- Exported and applied wrapFetchForCch only for OAuth Anthropic web-search calls.
- Mapped model_context_window_exceeded to "length" and mapped unknown stop reasons to "stop".
- Adjusted header and param generation to preserve caller User-Agent and gate Claude Code betas.
- Updated stream and strict-tool retry handling to clear terminal errors and prevent regressions.
Stopped the tiny-title subprocess from inheriting stdout and stderr so native model runtime output cannot corrupt the interactive scrollback. Added a regression test for worker stdio configuration.\n\nFixes #2206
- Replaced canonical-row resolution with getCanonicalModelSelections in model lists and selector flow.
- Hydrated model selector state from registry on construction and kept cached selections during refresh.
- Preserved highlighted and cached model selection when offline refresh completed or reordered models.
- Added parity checks between getCanonicalModelSelections and resolveCanonicalModel via registry tests.
- Tracked cumulative plus/minus line changes to translate new-file context rows to old indices.
- Merged old and translated new block-boundary context rows in one pass to prevent duplicate/out-of-order rows.
- Removed terminal risk mode toggles from config, terminal state collection, and render controllers.
- Dropped snapshot freezing, thaw tracking, and finalized-block replay in transcript rendering.
- Removed clear-on-shrink settings and initialization hooks from selector and interactive mode flows.
- Simplified render scheduling by using requestRender() without mutation flags or stream checkpoints.
- Added a new `view` todo operation in the tool schema and dispatch path, returning the current list without mutating it.
- Implemented a read-only execution path in the todo tool so all-`view` calls skipped state updates, completion transitions, and normalization.
- Updated tool prompts to document `view` usage and clarified when bash commands are acceptable for fact-computing pipelines.
- Added Anthropic request-shaping coverage for adaptive and non-adaptive models in packages/ai/test.
- Removed obsolete scratch thinking test used for commit-boundary tracing in coding-agent.
- Added regressions for transcript append-only handling on wrapped styled rows and trailing-line shrink.
- Added streaming-thinking and spinner-style reproduction coverage for commit-safe boundaries.
- Changed transcript commit tracking from a volatile boolean to a cooldown counter that decays over clean frames.
- Normalized row equality checks to ignore ANSI and trailing-space noise so equivalent renders do not trigger rewrites.
- Removed the Bun test-runtime exception from Ghostty image paint deferral so normal delay logic always runs.
- Updated bracketed-image parsing to recognize multiple image paths in a single paste, including quoted values and shell-escaped spaces.
- Changed the editor image-path handler to process each matched path in order, awaiting async handlers.
- Added tests for multi-path routing/normalization and recorded the fix in the coding-agent changelog entry.
urlHyperlinkAlways now short-circuits to plain text when the user has explicitly opted out via tui.hyperlinks=off, while still bypassing capability auto-detection for auto mode.
MCP OAuth fallback prompts now emit an auth-safe terminal hyperlink even when auto-detection disables normal URL hyperlinks, matching the provider login behavior while preserving the raw copy URL.\n\nFixes #2196
Same shape of bug the reviewer flagged for custom tools: forwarding
`LoadExtensionsResult` from parent to subagent reused Extension instances
whose factories closed over the parent's `ExtensionAPI` — cwd, eventBus,
and runtime all pointed at the parent. Any tool/handler/command that
referenced `api.exec()`, `api.events`, or `api.runtime` still acted on the
parent session/worktree from inside an isolated subagent.
Forward only the path list; each session rebuilds extensions through
`loadExtensions` so factories see the right `ExtensionAPI`.
- `extensibility/extensions/loader.ts`: extract `discoverExtensionPaths`
(FS scan only) from `discoverAndLoadExtensions`. The combined helper now
composes the two. New export added to the package barrel.
- `sdk.ts`:
- Add `discoverSessionExtensionPaths()` (the `disableExtensionDiscovery`-aware
path-only counterpart of `loadSessionExtensions`).
- Add `preloadedExtensionPaths?: string[]` to `CreateAgentSessionOptions`.
Three loader branches: `preloadedExtensions` (CLI same-process reuse,
still shallow-cloned), `preloadedExtensionPaths` (subagent: skip scan,
reload locally), or full discovery.
- Document `preloadedExtensions` as same-process-only; subagent
forwarding MUST use `preloadedExtensionPaths`.
- `tools/index.ts`: `ToolSession.extensionsResult` → `extensionPaths:
string[]` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `extensionPaths`. Drop
the forward for the isolated `runSubprocess` branch — worktree cwd ≠
parent cwd, so the subagent re-discovers extensions against its own
tree.
- New `test/sdk-extensions-per-session-binding.test.ts` pins the contract:
two `loadExtensions` calls on the same path with different `cwd` and
different `EventBus` instances yield distinct Extension + runtime
objects whose factories close over the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and comment context.
Refs PR review on #2193
Reviewer flagged that forwarding `LoadedCustomTool[]` from a parent session
to a subagent reused tool instances whose factories had closed over the
parent's `CustomToolAPI` — `cwd`, `exec`, `pushPendingAction`, and `ui` all
pointed at the parent. In isolated tasks the tool would `exec` against the
parent worktree and queue pending actions on the parent session.
Forward only the path list; let each session rebuild tools through
`loadCustomTools` so factories see the right `CustomToolAPI`.
- `extensibility/custom-tools/loader.ts`: extract `discoverCustomToolPaths`
(FS scan only) from `discoverAndLoadCustomTools`; export
`ToolPathWithSource`. The combined helper is now `discoverCustomToolPaths`
+ `loadCustomTools`.
- `sdk.ts`: replace `preloadedCustomTools` (`LoadedCustomTool[]`) with
`preloadedCustomToolPaths` (`ToolPathWithSource[]`). The custom-tools
block runs `loadCustomTools` unconditionally; only the path scan is
skipped when the caller pre-discovered it.
- `tools/index.ts`: `ToolSession.loadedCustomTools` →
`ToolSession.customToolPaths` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `customToolPaths`.
Drop the forward for isolated subagents — the worktree shifts `cwd`, so
the subagent re-discovers tools against its own working tree.
- New `test/sdk-custom-tools-per-session-binding.test.ts` pins the contract:
two `loadCustomTools` calls on the same path with different `cwd` and
different `pushPendingAction` callbacks yield distinct tool instances
whose factories see the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and added a `ToolPathWithSource` fixture.
Refs PR review on #2193
Each `runSubprocess` call re-ran `loadCapability<Rule>()`,
`loadSessionExtensions()`, and `discoverAndLoadCustomTools()` because
`ExecutorOptions` and the `createAgentSession()` call inside the executor
omitted three pass-through fields the parent had already paid for. The
already-correct paths (skills, context files, workspace tree, MCP manager)
showed the intended pattern.
- Cache `rules`, `extensionsResult`, and `loadedCustomTools` on the
parent's `ToolSession`.
- Add `rules` / `preloadedExtensions` / `preloadedCustomTools` to
`ExecutorOptions`; forward them from both `runSubprocess` call sites
in `task/index.ts` and into the executor's `createAgentSession()`.
- Add `preloadedCustomTools` to `CreateAgentSessionOptions` and skip
`discoverAndLoadCustomTools()` when it is supplied.
- Shallow-clone `extensionsResult.extensions` when reusing
`preloadedExtensions`, so the per-session autoresearch + custom-tools
inline wrappers never leak back into the caller's array.
Fixes#2190
Escaped literal double quotes with cmd caret syntax before invoking Windows .cmd MCP shims so JSON args cannot break out of the quoted argument.
Refs #2174
Escaped literal percent signs before joining Windows cmd.exe shim command strings so MCP server args are not consumed by cmd environment expansion.
Refs #2174
The package-root override branch of `resolveCanonicalPiSpecifier` returned
the bunfs override path without checking the target was actually present,
so when `bun --compile` quietly dropped one of the extra entrypoints
(observed on macOS arm64 release binaries), the static rewrite emitted a
`file://` URL to a missing module. The #1216 fallback only fired on the
throwing `getResolvedSpecifier` path, so the override never threw and the
rewrite committed the bad URL — extensions silently failed to load.
Each override target is now checked with `fs.existsSync` at module init.
Missing entries are dropped from `LEGACY_PI_PACKAGE_ROOT_OVERRIDES` so
`resolveCanonicalPiSpecifier` falls through to `getResolvedSpecifier`,
which throws under bunfs and triggers the existing rewrite catch — Bun
then resolves the canonical `@oh-my-pi/pi-*` specifier from the
extension's own `node_modules`.
Fixes#2168
Completes the injectable-fetch transport wiring (15.10.8) that the feature
left half-done, fixing the deterministic CI test failures:
- compaction.compact() rebuilt summaryOptions field-by-field but dropped
`fetch`, so the injected transport never reached
requestOpenAiRemoteCompaction / generateSummary's remote path. Thread it.
- Read-tool URL pipeline had no fetch seam: renderHtmlToText gained a
fetchOverride param but renderUrl/ToolSession never carried one, so the
jina/parallel reader backends always used global fetch. Add
ToolSession.fetch -> renderUrl -> renderHtmlToText (defaults to global).
- searchWithParallel mirrored extractWithParallel but missed the fetch
option; add it.
- Repair tests whose deleted hookFetch interceptors were never replaced
with a FetchImpl seam (fetch-kagi-toggle, web-search-parallel,
issue-970 discovery).
- Update issue-1746 POSIX case to the #2154 preserved-scrollback contract:
unknown-viewport streaming deferral is now platform-independent.
- Added optional FetchImpl fields to compaction, proxy, AI, coding-agent, and mnemopi options.
- Threaded injected fetch implementations through OAuth, discovery, and search/LLM request flows.
- Removed exported hookFetch utility and its package entrypoint from utils.
- Replaced global-fetch test monkeypatching with per-test FetchImpl mocks across test suites.
- Parsed a trailing `@slug` to set OpenRouter `provider.only` or Vercel Gateway routing per invocation.
- Resolved via `parseModelPattern`, composing with thinking levels and round-tripping through selectors.
- Split only when the base resolves to an aggregator, so ids containing `@` stay intact.
- Dropped blank lines, capped at 8 lines, and width-truncated each line so a proxy 502's HTML body can't flood the transcript.
- Mirrored the pinned error banner's preview behavior; full text still kept in the persisted session.
- Added a `bash.enabled` boolean setting with a default of `true` in the settings schema.
- Updated tool generation to include the `bash` model tool only when `bash.enabled` is enabled.
- Extended createTools tests to assert `bash` is omitted when disabled and omitted from requested disabled tool lists.
MCPManager.connectServers used to fall through to an unbounded
Promise.allSettled over every still-pending server without cached tools,
so a single MCP server stuck waiting on the per-request MCP timeout
(OMP_MCP_TIMEOUT_MS, default 30 000 ms) gated the entire UI ready
signal — exactly the 30.282 s stall the reporter observed against
sbox-superdocs in #2100.
Drop the fallback wait. Pending-without-cache servers are left in flight
and their tools surface via the existing background #onToolsChanged ->
refreshMCPTools path the moment the connect completes; failures continue
to log through the background catch handler (gated on
allowBackgroundLogging) so users still see which server failed.
Adds a regression test that spawns an unresponsive stdio MCP fixture
and asserts connectServers returns inside the 250 ms STARTUP_TIMEOUT_MS
window (padded for CI jitter). The same test times out at 15 s without
the patch.
Fixes#2100
On kitty (Linux/Wayland) and any terminal supporting OSC 5522 enhanced
paste, the /login API-key prompt for OpenCode Zen — and any other modal
Input prompt (Perplexity OTP, GitHub Enterprise URL, manual OAuth
redirect URL, …) — silently dropped pasted content. The user could not
paste their API key; on Enter or Esc the key surfaced in the main
prompt.
Cause: InputController.#setupEnhancedPaste enables kitty's enhanced
clipboard protocol on TUI start and consumes the resulting OSC 5522
packets in an addInputListener that runs *before* focus dispatch in
tui.#handleInput. The controller's pasteText callback then routed
unconditionally to this.ctx.editor.pasteText(text) — the main
CustomEditor — even when selector-controller had cleared editorContainer
and focused a temporary Input. The text accumulated in the detached
editor and only resurfaced when the modal was dismissed.
Fix:
- TUI.getFocused() exposes the currently focused component.
- Input.pasteText(text) mirrors Editor.pasteText so any Input can absorb
a payload from a non-bracketed transport.
- InputController's enhanced-paste callback consults getFocused() and
routes text to the focused component when it exposes pasteText,
falling back to the editor only when no modal target is in focus.
- Image pastes refuse with a status message when a modal Input is
focused, instead of stuffing a binary blob into the hidden editor.
Regression tests in packages/tui/test/input.test.ts and
packages/coding-agent/test/issue-2127-repro.test.ts pin both the new
TUI/Input contract and the InputController routing source.
Fixes#2127
Threshold-driven auto-compaction with strategy=shake auto-continued even when
the shake reclaimed nothing material, and the next agent turn re-triggered the
same shake (which had nothing new to drop on a second pass), spinning forever.
After shake completes, recompute the post-shake context estimate; when it
still exceeds the auto-compact threshold (or shake reclaimed nothing on overflow
recovery), emit a one-shot fallback warning and hand off to the summarization
driven context-full path so progress actually resumes. Idle is exempt — its
60s+ timer self-throttles and cannot dead-loop on its own.
Fixes#2119
Rendered the MCP OAuth fallback as a short terminal hyperlink plus a single unwrapped copy URL line so terminals do not receive hard-broken authorization URLs.\n\nFixes #2121
Skill prompt custom messages now scan user-authored skill args for magic keywords and turn budgets, matching normal prompt steering behavior without scanning skill body text.
Added a regression test for workflowz and hard turn-budget args on skill prompts.
Fixes#2128
- Updated PI native streaming requests to send model identifiers as provider-qualified keys.
- Updated the auth-gateway model registry to store `${provider}/${id}` first and retain legacy bare IDs as fallback keys.
- Added an `openPlanReview` flow that selected the newest `local://<slug>-plan.md`, resolved its title, and reopened approval.
- Registered a new `/plan-review` builtin slash command that invokes that flow and clears the editor text.
- Added tests covering latest-plan selection plus warnings when plan mode is inactive or when no local plan file exists.
- Updated `renderResult` to inspect `isError` on detail-less task results and render an error state with the error glyph.
- Replaced success/completed status symbols in agent, review, and result outputs with the shared `status.done` symbol.
- Added tests for detail-less task rendering to verify failed results show error and successful results show the done glyph.
can1357