- Added `isGrok46ModelId` boundary-aware model predicate to the catalog package.
- Included Grok 4.6 models in the thinking-loop guard to prevent runaway reasoning streams.
- Added alsa-lib and libpulseaudio dependencies to the package derivation.
- Configured patchelf to append client libraries to the native addon RUNPATH for dynamic loading.
- Replace the obsolete agent dashboard control center with a new fullscreen agents hub component.
- Integrate AI-assisted agent creation architect flow using model sessions.
- Provide interactive property strips and model browser integration for agent configuration.
- Update tests and documentation to support the redesigned agents hub.
Reject snippet-formatted or overlapping rename edits across all accepted URIs before applying any, so a later snippet edit cannot leave earlier files half-applied.
Fixes#8376
The direct diagnostics loop caught non-abort server errors without recording them, so a file whose every applicable server failed produced an empty aggregate rendered as OK with success: true — a false-negative hiding a total diagnostics failure.
Track per-file and global success/failure counts: zero successful server responses now yields success: false with an explicit failure line, while partial success still surfaces diagnostics and names the servers that failed.
Fixes#8377
Advertised abort semantics because multi-file text edits are applied sequentially and cannot satisfy textOnlyTransactional.
Added initialization capability coverage and documented the fix.
Fixes#8375
- Replaced blanket subagent advisor global settings with fine-grained per-agent configuration and frontmatter support.
- Added dashboard keybindings and inline override editors for managing agent advisor patterns.
- Implemented settings migration logic to convert legacy global options into per-agent settings.
- Updated session persistence and execution layers to restore and enforce per-agent advisor behaviors.
- Added Anthropic prompt-cache refresh scheduling and state management to keep prompts warm across idle sessions.
- Updated pricing models and database stats tracking to calculate and store cost-weighted cache savings.
- Integrated cache savings metrics and efficiency displays into the stats CLI, dashboard routes, and UI components.
- Added support for package renaming, manifest pointer tracking, and installation migration during CLI updates.
- Add comprehensive Nix flake definitions, derivations, modules, and CI workflows.
- Update tests and executables to resolve binaries from PATH rather than absolute paths.
- Ensure byte reproducibility and zeroed timestamps in embedded dashboard archives.
- Add handling for Nix-managed installations in CLI update checks.
- The mux pane-growth oracle treated every physical scroll as a logical append, but immutable-history recovery can recommit a corrected suffix after an off-screen mutation without advancing the shadow tape; exempt only changed shared history prefixes.
- The frame-neutral oracle compared prepared rows only; at narrow widths distinct raw rows prepare identically, so the renderer's raw-prefix divergence recovery recommits legitimately. Snapshot raw frames and allow declared transient growth.
- OSC66 spacer preservation intentionally composes six bounded context rows above the resize viewport; assert that exact bound instead of zero above-fold rendering.
Both oracle false positives reproduce identically at the PR head that introduced the harness (4cc9725037); three full randomized stress passes green after the fix.
- Added a 60-character minimum length threshold for demoting interrupted thinking into hidden continuity context in agent-session.ts.
- Updated LLM message conversion in messages.ts to strip incomplete thinking from user-interrupted assistant turns regardless of continuity note presence.
- Added test coverage in agent-session-interrupted-thinking.test.ts verifying behavior for reasoning lengths below and at the threshold.
- Raw chunked-TCP write/end race made the failure mode load-dependent (pre-existing since before the sweep; transport source unchanged). Owner approved removal; GET-listener and 401-resume coverage keeps Last-Event-ID resumption defended.
- Reframe interrupted-thinking prompt template to present preserved text as a natural user interruption.
- Update interrupted thinking session tests to match the new prompt format.
- Set generation temperature to zero for online title generation to prevent garbled names.
- Update system prompt to instruct exact copying of technical terms and names.
- Reject generated titles containing no word characters to prevent punctuation-only sessions.
- Pass draft images into inline /plan and /vibe skill invocations so attachments reach the skill message.
- Propagate dispatch errors so runWithDetachedModeDraft restores the detached command draft.
- Cover image delivery and rejected dispatch in the issue-8137 regression file.
can1357