- read now treats an xd://-mounted inspect_image as available (top-level
predicate OR mounted device gated by the effective mode), so default
xdev sessions with a text-only model keep metadata-guidance reads
instead of inlining images the provider boundary would scrub
- advisor tool session stops inheriting the primary's isToolActive and
xdevRegistry: advisors cannot execute xd:// devices, so their reads
inline images again
- setModelWithProviderSessionReset is now async and awaited at every
callsite, so retry-fallback model switches cannot race the
inspect_image tool-slate reconcile
- regression tests for both xd:// availability directions
- read now derives its image behavior from actual tool availability
(session.isToolActive) with the mode computation as fallback, so
restricted sessions whose explicit slate omits inspect_image (e.g.
subagents) never get metadata-only reads pointing at an absent tool
- reconcile passes the post-change availability into the read
description sync, keeping the advertised prompt correct across flips
in both directions and when tool construction fails
- flat quoted-dotted inspect_image.mode is normalized into the nested
target during migration instead of being silently dropped when a
legacy flat enabled key is present
- regression tests for all three: availability-driven read behavior,
flat+flat migration, description advertising
- Reconcile inspect_image centrally from setModelWithProviderSessionReset
so retry-fallback model changes (turn-recovery.ts) that bypass
syncAfterModelChange cannot leave a stale tool set
- Apply persisted inspect_image.mode changes immediately from the
settings selector via a new handleSettingChange branch
- Refresh the read tool's advertised description during reconciliation,
before applyActiveToolsByName rebuilds the prompt, instead of only
lazily on the next image read
- Fix the flat (quoted-dotted) enabled->mode migration to write the
nested target form the resolver actually reads
- Add committed regression tests: tri-state x capability matrix,
override precedence, and enabled->mode migration (nested, flat, and
explicit-mode-wins)
Replace the inspect_image.enabled boolean with inspect_image.mode
(auto|on|off, default auto). In auto the tool is registered only when
the active model lacks native image input, so vision-capable models
(e.g. kimi-code/k3) read images inline with their own capabilities
instead of delegating to a separate vision model. on/off force
registration regardless of model capability.
- New utils/inspect-image-mode.ts resolves the effective state from the
/vision session override, the persisted setting, and model capability
- read tool re-evaluates the effective state per image read and
re-renders its description, so it returns decoded image blocks again
whenever inspect_image is hidden
- /vision [on|off|auto|status] slash command (modeled on /computer)
overrides the mode for the current session only
- Tool set is reconciled on model switch with a status notice when
inspect_image appears/disappears
- Legacy inspect_image.enabled true/false migrates to mode on/off
- Render device doc parameter schemas as TypeScript types instead of raw JSON schema dumps.
- Optimize marked streaming block rules and add pre-gates to reduce CPU overhead.
- Increase the markdown render cache entry budget from 32 KiB to 256 KiB.
- Added V8 `.cpuprofile` parser and bottleneck summary generation utilities.
- Integrated profile summary rendering into the read tool execution.
- Refactored profile rendering machinery into shared tree utilities.
- Added comprehensive unit and integration tests for cpuprofile parsing and read tool dispatch.
- Added a new parser and bottleneck summary renderer for macOS `/usr/bin/sample` reports with symbol demangling.
- Integrated automated summary parsing for sample reports into the ReadTool.
- Updated model configurations and pricing parameters across multiple providers.
- Added comprehensive unit and integration tests for sample profile parsing and ReadTool integration.
- Added resolveWindowsShell to locate Git Bash, scoop installs, and path binaries with a fallback to cmd.exe.
- Updated bash-executor to prevent wrapping user commands in cmd.exe when using fallback shell paths.
- Updated installation script to report optional shell status rather than failing when bash is absent.
Two boundary defects on the mirrored-todo path.
1. The Agent error drain snapshotted #cursorToolResultBuffer without
awaiting entry.pending, unlike #emitCursorSplitAssistantMessage. An
async cursorOnToolResult still running when the provider errored
patched an entry the catch path had already detached, so the
pre-transform payload was persisted. A provider error is exactly when
a transform is most likely to be in flight.
2. The todo renderer interpolated mirrored provider text straight into
terminal output. A Cursor snapshot carries model-authored task
content, phase names and summary text verbatim, so a label holding
ANSI/C0 sequences rewrote the terminal on every render and replay.
sanitizeText alone is not enough - it preserves tabs, which punch
holes in bordered output - so every display path now funnels through
one forDisplay() helper: task labels, blocker notes, phase headers,
the zero-task fallback, and the streaming renderCall preview. Raw
values are untouched; content and phase name are the identity keys
the local list is looked up by and what gets persisted.
The regex splitter only recognized `&&`, `||`, `;`, `|` and newlines, so a
single `&` (background operator) — also a command terminator — slipped a
dangerous command past a deny rule (`sleep 1 & rm -rf /tmp/x`), which under
approvalMode: yolo executed with no prompt.
Extract the shell-aware tokenizer from gh-cache-invalidation into a shared
tools/shell-tokenize.ts and reuse it for deny/prompt segmentation. It honors
every command boundary (`&&`, `||`, `;`, `|`, single `&`, subshells,
newlines) plus quoting and escapes, so both callers share one implementation.
Fixes#6695
bashApprovalPatternToRegExp anchors globs with ^...$ against the whole
normalized command, so a bash.patterns deny rule only fired when the
dangerous command was first in the line. A compound command such as
`cd /tmp && rm -rf /tmp/x` bypassed the rule and, under approvalMode:
yolo, executed with no prompt -- deny is the guard that outranks yolo.
deny/prompt rules now match the whole command or any single segment
(split on &&, ||, ;, |, newlines). allow rules still require the entire
command to match and never apply to compound lines, so a narrow allow
cannot vouch for a smuggled unsafe segment.
Fixes#6695
Use the resolved supportsImageDetailOriginal capability to constrain native computer frames whenever a Responses transport clamps screenshot detail to auto. Preserve the established Claude-family fallback for transports that do not expose this capability.
Cover Copilot GPT-5 Responses through real catalog model resolution and the controller's observable capture options.
Passed session-scoped settings through Edit and Write generated-file checks and fell back to schema defaults when no global singleton exists.
Guarded inline image sizing against an uninitialized global settings proxy and added isolated-session regression coverage.
Fixes#6549
- Treated transient non-array retain items as absent during TUI streaming.
- Added regression coverage for malformed partial renderer arguments.
- Documented the fix in the coding-agent changelog.
Fixes#6528
- Added language-specific code formatters for JavaScript, Julia, Python, and Ruby to improve display rendering.
- Integrated display formatting into browser run and eval render tools while preserving verbatim execution.
- Added comprehensive test suites verifying formatting stability, lexical safety, and streaming behavior.
- Added available shell builtins list to the bash tool prompt template.
- Added helper to check if shell builtins are disabled via settings or environment.
- Prepended a model-visible PREVIEW_PENDING_NOTICE to ast_edit preview
results; the TUI-only proposed badge never reached the model, so
preview diffs read as already-applied edits.
- Rendered the resolve reminder with the source tool name via
Handlebars instead of a generic 'This is a preview'.
- Documented the xd://resolve / xd://reject two-phase flow in the
ast_edit tool prompt.
- Kept op required in the todo schema; lenientArgValidation now routes raw args to execute(), where resolveTodoParams re-validates and repairs an omitted op (list -> init, phase+items -> append, bare items on empty list -> init).
- Ambiguous op-less calls surface the schema error as a retryable tool error instead of a hard validation failure.
- Extracted #formatToolExecution into a standalone formatDefaultToolExecution module.
- Updated xdev renderXdevCall and renderXdevResult to use the default card when no mounted renderer exists.
- Added fallback rendering that shows tool label, args, and output with appropriate theming.
- Added integration test verifying generic card renders for mounted tools without bespoke renderers.
- Catch execution errors in XdevRegistry and render them using the mounted tool's error handling.
- Preserve xdev dispatch context when device execution fails.
OutputSink.dump() was the only path that closed the spill Bun.FileSink.
The bash and Python executors re-throw on failure and their finally
blocks never closed the sink, so any large-output command that errored
leaked the artifact descriptor until an unrelated read (e.g. a SKILL.md
load) hit EMFILE.
Added an idempotent OutputSink.dispose() that closes the sink exactly
once (awaiting any in-flight sink creation, guarding post-finalize
resurrection) and wired it into every executor's finally block.
Fixes#6463
can1357