Rephrased and condensed prompts for the browser, eval, irc, and read tools. The updates focus on clarity, conciseness, and improved parseability for agent consumption by:
- Consolidating instructions and helper descriptions.
- Removing redundant phrasing and examples.
- Eliminating extraneous sections that added cognitive load.
- Added usage snapshot persistence in sqlite with hour-bucket upsert behavior.
- Added listUsageHistory query support with optional provider and sinceMs filters.
- Added usage CLI history mode with `--history` and `--days` and trend rendering.
- Added changelog documentation for usage trend inspection and no-history exit behavior.
- Added scripts/tool-prompt-usage.ts as a Bun CLI to estimate rendered tool prompt sizes.
- Implemented path-based prompt collection and configurable --encoding/--json options.
- Computed per-prompt and aggregate token, character, and line totals from rendered prompts.
- Added an anchored Subagents HUD renderer that formats active subagent sessions as `Id: description` rows.
- Integrated a new interactive-mode container and observer-driven render path so the HUD updates with session events and clears when no subagents are active.
- Exported `formatTaskId` for shared HUD formatting and added tests covering active-only filtering, fallback task/progress text, and line truncation.
- Added a trailing-sentinel guard to identify newline-generated phantom lines and drop delete edits targeting them.
- Updated edit validation to allow those no-op deletes while preserving real line bounds checks.
- Adjusted format-v2 tests to expect no-op handling of sentinel deletes and clipping for ranges ending at the sentinel.
- Updated task call and result headers to use the dispatch glyph during running async calls instead of spinner-style states.
- Switched running and pending agent rows to a static done-dot marker and reused the dot with foreground color settling when rows complete.
- Updated task rendering tests to validate the new glyphs and ensure running/pending rows do not emit spinner or pending symbols.
- Replaced global search query mutation logic with a dedicated `Input` instance so typing now supports cursor movement, word deletion, and other editor hotkeys.
- Updated search banner rendering to display the embedded input line with live cursor while preserving match-count formatting and prompt width handling.
- Extended `Input` with a configurable prompt and end-of-value cursor placement, then updated memory-search tests for the new hotkey-driven editor behavior.
- Updated the snapcompact system prompt note to state that rasterized tool results are provided in PNG frames below.
- Instructed the model that image delivery is deliberate harness behavior and should not be treated as a tool malfunction.
- Recorded the updated behavior in the changelog fixed notes for this release.
- Added explicit request-debug path helpers in `packages/ai/src/utils/request-debug.ts` for one-shot dumps.
- Added `/debug dump-next-request`, `/debug dump-request`, and `/debug next-request` subcommands to arm next-request dumps.
- Changed `debug` handling in `packages/coding-agent/src/slash-commands/builtin-registry.ts` to execute args instead of always opening selector.
- Fixed explicit request-debug mode to resolve `~`/relative paths and create parent directories before logging.
- Fixed one-shot request-debug mode to consume its target after one call and overwrite existing response logs.
- Added fuzzy search preprocessing to normalize case, camelCase, and punctuation.
- Added token and phrase scoring for exact, prefix, substring, acronym, and compact hits.
- Added fuzzyRank to return {item, score}-ranked matches and delegated fuzzyFilter to it.
- Updated settings search tabs to sort by best score, keep original-order ties, and mute unmatched tabs.
- Stored the active kitty keyboard enable sequence in the terminal and re-applied it after entering the alternate screen, then emitted `\x1b[<u` before leaving the alternate screen.
- Updated StdinBuffer parsing so `\x1b\x1b` waits for CSI/SS3 followers, splits `\x1b\x1b[` SGR mouse reports into a standalone Esc plus report, and reduced `PARTIAL_HOLD_MAX_MS` to 150ms.
- Updated block resolution to detect structural-closing-line anchors and convert unresolvable `insert after block` edits into plain `insert after` inserts while emitting a dedicated warning.
- Propagated these resolver warnings through `PatchSection` and `Patcher` results so parse and application callers receive them.
- Added tests covering the closer-anchor fallback and confirming non-closer unresolved block anchors still throw.
- Detached async task progress rows stopped running a redraw driver and task progress rendering switched running/pending rows to static task-icon text.
- Background task snapshots were frozen once blocks left the transcript live region, preventing later partial snapshots from repainting commit-eligible rows.
- Updated task-progress and detached-background-task tests to validate static task rows and the new freeze behavior.
- Extracted `limitMatchesActiveAccount`/`reportMatchesActiveAccount` into `slash-commands/helpers/active-oauth-account.ts` as the single definition of the report-to-account matching rules, including projectId matching against `limit.scope.projectId`/metadata.
- Dropped the duplicated `ActiveAccountIdentity`/`OAuthAccessResolver` shims, `as unknown` session casts, the dead `getOAuthAccountId` fallback, and the email-vs-scope-accountId comparison from `command-controller.ts` and `usage-report.ts`.
- Replaced the async per-provider `resolveActiveAccountsForReports` map with one synchronous typed `authStorage.getOAuthAccountIdentity()` call per render, gated to the session's current provider.
- Re-exported `OAuthAccountIdentity` from `session/auth-storage.ts` and added `active-oauth-account.test.ts` covering the matching rules.
- Added the exported `OAuthAccountIdentity` interface (`accountId`/`email`/`projectId`) next to `OAuthAccess` in `auth-storage.ts`.
- Reworked `AuthStorage.getOAuthAccountIdentity()` to return that type and carry the credential's `projectId`, so Google-style providers that key usage on the GCP project can be matched.
- Added `auth-storage-account-identity.test.ts` covering no-OAuth, field carriage, empty-field dropping, session-sticky rotation, and config-override suppression.
- Recorded the new API under `## [Unreleased]` in the pi-ai changelog.
- Moved the /usage active-account entry from the released 15.9.4 section into `## [Unreleased]` under `### Changed`.
- Dropped the Ollama `ollama-chat` discovery entry that described code not present in this branch.
- Switched `core/shmr` to the configured embedding provider: `embed()`, the new `embedBatch()`, `clusterBySimilarity()`, `computeHarmonyScore()`, `harmonize()`, and `recallBeliefs()` are now async and batch-embed candidate texts in a single provider call.
- Reused precomputed vectors from `memory_embeddings` for episodic candidates in `harmonize()` instead of re-embedding them.
- Kept the SHA1 bag-of-words hash (`hashEmbedding`) as the deterministic all-or-nothing fallback when no provider is available or a batch fails, and derived centroid dimensions from actual vector lengths instead of the hard-coded 384.
- Rewrote `shmr.test.ts` for the async API: provider-vector clustering (single batch call), deterministic hash fallback, and `memory_embeddings` reuse.
Fixes#2324: Mnemopi: shmr.ts uses SHA1 bag-of-words hashing instead of real embeddings for consolidation clustering
- Replaced the bare `catch {}` blocks in `runEmbedding()` (`beam/helpers.ts`), `getLocalModel()`, and the local-model path of `embed()` (`embeddings.ts`) with structured `logger.debug` entries carrying the error plus per-site context (item count, model name); failure semantics stay best-effort.
- Threaded `MnemopiOptions.debug` through `resolveRuntimeOptions()` in `memory.ts` so `mnemopiDebugEnabled()` escalates these logs to `warn` when `mnemopi.debug` is set.
- Passed `mnemopi.debug` from coding-agent settings into provider options (`debug` added to the `MnemopiProviderOptions` pick in `src/mnemopi/config.ts`).
- Added `embedding-failure-logging.test.ts` asserting the logged context on a real local-model load failure and the debug→warn escalation; the changelog entry landed with the previous commit (same contiguous run).
Fixes#2322: Mnemopi: runEmbedding() and getLocalModel() silently swallow errors — mnemopi.debug produces no diagnostic output
- Added `mnemopi.polyphonicRecall` and `mnemopi.enhancedRecall` boolean settings (default off) to `settings-schema.ts` and `loadMnemopiConfig`, applied via the new `configureRecallFeatures()` in `createScopedResources`.
- Made `polyphonicRecallEnabled()`, `enhancedRecallEnabled()`, and `isEnhancedRecallEnabled()` fall back to the configured defaults while `MNEMOPI_POLYPHONIC_RECALL` / `MNEMOPI_ENHANCED_RECALL` env vars still win when set.
- Exported `configureRecallFeatures`/`RecallFeatureFlags` from the package root and `core` barrels; documented the settings in `docs/mnemosyne-memory-backend.md`.
- Added `recall-feature-flags.test.ts` covering defaults, config enablement, and env precedence; the mnemopi changelog hunk also carries the adjacent #2322 entry (same contiguous run).
Fixes#2323: Mnemopi: MNEMOPI_POLYPHONIC_RECALL and MNEMOPI_ENHANCED_RECALL not configurable via config.yml
- Running job labels now shimmer in the TUI to provide a dynamic visual indicator of activity.
- Adjusted cache key to account for shimmer animation, ensuring it updates at 30fps instead of the 12.5fps spinner cadence.
- Suppressed job ID display when the job label is identical to its ID, avoiding redundant information.
- Ensured flattened chain rows under a `└─` branch are anchored by a vertical line one level right of the suppressed gutter (below the branch head's content), never in the `└─` corner column itself, resolving visual issues #2298 and #2325.
Fixes#2325.
- Added `hasSteeringMessages` to `executeToolCalls` polling so queued steering is detected without dequeuing.
- Retained fallback to `getSteeringMessages` by consuming messages when no peek callback exists.
- Removed obsolete compaction-threading audit test coverage.
- Updated issue-825-repro and skill-queue tests for object-based queued message text entries.
- Expanded queued-message tests to verify image restoration via clearQueue paths.
- Stored queued steering/follow-up attachments in `QueuedDisplayEntry` so restore APIs retain image data.
- Changed `AgentSession.clearQueue` and `popLastQueuedMessage` to return `{ text, images }` payloads.
- Restored queued text and images into editor image buffers when steer submission fails or queue items are restored.
- Handled stale online catalog refreshes by falling back to curated models.
- Raised grok model maxTokens to 2,000,000/1,000,000/512,000 in models.json.
- Updated run-summary test mocks to track tool completion and only surface steering messages after the first task finishes.
- Reworked steering message retrieval from call counts to completion-and-drain state so pre-chat polls no longer block tool execution.
- Revised task prompt guidance to require batching multiple `tasks[]` in one call when subagents share context.
- Added optional `hasSteeringMessages` config hook and limited steering checks to boundaries.
- Fixed interrupted tool-batch steering by keeping queued messages until boundary handling.
- Added idle text and image submissions to steer queueing when no input waiter exists.
- Auto-continued resumable sessions after queued steering and preserved submit metadata.
- Fixed deep insert-after-block landing by retreating inward corrections across trailing closers.
- Added blockStart tracking and warning diagnostics for inward correction of block inserts.
- Clarified insert-after-block prompt and changelog guidance to require opener-based landing rules.
- Added regression tests for nested, empty, and conflicted inward landing scenarios.
- Added a `personality` enum to `settings-schema.ts` and new `Personality` type alias.
- Replaced inline reply guidelines with a templated `<personality>` block in `system-prompt.md`.
- Added markdown personality specs and wired them into `system-prompt.ts` rendering.
- Updated `sdk.ts` and `selector-controller.ts` to apply personality changes and refresh prompts.
- Set sub-agent sessions to use `personality: none` to suppress personality rendering.
- Added `partialHoldTimeout` to `StdinBufferOptions` to configure extra wait for dangling partial escapes.
- Reworked `StdinBuffer` flush scheduling to defer emits and avoid stale partials merging with new escapes.
- Held SGR mouse and kitty partial escapes until cap expiry to prevent tail bytes leaking as typed text.
- Added `SettingsList` section-focus state with `sectionFocused`, `hasSectionFocusTargets`, and `toggleSectionFocus()`.
- Implemented section-heading navigation with Tab/Shift+Tab, Up/Down focus jumps, and Enter/Escape exits.
- Updated `/settings` input hints and fallback routing to tab-bar keys when section focus is unavailable.
- Added tests for section-focus navigation, mouse parsing, and tab-bar behavior coverage.
- Added mouse hover, wheel, and click routing for `/settings` rows and tabs.
- Changed `/settings` to open as a fullscreen alternate-screen overlay.
- Added hover, hit-testing, and wheel APIs across TabBar, SelectList, and SettingsList.
- Added SGR mouse parsing plus `routeMouse` dispatch and exported it from the `tui` entrypoint.
- Renamed all functions, types, and constants in @oh-my-pi/snapcompact to namespace-relative names (`snapcompactCompact` → `compact`, `renderSnapcompactFrames` → `renderMany`, `snapcompactFrameCount` → `frames`, `SnapcompactShape` → `Shape`, `SNAPCOMPACT_SHAPES` → `SHAPES`, …).
- Converted every consumer to `import * as snapcompact` member access: `agent/compaction.ts`, `coding-agent` `agent-session.ts`/`session-manager.ts`/`snapcompact-inline.ts`, and all affected tests.
- Renamed internal `geometry` locals to `geo` in `snapcompact.ts` to avoid TDZ collisions with the new `geometry` export.
- Updated `docs/compaction.md` prose and added a Breaking Changes entry to the snapcompact changelog documenting the full rename map.
- Added `renderSnapcompactFrames()` and `snapcompactFrameCount()` to @oh-my-pi/snapcompact for paging arbitrary text into PNG image blocks without dim-marker bookkeeping.
- Widened the agent loop's `transformProviderContext` hook to `(context, model) => Context` so per-request transforms can gate on the dispatch model's capabilities.
- Added `SnapcompactInlineTransformer` rendering the system prompt and large historical tool results as snapcompact frames on vision models: vision gate, per-provider image budgets, 3k-token floor, savings-margin gate, skip-last rule, and hash-keyed render caches swept to live tool calls.
- Added default-off `snapcompact.systemPrompt` and `snapcompact.toolResults` settings under a new Context → Experimental group, composed after secret obfuscation in `sdk.ts` so frames are built per-request and never persisted to session.jsonl.
- Added prompt stubs (`snapcompact-system-stub.md`, `snapcompact-system-frames-note.md`, `snapcompact-toolresult-note.md`) and unit tests covering frame paging, no-mutate guarantees, budget caps, gates, and render caching.
can1357