The inline writethrough budget is 500ms (INLINE_DIAGNOSTICS_WAIT_TIMEOUT_MS);
the test published the deferred diagnostics at 900ms and asserted the inline
call returned in <800ms, leaving only ~300ms of headroom over the budget. CI
jitter pushed elapsed to 844ms (still correct deferral, just slow), failing the
over-tight bound. Publish at 2000ms and assert <1500ms so the deferral margin
is wide while still proving inline does not block on the slow publish.
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.
- 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.
- Added status.done and tool.* symbols to theme mappings and presets.
- Replaced generic success glyphs with contextual +/-, tool icons, and warnings.
- Mapped tool/task/job completions to status.done or status.enabled with icon overrides.
- Triggered runtime provider refresh after extension registration and warned on failure.
- Added tree-sitter `enclosing_block_boundaries` API with line range models.
- Added N-API `enclosingBlockBoundaries` bridge and exported JS declarations.
- Replaced matching-bracket context resolution with source-aware block context in read and diff flows.
- Passed source path through diff/read generators to surface native block boundary previews.
- Added matching-bracket utilities to locate partner lines for visible spans.
- Added read tool output to use displayContent text and startLine for bracket-aware previews.
- Added matching-bracket context rows to generateDiffString and generateUnifiedDiffString.
- Adjusted diff row insertion to deduplicate and keep contiguous changed groups together.
- Tracked in-flight browser helpers with names and durations for timeout reporting.
- Wrapped observe, screenshot, and extract in per-op deadlines capped at 20_000ms.
- Updated timeout cancellation errors to list stalled helper names and elapsed time.
- Removed the mid-skip placeholder line that was output when skipping lines in the middle of a diff, relying instead on the line number jump to convey the gap. Removed the corresponding placeholder-filtering logic from the hashline diff preview that was handling these placeholders.
- Renamed eval oneshot helper from llm() to completion() across JS/Python APIs.
- Remapped eval bridge internals to completion semantics (__completion__, runEvalCompletion, completion status op).
- Updated docs, prompts, and timeout guidance to describe completion() usage and behavior.
- Adjusted completion defaults for active-session model preference, fallback parsing, and slow-tier effort handling.
- Enabled clickable read-path output for result rows, summaries, and previews.
- Resolved read links from result paths, source metadata, internal URLs, and absolutes.
- Preserved selector suffixes while rendering line-anchor hyperlinks.
- Ignored aborted signals for plain-file and directory reads while keeping conflicts-cancel behavior.
- Added tests for non-abortable read behavior and link-label rendering regression coverage.
- Trimmed first-changed-line suffixes from edit path display and passed the line as a hyperlink target.
- Added middle-eliding path truncation for edit and rename file labels.
- Simplified diff-stat output to show only added/removed counts in a compact bracketed form.
- Added a new `edit-lsp-writethrough.bench.ts` benchmark to measure writethrough latency with and without deferred diagnostics.
- Added a slow-server case to `lsp-diagnostics-freshness.test.ts` that confirmed deferred diagnostics arrive after a prompt inline return.
- Updated `waitForDiagnostics` to accept exact document-version matches immediately and otherwise wait for a quiescence window before using the latest publish.
- Removed the old unversioned-acceptance option and applied the settle-based wait logic through inline and deferred diagnostics fetch paths.
- Added an LSP writethrough regression test ensuring stale unversioned diagnostics are ignored in favor of later fresh publishes.
- Adjusted `LspTool` to retry only zero/decl-only references with two 250ms waits for project-aware servers.
- Removed raw-mode GitHub repo README API fallback in `read`, so `:raw` now renders the page directly.
- Replaced regex heuristics in `isImagePlaceholderAnswer` with a fixed normalized placeholder set.
- Ensured eval LLM calls always include a non-empty system prompt to avoid 400s.
- Aligned eval tool docs with session spawn policy by omitting agent() when spawns are disallowed.
- Added regression coverage for default system prompts and spawn-aware agent() description behavior.
- Updated sendRequest timeout handling to use explicit timeoutMs, then AbortSignal deadlines, else 30s fallback.
- Normalized getServersForFile matching to accept both `.ts` and `ts` for extension routing.
- Expanded references retry logic to handle thin results with progressive backoff before giving up.
- Filtered rename_file fanout to servers matching source/destination extensions only.
- Updated status output to separate configured servers from started clients with readiness labels.
- Added regression tests for timeout ownership, extension filtering, and status readiness reporting.
- Added `:raw` repo-root resolution via GitHub API `/readme` for decoded markdown.
- Preserved fallback to default raw HTML rendering when the README payload was unusable.
- Added regression coverage for successful README decoding and fallback behavior.
- Set `FindTool` to disable recursive glob traversal so `dir/*` stays shallow.
- Added `parseSearchPathPreferringLiteral` to prefer literal paths like `apps/[id]/page.tsx` when they exist.
- Updated `resolveToolSearchScope` to reject external URLs with a clear `read` usage error.
- Expanded plan-mode sandbox checks to allow absolute paths inside the local artifact root.
- Propagated `schemaOverridden` from `YieldTool` into executor `YieldItem` metadata.
- Bypassed schema validation on override or schema-builder errors and kept payload output with success exit.
- Emitted `SUBAGENT_WARNING_SCHEMA_OVERRIDDEN` so accepted override results no longer surface as `schema_violation`.
- Expanded Codex placeholder detection to match common image-reference phrases and punctuation.
- Raised `codex` provider failure when final and streamed text are placeholders and no sources exist.
- Dropped placeholder prose from returned answers while preserving citation sources.
`finalizeSubprocessOutput` always spliced collected `report_finding`
entries onto a top-level `findings` array regardless of the active output
schema. A caller-supplied schema with `additionalProperties: false` and
no `findings` property would accept the raw payload in-tool (via the
`yield` validator, which only sees the pre-injection data) but then fail
post-mortem validation — emitting `schema_violation: findings: must not
be present` and propagating as a fatal `RuntimeError` through
`agent-bridge.ts` and the eval Python/JS preludes, collapsing the entire
workflow cell along with any prior successful subagent work.
`normalizeCompleteData` now takes the resolved validator and only
performs the injection when the augmented candidate validates. When the
schema rejects it, the raw payload is returned instead — which the in-
tool yield validator already accepted, so the lockstep guarantee
documented at the top of `output-schema-validator.ts` is honored.
Findings remain visible via the agent progress stream and JSONL
artifact, so no information is dropped when injection is suppressed.
Both finalize call paths (yield-success and no-yield fallback) now share
the single validator build instead of constructing it twice, and the
yield-path schema_violation branch is now reached only via the
explicit malformed-schema check, never via spurious findings rejection.
Fixes#2070
- Added a `showHeader` option to shell rendering and suppressed the bash frame title bar by default.
- Parsed trailing raw-output artifact notices and folded their IDs into status footer metadata instead of command output.
- Updated read-group rendering to use the enabled success mark and omitted duplicate success marks on child files in grouped reads.
- Adjusted find and search renderers to apply tool-title coloring, search icons, and padded layout via createCachedComponent.
- Added tests covering read-group success marking and padded find/search renderer output.
- Updated task call and result rendering to process shared context with the Markdown renderer, so context sections are now displayed with proper Markdown formatting.
- Stopped shimmer animation on pending bash/eval/task blocks once async state is `running`, preventing the committed frame from freezing a transient dark border segment.
- Adjusted rule path display to fall back to a root-relative path when cwd-relative resolution is unavailable.
- Marked Markdown cached lines as readonly snapshots and returned copied arrays from `render()`.
- Stored fresh snapshot arrays in both L1 and L2 caches so callers appending rows cannot mutate shared cached Markdown output.
- Added an AskTool test that renders calls and results twice to verify repeated renders remain stable and do not duplicate option labels.
- Replaced approved-plan renaming with `resolveApprovedPlan` resolution and state/slug lookup.
- Updated ACP and interactive apply flows to propagate canonical `planFilePath` instead of renamed paths.
- Added local plan fallback lookup by mtime for unresolved slugs after plan approval.
- Restricted plan-mode writes to `local://` plan artifacts and simplified path handling.
- Added a configurable `contentPaddingLeft` option to `renderOutputBlock` with normalized defaults.
- Updated edit renderer output blocks to disable inherited left padding and align inner-width wrapping.
- Added coverage for completed edit gutter rendering to confirm no leading space and correct frame width.
- Added archive format sniffing to identify ZIP, TAR, and TAR.GZ from file bytes.
- Added MIME/extension and header-based routing for notebook, sqlite, and archive payloads.
- Added archive entry rendering with slash-terminated dirs and size suffixes.
- Added tests for archive, sqlite, notebook, and fallback binary dispatch scenarios.
- Added `/tan` slash command registration and interactive handling.
- Added TanCommandController validation and async task scheduling for `/tan` dispatch.
- Added session cloning that suppresses breadcrumbs, copies artifacts, and handles abort cleanup.
- Added `promptCacheKey` support in Agent and inherited `providerPromptCacheKey` in session creation.
- Collapsed non-touched phases to one-line summaries in multi-phase todo renders while retaining full output for active, touched, or expanded views.
- Computed touched phases from in-progress tasks, completion transitions, and tool operations, with init operations now marking all phases.
- Added renderer tests covering collapsed rendering, argument-less fallback behavior, expanded mode, and separator-free phase output.
- Fixed edit/read/search/ast-edit/ast-grep outputs to resolve OSC8 links from session cwd.
- Fixed grouped-file output classification to honor headerBase and fileScope for parent path resolution.
- Fixed read and write renderers to use resolved source/resolved paths as hyperlink targets.
- Added `icon.search` to theme symbol maps and used it for Search, Find, AST Grep, and BM25 success headers.
- Reworked `searchToolBm25Renderer` results into framed bullet lists with expand-item hints.
- Updated renderer tests to match the new search-tool output contract.
- Added a read-link probe test that renders text and image paths with active hyperlinks.
- Updated ai auth retry tests for revised static-key validation and rotation behavior.
- Routed image-gen, inspect-image, and web search providers through `withAuth`.
- Used `reuseInitialApiKey`/`createAuthStorageResolver` for force-refresh and rotate retries.
- Attached HTTP status to thrown errors so the retry classifier detects retryable failures.
- Added ChatBlock and ChatBlockHost with mount, finish, and dispose lifecycle callbacks.
- Added InteractiveModeContext.present and resetTranscript APIs and used them to mount/repaint blocks.
- Reworked controller rendering paths to emit command, event, extension, and selector outputs via ctx.present.
- Implemented component and container dispose hooks in tui so loaders and child blocks cleanup timers/effects.
- Updated tool expand-hint rendering to use `expandKeyHint()`, which pulls the `app.tools.expand` binding and formats collapsed previews as `<key>: Expand`.
- Updated related tests in render utils and TUI regressions to assert the new hint string for default and remapped bindings.
- Added a resolve-tool regression test and changelog note covering `action: "discard"` with no pending action as a successful cancellation.
- Centralized transcript spacing by stripping blank edges and inserting separators.
- Removed per-component leading spacers and empty placeholders that added extra gaps.
- Introduced TranscriptBlock grouping so related outputs render as single transcript children.
- Updated transcript-related tests to validate one-row block separators and blank-line trimming.
- Replaced split-by-blank parsing in grouped renderers with classifyGroupedLines.
- Introduced path-tree grouping and folding to render multi-level directory headers.
- Normalized and deduplicated grouped paths, treating URL-like entries as root files.
- Adjusted file/url context mapping to keep line links stable across blank boundaries.
- Replaced `providers.parallelFetch` with a new `providers.fetch` enum in settings and added migration cleanup for the legacy key.
- Updated `renderHtmlToText` to follow configured reader preference with ordered fallback attempts and remote-reader timeout handling before local conversion.
- Updated YouTube and fetch tests to use `providers.fetch` and cover Jina-first stall fallback behavior.
- Shared immutable model registries and auth storage via beforeAll/afterAll.
- Swapped fixed-delay settle sleeps for predicate polling and signals.
- Stubbed network/timers to drop wall-clock waits in registry and history tests.
- Added resetDisplay invalidation tests and startup-timing breakdown lines.
- Parsed /actions/runs URLs into run and job render handlers.
- Rendered run metadata with per-job breakdown, showing steps for failed jobs.
- Fetched job logs via API token, stripping ISO timestamp prefixes.
The todo tool's renderCall ran args?.ops?.map(...) directly, which throws
TypeError on any non-array ops value. parseStreamingJson surfaces such
shapes mid-stream: a partial Anthropic input_json_delta buffer like
'{"ops":"[{' becomes { ops: '[{' }, and intermediate states can hand back
null entries before object fields arrive. Each crash spammed Tool
renderer failed warnings and starved the TUI render loop.
Guard against:
- ops being any non-array (string, object, primitive)
- entries being null / non-object
- entry.items being a non-array
The fix is in the TUI renderer only — schema validation in the agent
loop is unchanged, so any genuinely malformed model output still
surfaces an invalid-args tool error to the model.
Fixes#2005
can1357