannot
distinguish a thinking model catalogued `reasoning: false` (e.g. Qwen3
served locally via llama.cpp, whose bundled jinja chat template defaults
`enable_thinking: true`) from a model that never emits thinking. The
tight non-reasoning budget was consumed by the thinking preamble before
the useful output could be emitted, so every affected call silently
failed with `stopReason: "length"`.
Drop the `model.reasoning` conditional across every affected online call
site and always reserve the reasoning-safe budget. `maxTokens` is a hard
cap, not a target — non-thinking completions still return in the tiny
happy-path budget.
Sites fixed:
- utils/title-generator.ts (30 -> 1024)
- utils/commit-message-generator (60 -> 1024)
- tts/speech-enhancer (512 -> 1536)
- auto-thinking/classifier online path (8 -> 1024); classifyLocal
keeps its separate LOCAL_ANSWER_MAX_TOKENS
- session/unexpected-stop-classifier online path (16 -> 1024);
classifyLocal keeps ANSWER_MAX_TOKENS
Fixes#4355
Plan-approval's 'Approve and compact context' used to pass the rendered
plan-mode-compact-instructions prompt as the first positional argument
to handleCompactCommand -> session.compact(), which landed on the
session_before_compact extension hook as customInstructions. Extensions
treating that field as user focus (e.g. to bias a query-focused summary)
would then see plan-mode boilerplate instead of operator intent and
produce query-biased compactions.
Add CompactOptions.internalGuidance: a private summarizer-only channel.
session.compact() reads it into the fallback-model summarizer while the
session_before_compact hook payload still only carries the public
customInstructions arg (undefined for the plan-compact path). The
snapcompact-disable predicate and the /compact rejectsFocus guard cover
both fields so a directed summary is never silently downgraded.
Extend the interactive-mode handleCompactCommand facade + command
controller with a fourth internalGuidance parameter, and switch the
plan-approval callsite in interactive-mode.ts to route the plan prompt
through it.
Fixes#4359
Selecting "Approve and compact context" while a user turn was typed during
compaction surfaced `Failed to finalize approved plan: Agent is already
processing` and silently discarded the operator's queued turn.
`flushCompactionQueue` fires the queued user turn (fire-and-forget) before
`handleCompactCommand` returns, so by the time `#approvePlan` resumed, the
session was streaming. The previous shape aborted the queued turn and still
raced into `AgentBusyError` when `session.prompt()` ran before abort settled.
The finalize path now queues the plan-approved directive as a synthetic
follow-up when the session is streaming, and catches a racing `AgentBusyError`
from `prompt()` with the same fallback. `AgentSession.followUp()` gained a
`{ synthetic, expandPromptTemplates, attribution }` option so the hidden
execution directive lands as an agent-attributed developer message on the
follow-up queue, without flipping advisor auto-resume the user-follow-up path
does.
Fixes#4358
Adds the rich TUI ask dialog, additive schema fields, ask.enabled tool gating, note/preview/header support, chat redirect, and timeout behavior that defers while nested prompts are active instead of discarding user input.
Op: extend
Idle recap crashed with `TypeError: undefined is not an object (evaluating
'H.content.filter')` when the reporter's session_stop block-decision extension
poisoned the transcript with eight persisted `session-stop-continuation`
custom entries. The primary block-reason continuation flow was intact — the
custom message correctly renders as a `role: "developer"` LLM message —
but the follow-on idle recap fired 4 minutes later, and the side-channel
provider stream handed back a `done` event whose `message.content` had been
dropped. `runEphemeralTurn`'s sanitize step at
`assistantMessage.content.filter(block => block.type !== "toolCall")` then
tripped the TypeError, propagated as "Idle recap turn failed" in the debug
log while silently muting the session.
- Normalized the provider "done" event's `message.content` to `[]` when
the shape is not an array, so a wrapper stream that drops content surfaces
as an empty recap reply instead of an unrecoverable side-channel crash.
- Guarded `#buildEphemeralSnapshot`'s in-flight-assistant preservation
branch with `Array.isArray(streaming.content)` for the same reason.
- Added a regression test that seeds the reporter's transcript shape (one
real turn, eight persisted `session-stop-continuation` customs carrying a
multi-line block reason with U+2717 glyphs) and drives a recap through a
side stream that returns `content: undefined` on `done`. The test
fails on the pre-fix tree with the exact reporter TypeError and passes
after the guard lands.
Fixes#4323
- Prevent premature failure during process startup by waiting for stderr to drain before throwing exit errors.
- Resolve race conditions between stdout closure, process exit, and readiness timeouts by using a local child process reference.
- Ensure proper cleanup of abandoned processes during startup failures to prevent leaks.
- Introduced a dedicated advisor rail symbol to differentiate note cards from thinking output.
- Applied bold custom header tags and severity-tinted rails to distinguish advisor notes from surrounding text.
- Shifted note body text to the default content color to prevent blending with dimmed thinking-output styles.
Four tightly-scoped hot-path fixes covering the highest-impact items in the
reporter's CPU profile (13.1 s profiled / 30 s window):
1. `event-controller.ts:handleEvent` no longer fires a blanket
`statusLine.invalidate() + ui.requestRender()` before every session event.
The pre-render was a leftover from #4145 when `updateEditorTopBorder()`
still eagerly rebuilt the border; the lazy provider added in #4145 made
it redundant. It fired on every `message_update`/`tool_execution_update`
during streaming — the pre-render's frame ran while the handler was
awaiting, then the handler's own `requestRender` scheduled a second
identical frame. Every handler that mutates visible state already calls
`requestRender()`.
2. `shimmer.ts:shimmerSegments` iterates the segment string in place instead
of building a code-point array with `Array.from(seg.text)` every animation
frame. Runs of same-tier chars are emitted via a single `slice` per run
rather than accumulating into `runBuf`. Surrogate pairs stay atomic — the
code-point index still advances by 1 per emoji. Microbench over 30k
frames: 45 ms → 18 ms (2.53x), allocation rate down from ~N-per-frame to
a handful per frame. New tests cover mixed BMP+surrogate and all-emoji
inputs. `Array.from` was the #1 self-time hotspot in the reporter's
profile at 10.2%.
3. `Markdown.setText` gains an equality guard mirroring `Text.setText`
(returns `false` when `text === #text`). Providers re-emit identical text
on ticks with no delta (throttled frames, reconciled tool-execution
updates); each of those now short-circuits instead of dropping
`#cachedLines` and forcing a full lex + wrap on the accumulated paragraph
(the reporter's #3 hotspot at 8.4%). New test asserts render-reference
stability + return-value semantics.
4. `SPINNER_RENDER_INTERVAL_MS` aligned with `SPINNER_GLYPH_ADVANCE_MS`
(both 80 ms). The previous 33 ms cadence emitted ~2.4 paints per glyph
step; the differential-output dedup only skips the write, not the
compose walk. Visually identical (glyph advance was already 12.5fps),
halves paints during tool execution.
Skipped (out of scope for a bug fix, deserve dedicated PRs):
- Freezing streaming prefix on single `\n` boundaries — correctness-bound
to `\n\n` block separators (CommonMark loose-list continuation).
- Compose-phase idle gate + adaptive-backpressure moving-average — need a
component-level dirty flag; the 200 ms cap in `#scheduleRender` was set
for a reason (#4145 tail-latency guard).
Tests updated: two IRC-expiry tests in event-controller-message-start.test.ts
that were asserting the pre-render's second `requestRender` call now expect
one.
Fixes#4353
roboomp