`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
- Stopped expanded view from dumping every match when all hits share one file.
- Applied an `EXPANDED_LINES × 2` budget while keeping context rows.
- Appended a `… N more matches` summary when truncated.
- Updated edit result rendering to inline diff change statistics in the file header instead of using a separate metadata row.
- Removed the redundant standalone metadata line and removed the extra blank line before diff bodies for a tighter single-hunk display.
- Added a test asserting the header now contains +/-/hunk stats and that no extra stats row appears before the diff.
Passed options.expanded through the edit call preview renderer so approval previews can lift the streaming diff tail window and hide the preview label.
Added regression coverage for collapsed versus expanded edit preview rendering.
Fixes#1992
- Added `setPaddingY` to `Box` and used `setBoxPaddingForFramedBlock` when rendering framed outputs.
- Read tool results now skipped vertical padding in framed blocks, removing extra blank rows above and below the output.
- Added a regression test for `ToolExecutionComponent` that confirmed framed read content no longer renders extra blank lines.
- Adjusted renderCollapsedSearchGroups to compact each result group before truncation so first-section hits stay visible.
- Removed collapsed-body truncation notices and kept truncation status in the output header.
- Made PI_INTENT_TRACING, PI_AUTO_QA, PI_PY, and PI_JS take precedence when set.
- Fell back to config when the env flag is unset instead of ORing.
- Surfaced PI_PY=0/PI_JS=0 in the disabled-backend error messages.
- Replaced `¶path#hash` prefix with `[path#hash]` delimiters across parser, tokenizer, and grammar.
- Updated prompts, docs, and recovery paths to the new bracketed form.
Returned the current workspace folder list when a server queried workspace/workspaceFolders after initialization so advertising the capability no longer left late requests answered with -32601.
Ensured rust-analyzer textDocument/didOpen ran before workspace readiness polling so the server could discover the file's Cargo workspace, and skipped the readiness wait entirely for standalone .rs files outside any Cargo workspace ancestor.
Continued rust-analyzer workspace readiness polling across transient analyzerStatus request timeouts while preserving early exit for unsupported methods and server failures.
Advertised workspace folder support during LSP initialization and waited for rust-analyzer to finish loading Cargo workspaces before opening project-indexed files.
Fixes#1976
- Added image-reference rendering to make `[Image #N]` placeholders clickable in chat.
- Added MIME-aware image blob materialization with extensioned sidecar paths.
- Added clickable path, line, and URL hyperlinks for read, search, and fetch outputs.
- Hardened OSC8 hyperlink emission with URI validation and control-byte/idempotency checks.
The no-selector run_watch guard was using resolveDefaultRepoMemoized via tryResolveCurrentRepo, so a long-lived process could validate against a stale cwd-to-repo cache entry after the checkout or GitHub remote at that path changed. That allowed the guard to trust the current HEAD for an explicit repo based on the old cached repository.
Add a fresh best-effort cwd repo lookup for safety checks and use it before deriving branch/HEAD. Cached lookup remains for search default scoping where stale data only affects a convenience fallback. Added a regression test that populates the cache, changes the mocked repo at the same cwd, and asserts run_watch rejects before issuing API calls.
Refs #1949#1951
resolveGitHubRepo rejected calls that supplied both an explicit repo and a full Actions run URL when the two owner/repo slugs differed only by casing. GitHub repository paths are case-insensitive, so this was the same class of false mismatch as the cwd guard fixed earlier.
Compare repo slugs through a shared ASCII case-insensitive helper and use it for both the run-URL consistency check and the cwd guard. Added a regression test for repo=cagedbird043/cxf with a run URL under CagedBird043/CXF.
Refs #1949#1951
GitHub owner/repo slugs are case-insensitive; `gh repo view` returns
the canonical casing while callers may pass any casing. The new guard
used strict equality, so a caller in the correct repo who typed
`owner/repo` while the canonical form was `Owner/Repo` was forced to
pass a redundant `branch`/`run` selector. Normalize both sides via
toLowerCase() before deciding the cwd is a different repository.
Regression test covers the casing-only match.
Refs #1949#1951
executeRunWatch passed undefined for the explicit `repo` to
resolveGitHubRepo, so a call like
`{op: "run_watch", repo: "owner/cxf", branch: "main"}` from a nested
or umbrella workspace silently fell through to `gh repo view` in cwd
and streamed `watching <sha> on <cwd-repo>` against the wrong
repository.
Route params.repo through resolveGitHubRepo so the explicit owner/repo
wins over both cwd inference and run-URL inference. When no `branch`
or `run` selector is given, refuse to derive the watched commit from
`git HEAD` unless the cwd actually points at the resolved repo —
otherwise raise a ToolError telling the caller to pass `branch` or
`run` instead of silently rebinding to an unrelated commit.
Also deduped resolveSearchRepoScope's best-effort cwd resolution into a
shared tryResolveCurrentRepo helper used by the new guard.
Fixes#1949
- Added `getOAuthAccesses` to resolve each stored credential once.
- Sent one live request per account, reporting TTFT and TPS.
- Streamed per-account progress with interactive status lines.
When `async.enabled` is true but `AsyncJobManager.instance()` returns
`undefined` (orphaned-session state, host that never wired one up, etc.),
the `task` tool was returning a hard error and was unusable for the rest
of the session — even though the existing sync codepath (`#executeSync`,
which still parallelizes via `mapWithConcurrencyLimit`) was right there.
Fall back to `#executeSync` instead and emit a `logger.warn` so the
missing-manager state stays diagnosable. Background/job-poll semantics
are lost in this degraded mode, but the tool keeps working.
Fixes#1922
Can Bölük