- Implemented persistent execution backends for Ruby and Julia using dedicated kernel processes and NDJSON-based IPC.
- Integrated language-specific prelude environments, runtime path resolution, and security-focused environment variable filtering.
- Exposed configuration options, tool schema updates, and lifecycle management for seamless agent interaction with both languages.
- Added comprehensive integration tests and updated prompt documentation to support the new evaluation capabilities.
- Centralized draft state and image management by migrating fields from context to the CustomEditor component.
- Standardized transcript row construction by introducing shared helpers for background jobs, IRC traffic, and file mentions.
- Refactored redundant UI logic and helper functions into reusable utility modules to streamline message submission and component rendering.
- Standardized event handler types by consolidating lifecycle definitions into a shared module while maintaining public API stability.
- Updated system and tool prompts to present dedicated tools as preferred defaults rather than absolute prohibitions.
- Relaxed the hard-forbidding of shell equivalents for file operations, searching, and editing.
- Retained guidance on prioritizing tools for their gitignore semantics, structure, and line-anchoring capabilities.
- Implemented `waitForSelector` and `waitForNavigation` methods in the browser tool API.
- Introduced per-operation fail-fast budget management with dynamic timeout clamping.
- Added validation for selector engines to reject unsupported Playwright-only platform features.
- Standardized error handling to provide descriptive, named timeouts for stalled browser operations.
- Inlined the temporary model status formatting logic directly into the controller.
- Removed the unused `formatTemporaryModelStatus` utility function and its associated test.
- Added `includeWorkspaceTree` configuration setting to optionally render the workspace directory tree.
- Configured the system prompt template and SDK to respect this toggle, allowing users to disable the tree to prevent prompt cache invalidation.
- Implemented `tab.ariaSnapshot()` to capture and represent page structures as ARIA-tree YAML.
- Introduced `tab.ref()` and ref-based selector parsing to enable precise element interaction via unique ARIA identifiers.
- Integrated automated script bundling for cross-environment evaluation of ARIA snapshot logic.
- Updated browser action methods to resolve and target elements using ARIA-ref handles.
- Added `buildSideRequestContext` to the `Agent` class to generate prompt-cache-friendly provider contexts.
- Updated ephemeral side-channel turns to forward the full tool catalog to maintain prompt cache hit rates.
- Injected a `developer` role reminder into ephemeral turns to instruct the model to suppress tool calls.
- Implemented automatic post-processing to strip any tool calls from ephemeral turn responses.
- Exported message and dialect helper functions in `agent-loop.ts` to support context construction.
- Add a dedicated `<parallel-reflex>` section to the system prompt to discourage serial work habits and enforce parallelization by default.
- Refine task-spawning guidance to emphasize intentional delegation, agent specialization, and clear assignment criteria.
- Update `task.md` parallelization heuristics and rule definitions to clarify when subagents should be deployed concurrently versus sequentially.
- Shortened language in `browser.md`, `eval.md`, and `prompt.md` to improve clarity and reduce token consumption.
- Refined instructional phrasing throughout the tool documentation for better readability.
- Simplified system and personality prompts for improved conciseness and clarity.
- Streamlined tool instruction sets and parameter descriptions across all agent modules.
- Refactored prompt documentation in `hashline` to clarify terminology and task-specific constraints.
- Updated tool metadata in TypeScript service definitions to align with reduced documentation verbosity.
- Removed the customizable `timeout` parameter from the tool schema and implementation.
- Fixed the timeout duration to 5 seconds to simplify tool usage.
- Updated documentation and error messages to advise narrowing search patterns instead of adjusting timeouts.
- Changed `wrapSteeringForModel` to wrap every `steering:true` user message regardless of position, so a steer's wire bytes stay identical once buried instead of reverting to raw and busting the prompt cache.
- Neutralized the present-tense framing in `user-interjection.md` so always-wrapping no longer leaves stale "current task" wording on buried interjections.
- Updated `session-messages.test.ts` to assert buried steering messages are wrapped too.
- Standardized elision markers across all tool outputs and filters to use cohesive `[...N [type] elided...]`, `[...Nln elided...]`, and `[...xB elided...]` syntax.
- Updated documentation, prompts, and test expectations to reflect the unified elision format.
- Improved transcript viewer robustness by preventing content aliasing through path-inclusive signature hashing.
- Added logic to clear stale transcript content when associated session files are deleted, accompanied by verifying test cases.
- Refined the advisor's scope to prioritize concrete technical risks and user advocacy while discouraging process-related critiques.
- Explicitly barred the advisor from intervening on user intent, process questions, or issues already handled by developer tooling.
- Updated `advise` tool documentation to clarify its purpose in preventing wasteful or incorrect work.
- Restrict the advisor from providing redundant insights, context, or second opinions.
- Prohibit restating information or problems already visible to the agent via its own tools.
- Prevent repetition of previously provided advice to minimize noise.
- Integrated comprehensive loop guard support for DeepSeek and assistant prose patterns, including configurable stream checks.
- Implemented Moonshot Flavored JSON Schema (MFJS) normalization for improved tool compatibility and enum type inference.
- Added support for Ollama reasoning effort backfilling and Grok-specific service tier cost tracking across providers.
- Expanded model catalog with new entries and unified compatibility logic for improved OpenRouter API integration.
- Added `images.describeForTextModels` configuration defaulting to true for text models.
- Added `describeAttachedImagesForTextModel` to persist images and generate local:// descriptions.
- Added image-description notices to session flow with hidden typing and pre-user insertion.
- Added fallback behavior that returns notes when vision is unavailable or output is empty.
- Added default system-prompt guidance to scan skill descriptions and read applicable skill:// content before work.
- Covered the rendered prompt contract with a frontend-design skill regression test.
Fixes#2829
- Added own-line display-math tokenizers for `$$...$$` and `\[...]` markdown blocks.
- Added delimiter-free `\begin...\end` math parsing in text conversion with multiline row preservation.
- Added ANSI rendering for `\textcolor`, `\color`, `\colorbox`, and `\fcolorbox` with scoped color resets.
- Added tests for LaTeX color and math parsing edge cases, including inline code and nested scopes.
- Added LaTeX math and Mermaid allowances in terminal and final-chat prompts.
- Added inline math tokenization in TUI for $, $$, \(\), and \[\].
- Added LaTeX-to-Unicode conversion helpers and exports for math rendering.
- Fixed inline math detection to skip escaped dollars and currency-like spans.
- Removed render_mermaid from tool discovery, task definitions, and registries.
- Removed renderMermaid setting and prompt/docs references tied to the deleted tool.
- Added maxWidth and theme color options to Mermaid ASCII resolution in markdown flow.
- Re-rendered Mermaid ASCII in both directions and clipped output to available width.
Resolved inspect_image attachment labels and attachment URIs against the latest chat image attachments before falling back to file-path loading. Added regression coverage for Image #N labels, bracketed image markers, attachment://N URIs, missing attachment diagnostics, and cwd-independent resolution.
Fixes#2787
- Passed USER_INTERRUPT_LABEL through abort paths in collab, ACP, RPC, runtime, and SDK flows.
- Added userInitiated to synthetic continue inputs and session prompt calls.
- Suppressed advisor auto-resume during user aborts and preserved queued concerns.
- Cleared suppression on user prompts and reclaimed parked advisor cards on abort settle.
- Added discovery of local, user, and ancestor `WATCHDOG.md` files via `discoverWatchdogFiles`.
- Appended discovered watchdog prompts to advisor system prompts during session setup.
- Added protocol startup defaults that force `advisor.enabled` and `advisor.subagents` false.
- Handled `maintainContext` failures and drained pending updates before token estimation.
- Added advisor context maintenance hook and token estimation before prompting for auto-upkeep.
- Added re-prime replay handling to reset advisor context and recover deferred prompts.
- Implemented session-level context compaction with model promotion and snapcompact-first fallback summarization.
- Surfaced advisor settings in the model tab and updated advisor system guidance text.
- Created AdvisorRuntime and AdviseTool to drive a read-only advisor agent that delivers severity-tagged advice (nit, concern, blocker) with interruption policy and transcript delta rendering.
- Added /advisor slash command with on/off/status/dump subcommands to control advisor lifecycle and inspect advisor metrics (model, messages, tokens, cost).
- Added advisor.enabled and advisor.subagents settings to enable passive advisor review on main agent and spawned task/eval subagents.
- Implemented advisor message rendering with severity-color badges (blocker=error, concern=warning, nit=muted) in chat log and status line indicator (++ badge).
- Extended yield-queue and session-history-format to support advisor batching and optional thinking block inclusion.
- Added a token-first four-phase design-system workflow (analyze, build-if-missing, compose-with-tokens, verify) to the designer agent so visual work references design tokens instead of hardcoded magic numbers.
- Added an evidence standard to the reviewer agent: a finding is not real until you can name the exact input that triggers it, and passing tests are not proof of correctness.
- Added an evidence-bound completion requirement to the task agent: name the exact check run and its observable result before returning.
- Added a return_handle (Python) / returnHandle (JS) option to the eval agent() helper that returns a DAG node dict { text, output, handle, id, agent } instead of bare text, where handle is the spawned agent's recoverable agent:// URI.
- Enabled downstream pipeline/parallel stages to reference a large transcript by handle/output instead of re-inlining it; the default path stays backward compatible (bare text, or the parsed object under schema).
- Documented return_handle and the acyclic DAG-wiring pattern in the eval tool description and added a VM-level prelude regression test for the node shape and the no-details fallback.
- Added `features.unexpectedStopDetection` and `unexpectedStopModel` settings for opt-in behavior.
- Added assistant-stop handling to classify stop reasons and resume generation with retry prompts.
- Added unexpected-stop classifier logic with candidate checks, model fallback, and YES/NO parsing.
- Added retry tracking that caps auto-continues at three attempts and logs a warning when exceeded.
- Updated `init` handling to build a single-phase list from `items` when `list` is absent, using `phase` if provided or defaulting to `Tasks`.
- Kept the existing init validation behavior by emitting `Missing list for init operation` only when neither `list` nor `items` was supplied.
- Added tests for flattened init forms, including implicit phase defaulting, explicit phase use, and the missing-input error case.
- Added `jsonSchemaToTypeScript` and `renderToolInventory` to generate tool blocks with TypeScript signatures.
- Added `examples` and `TSchema` fields to dump-tool metadata and passed them through prompt rendering.
- Changed Harmony invocation rendering to omit `<|constrain|>json` markers in tool call payloads.
- Added compact native tool list-mode inventory rendering with full `# Tool:` output elsewhere.
- Added model-to-syntax mapping in catalog with preferred tool-call syntax API.
- Added `ToolExample` typing and `ToolCallSyntax` exports across tool/grammar interfaces.
- Added syntax-aware tool example rendering through provider-specific grammar invocations.
- Added `exampleSyntax` context flow and example metadata so rendered prompts include examples.
- Updated the default `omp bench` prompt text to emphasize full-spectrum reasoning before answering.
- Required explicit enumeration of all four-table join orders with cost comparisons across nested-loop and hash joins plus index-scan versus full-scan tradeoffs.
- Expanded the changelog rationale to document sustained deliberation and exhaustive costing to avoid short-circuit benchmark responses.
- Updated the benchmark prompt to request a concrete, schema-driven query-optimization walkthrough with explicit selectivity, cardinality, join-order, and operator-cost calculations.
- Adjusted the output constraints to require plain-paragraph analysis output with no headings, lists, code fences, or tables.
- Documented the default benchmark prompt replacement in the package changelog under the Changed section.
- agent-loop: raise repetition-detection floor to 180 chars and clear thinking
replay anchors when collapsing a detected loop.
- providers/google: ignore empty text parts, retain terminal thoughtSignatures,
and stop function-call signatures clobbering the prior block.
- autolearn: capture goal-mode at the turn boundary; harden managed-skill writes
against hard-links/symlinks (O_NOFOLLOW + nlink); refuse minting managed skills
whose name an authored skill already claims.
- eager tasks: thread agentKind through the session so a custom top-level agentId
still gets always-mode delegation; split Eager Tasks prompt into hard vs soft.
- title-generator: race the online title model against a local tiny-model fallback.
- eager-todo: keep the soft reminder aligned with the todo init schema.
- mcp/stdio: keep close() detaching the read loop instead of awaiting it.
- stream loop: fix collapsing and tool-call thought-signature handling.
can1357