- Implemented `/queue` command and `->`/`=>` shorthands to support deferred, sequential message processing.
- Added a robust parsing utility to handle various list-based queue inputs and automate yield management.
- Integrated visual decorations and state tracking to provide real-time feedback on queueing status.
- Enabled non-cursor line text decoration in the TUI to support dynamic queue header rendering and list numbering.
- Enabled persistence of dangling tool calls during transcript rebuilds by adding `keepDanglingToolCalls` configuration.
- Integrated `seal()` logic for pending tool blocks to properly finalize history during idle session states.
- Enhanced UI helpers and session context to preserve assistant turns during streaming or mid-turn rebuilds.
- Added comprehensive unit and integration tests to verify correct tool call tracking and transcript integrity.
computeNonMessageTokens / computeNonMessageBreakdown re-tokenize the system
prompt and every tool's wire schema (per-tool JSON.stringify) on each call,
but the per-turn compaction and context-threshold paths call them several
times (getContextBreakdown twice, #estimateStoredContextTokens once) over
inputs that change at most once per turn. Memoize on the identity of
(systemPrompt, tools, skills) -- the same stable refs the StatusLineComponent
cache already trusts -- so the expensive parts run at most once per input
change instead of per call.
Stopped new-session and session-switch UI paths from detaching active loader/render components without running their disposal hooks.
Added container and loader coverage for disposing children before destructive transcript/status replacement.
Fixes#4686
Replace the visible-anchor suppression with a billed-usage predicate so live and resume paths agree on rendering the badge whenever the turn actually consumed tokens. Only genuinely free turns (no input, output, cache, or premium requests) drop the row, so hidden automated turns keep cost transparency.
Fixes#4532
Suppress token-usage rows for assistant turns that have no visible text, tool call, or terminal error anchor. Share the same decision across live rendering and transcript rebuilds so resume matches live output.
Fixes#4532
- Enforced strict history protection by gating ephemeral block removal on uncommitted state across controllers and UI components.
- Optimized settled-row calculations using explicit mermaid fence detection and improved scrollback integrity.
- Refactored transience management to target only actively streaming blocks, preventing redundant label rendering.
- Implemented persistent compaction for auto-retry errors and enabled consistent terminal title updates during session renaming.
- Refactored abort reason handling to rely on shouldRenderAbortReason instead of isSilentAbort.
- Updated documentation to clarify that both silent and user-interrupt aborts yield no label.
- Introduced an automated retry recovery system to track, manage, and persist recovered error states within agent sessions.
- Enabled compact transcript rendering for recovered auto-retry errors by removing heuristic commit machinery.
- Improved raw read tracking and provenance in the ReadTool to support refined file snapshot recording and hashline editing.
- Excluded recovered assistant messages from default model context and updated event controllers to handle retry recovery life cycles.
- Extracted decodeStreamedToolArgs into tool-args-reveal.ts and used it from both the live event path and transcript rebuilds, so mid-write theme/settings/focus replays no longer show stale streamed write/edit/eval content.
- Fixed the smoothing-off live path returning stale provider-parsed args.
- Documented the mandatory shared decode in the AGENTS.md streaming-preview hazard note; added changelog entries for this batch.
- Introduced `isProbablyBinary` utility to sniff file headers for NUL bytes or invalid UTF-8 sequences.
- Updated `ReadTool` to use the binary sniffer, preventing mojibake corruption in output when reading non-text files.
- Refined `file-mentions` auto-reads to skip binary files and mark them as `binary` in the message transcript.
- Added comprehensive unit tests for binary detection logic, covering NUL bytes, truncated multibyte characters, and path-based file sniffing.
- Migrated internal streaming state from string-based properties to symbol-keyed properties for improved data isolation and safety.
- Replaced the deprecated `stripVariant` utility with centralized `clearStreamingPartialJson` and symbol-specific helper methods across all provider implementations.
- Implemented `stripStreamingBlockSymbols` and updated deep equality checks to ensure metadata does not interfere with content comparisons.
- Standardized streaming metadata access through a new `block-symbols` utility module.
- Migrated 288 lines of scattered error classification logic from `utils/error-id.ts` into a cohesive `packages/ai/src/error/` module with 13 specialized submodules covering flags, classes, OAuth, providers, rate-limiting, and finalization.
- Replaced 100+ generic `Error` throws across 60+ provider and registry files with semantic `AIError.*` classes (e.g., `AIError.MissingApiKeyError`, `AIError.OAuthError`, `AIError.ProviderResponseError`), improving error diagnostics and retry logic.
- Consolidated error utility imports from `pi-utils` and scattered classification functions into a single `AIError` namespace, reducing coupling and simplifying error handling across all packages.
Mid-turn renderSessionContext (settings overlay close, focus attach during streaming) now hands the rebuilt todo snapshot back to the EventController via the new inheritDisplaceableTodo method instead of sealing it. Idle rebuilds keep the historic seal path.
Added a regression test that asserts the trailing todo snapshot is published to the controller and stays displaceable while session.isStreaming is true.
Fixes#3516
Dropped eager todo snapshot displacement from tool_execution_start, streaming message_update, and the rebuild assistant-iteration step. Displacement now runs only when the next todo's successful result lands, so a failed follow-up leaves the last-good todo panel on screen.
Added regression coverage for the failed follow-up case and updated the streamed-second-todo test to drive displacement from the success result.
Fixes#3516
Resolved any tracked todo snapshot before storing a fresh one in the rebuild paths so an assistant message replaying multiple todo tool calls collapses to the final snapshot.
Added a renderSessionContext regression test for two todo tool calls in one rebuilt assistant message.
Fixes#3516
Kept successful todo result blocks live until a later todo update replaces them or the turn ends.
Added regression coverage for same-turn todo snapshot replacement after intervening tool output.
Fixes#3516
Some providers (MiniMax, GLM, DeepSeek) return thinking blocks in
their responses even when reasoning is disabled — the model generates
thinking content regardless of the reasoning_effort parameter.
When the user sets thinking level to "off", they expect no thinking
content to be visible. Previously, thinking blocks would still appear
because the hideThinkingBlock setting was independent of the thinking
level and defaulted to false (show).
Fix: add effectiveHideThinkingBlock computed property that returns
true when hideThinkingBlock is true OR the session thinking level is
"off". All render paths (streaming, transcript rebuild, component
construction) now read the effective value instead of the raw setting.
The toggle (Ctrl+T) is guarded: when thinking is off, it shows a
status message ("Thinking is off — enable thinking to show blocks")
instead of silently no-op'ing or corrupting the persisted setting.
Fixes#626
- Transitioned the eval tool from batch multi-cell execution to a single-step input structure with flat parameters.
- Updated core agent logic, UI components, and documentation to support state persistence across incremental eval calls.
- Restricted bash tool capabilities by requiring explicit use of `read` or `find` instead of `ls` or `find`.
- Added support for Ruby and Julia language runtimes to the eval tool and associated web renderers.
Tail appended transcript JSONL instead of rebuilding rendered history on every poll, collapse compacted history for live chat rendering, and replace synchronous session rewrites so tailers detect historical changes.
Fixes#3258
- 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.
Typing #<number> (e.g. #3164) in the prompt now offers PR and Issue autocomplete candidates; accepting one rewrites the token to the pr:///issue:// internal URL (+ trailing space, matching the @/internal-url convention). The existing read tool -> InternalUrlRouter -> gh pipeline resolves it from the cwd's git remote, so no new resolution code is needed.
Bare # and #<text> keep the existing prompt-action menu (additive, no regression). #<number> requires a positive integer, so #0 / leading zeros do not offer candidates.
Closes#3218
- Added a `proseOnlyThinking` configuration setting to suppress raw code blocks in AI thinking traces.
- Implemented `formatThinkingForDisplay` utility to replace code blocks with ellipses in the UI.
- Integrated runtime toggling and live refreshing of message components via streaming reveal controllers.
- Added a live tokens-per-second indicator to the assistant thinking pulse.
- Verified logic with new unit and integration tests for thinking block presentation.
- Added tracking for expected cache invalidations during model changes, compactions, and plan-mode transitions.
- Included `cacheMissExplainedAt` metadata in session context to prevent displaying misleading cache miss warnings in the transcript.
- Updated controller logic to reset assistant usage markers when mode-switching or performing actions that invalidate the prompt cache.
- Added `display.cacheMissMarker` setting to enable visual indicators for prompt cache invalidation in assistant messages.
- Included updated theme symbols to represent cache misses across supported icon sets.
- Configured the selector controller to rebuild the chat display when the marker visibility setting is toggled.
- Implemented `detectCacheInvalidation` to identify when model requests lose their prompt cache.
- Added `CacheInvalidationMarkerComponent` to display a slim notice above affected assistant turns.
- Updated `ChatTranscriptBuilder` and `EventController` to track session usage and inject markers dynamically.
- Included comprehensive test coverage for invalidation detection logic and UI rendering.
- Refreshed all injected message frames with a consistent rounded-outline card design.
- Implemented icon-tagged headers for hooks, local skill invocations, and generic custom messages.
- Updated skill invocation cards with home-shortened paths, dynamic line count units, and compact invocation argument display.
- Unified branch summary styling with compaction banners to provide a consistent visual language for history collapse points.
- Removed leaked absolute home directory paths from skill metadata displays.
- Swapped legacy `zodToWireSchema` for `toolWireSchema` to normalize tool schemas.
- Updated `getSchemaPropertyKeys` in `tool-index.ts` to process schemas via `toolWireSchema`.
- Refactored tool token estimation in `context-usage.ts` to utilize the new schema helper.
- Fixed ArkType assertion checks in test helpers to correctly verify instances against `arkType.errors`.
- Aligned test suites and mock specifications with raw schema-based parameters instead of manually stringified JSON structures.
- Added context snapshot metadata to AssistantMessage for prompt and non-message token history.
- Anchored context usage calculations on assistant snapshots and computed percent numerically.
- Updated status-line, /context, selector, and interactive mode flows to share session usage totals.
- Extended status-line cache fingerprinting and invalidation for assistant usage and prompt/tool/skill changes.
- 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.
- Canonicalized assistant and thinking messages by trimming and collapsing dot text.
- Skipped rendering assistant and thinking blocks when canonicalized content was empty.
- Filtered ACP thinking notifications and session outputs to ignore placeholder content.
- Added canonicalizeMessage tests for undefined, blank, whitespace, and dot-only inputs.
- Removed the streaming guard that previously rejected /tan while the parent response was still generating.
- Passed "deliverAs: \"nextTurn\"" when sending the background dispatch breadcrumb and kept "triggerTurn: false" so an in-flight turn is not steered.
- Skipped rebuilding chat messages during streaming sessions and updated tests to cover the non-blocking dispatch path.
- Added a space-hold gesture state machine in CustomEditor, tracking repeated spaces, detecting holds beyond SPACE_HOLD_THRESHOLD, and firing start/end callbacks via a release timer.
- Hooked editor space-hold callbacks in InputController so STT toggles on hold start and again on release when STT is enabled.
- Added tests for space-hold start/stop behavior and updated keybinding docs to describe the hold-to-record STT workflow.
- Routed `customType: "handoff"` messages to the compact divider path in Agent Hub and UI helpers.
- Added handoff summary expansion that extracts context text and strips `<handoff-context>` wrappers.
- Refactored shared divider rendering into `SummaryDividerComponent` used by compaction and handoff messages.
can1357