handleServerRequest fell through to a JSON-RPC -32601 Method not found for several defined server -> client requests (window/showMessageRequest, window/showDocument, workspace/{semanticTokens,inlayHint,codeLens,codeAction,diagnostic}/refresh). Servers that block on a real reply -- the same failure class as the client/registerCapability hang fixed in #3029 -- could stall waiting for an acknowledgement that never came.
Reply with the spec no-op result instead: null for showMessageRequest / *Refresh, { success: false } for showDocument. Headless omp cannot honour the UI surface, but it still owes a defined response.
Fixes#3044
- Add a check requiring `cacheWrite > 0` to identify meaningful cache invalidation.
- Prevent false positives for providers with implicit caching that intermittently report zero reads without a fresh cache write.
- Add regression test case to verify implicit providers are not flagged as invalidations.
- Replaced four individual power boolean settings with a single `power.sleepPrevention` enum for improved configuration management.
- Implemented automatic migration logic in `Settings.init` to map legacy macOS power booleans to the new enum levels.
- Updated `AgentSession` to utilize the new `sleepPrevention` enum for macOS power assertion lifecycle management.
- Changed default value of `display.cacheMissMarker` to `false` to suppress cache-miss markers.
- Added comprehensive unit tests in `settings-manager.test.ts` to verify backward-compatible migration behavior.
- Accepted client/registerCapability and client/unregisterCapability server requests so Expert can continue startup before semantic requests.\n- Allowed JSON-RPC string ids on LSP request/response handling.\n- Added a regression test for dynamic registration gating hover.\n\nFixes #3029
Added an advisorEnabled visibility predicate and wired the advisor dependent settings through it so the Model Advisor sub-options hide unless Enable Advisor is active. Added regression coverage for the settings UI adapter.\n\nFixes #3027
- 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.
- Renamed `repeatToolDescriptions` to `inlineToolDescriptors` throughout configuration, SDK, and internal session management.
- Set the default value to `true` and updated descriptions to clarify the descriptor inlining behavior.
- Fixed the `/dump` command to prevent duplicate tool inventory output when inlining is enabled.
- Switch all UI components and tests from sharp box corners (`boxSharp`) to rounded ones (`boxRound`).
- Update `Theme` to re-export sharp junction symbols (tees and cross) under `boxRound` to ensure consistent divider rendering in rounded boxes.
- Remove outdated architectural notes regarding forced tool-choice queues in documentation.
- Introduced `SoftToolRequirement` to support non-invasive tool enforcement with lifecycle management and escalation.
- Added `ToolChoiceDirective` to coordinate hard and soft tool requirements within the agent loop.
- Optimized preview workflows in `coding-agent` by replacing forced tool choices with non-forcing pending invokers.
- Enhanced `CompactionSummaryMessage` to prioritize structured rendering for tool requirement reminders.
- 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.
- Added a test asserting `obfuscate` produces byte-identical output when re-run over the same content across turns, the invariant that keeps obfuscated history prompt-cache-stable.
- Added a test asserting earlier-message placeholders stay stable when a later message reveals a new regex-discovered secret.
- 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 all test temporary file handling to use the system temp directory (`os.tmpdir`) instead of creating artifacts inside the source tree.
- Added lifecycle management to `ttsr-cli.test.ts` to ensure temporary directories are created once per test run and cleaned up automatically.
- Updated file generation paths in CLI and reproduction tests to prevent local state pollution.
- Moved the `INTENT_FIELD` constant from `@oh-my-pi/pi-agent-core` to the specialized `@oh-my-pi/pi-wire` package to permit broader usage across the monorepo.
- Updated all references across `agent`, `ai`, `coding-agent`, `collab-web`, and `snapcompact` packages to import the constant from the new location.
- Added `@oh-my-pi/pi-wire` as a dependency to all affected packages.
- Removed configurable tab width support and the `display.tabWidth` setting across all packages.
- Deleted obsolete utility functions `getIndentation`, `getIndentationNoescape`, and `setDefaultTabWidth`.
- Standardized tab expansion logic to use a fixed `DEFAULT_TAB_WIDTH` globally.
- Cleaned up related configuration schemas, test suites, and internal API signatures to remove path-dependency.
- Updated log and error truncation messages to use a consistent `[...Nch elided...]` format.
- Standardized diagnostics and prompt text output to improve consistency in reporting truncated information.
- 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.
- Fixed an alignment issue where the transcript body was incorrectly offset by an extra gutter column relative to the "Agent Hub" title.
- Updated the transcript renderer to omit the redundant outer gutter and ensure file-mention rows include the standard 1-column left pad.
- Added regression tests to verify consistent gutter alignment and correct scroll behavior.
- Replaced inline chat view with a dedicated fullscreen `AgentTranscriptViewer` overlay.
- Introduced `ChatTranscriptBuilder` to enable non-incremental, full-history transcript rendering.
- Implemented robust state management for thinking blocks, message history, and transcript disposal.
- Added support for auto-reloading local session files and sync for remote transcript data.
- Replace individual component invalidation with a full display reset when toggling thinking block visibility.
- Ensure stale snapshots of thinking blocks in terminal scrollback are retired correctly.
- Implemented `AdvisorTranscriptRecorder` to persist advisor sessions to append-only `__advisor.jsonl` files.
- Integrated transcript recording into agent sessions with managed flushing, atomic file switching, and synthetic turn attribution.
- Restricted advisor-kind agents by excluding them from rosters, history protocols, messaging, and interactive agent commands.
- Reserved the `__advisor` filename stem across the output manager and task registry to prevent task ID collisions.
- Included advisor syncBacklog and immuneTurns in the default-resetting configuration for protocol hosts.
- Updated the lazy startup tests to verify that these settings are reset to defaults rather than inheriting user-defined values when a protocol host initiates.
Added the ACP mobile speech.models.list method so voice settings can fetch static local STT, TTS, and voice catalog options without invoking setup/download paths.
Fixes#3011
- Added a `mode` property to `CompactOptions` to allow fine-grained control over compaction strategies.
- Implemented `soft`, `remote`, and `snapcompact` submode overrides for the `/compact` command.
- Integrated `parseCompactArgs` to enable robust subcommand routing and validation, including focus instruction rejection for specific modes.
- Established a `CompactMode` registry to manage compaction strategies and verify remote availability.
- Removed qrcode and qrcode-view subcommands from the collab command.
- Updated showCollabLink to always trigger QR code display.
- Refactored internal verb logic to simplify session sharing flow.
Drop the runtime qrcode + @types/qrcode packages in favor of a zero-dependency
byte-mode QR encoder (versions 1-40, EC L/M/Q/H, auto version + mask selection)
with a half-block ANSI renderer. Cross-validated byte-for-byte against the qrcode
reference library and decoded end-to-end with jsQR. Adds encoder regression tests.
- Added collab.webUrl and rendered browser links as web UI wrappers whose fragments carry relay links.
- Added one-shot /collab qrcode and /collab qrcode-view commands with terminal QR rendering.
- Updated coding-agent and collab-web parsers to prefer parseable wrapper fragments while preserving legacy links.
- Added regression tests and changelog entries for split-host collab links and QR commands.
getOpenRouterRouteSuffix() used strict parseThinkingLevel(), which never
recognizes the max->xhigh alias, so openrouter/<id>:max was consumed as an
OpenRouter route suffix and cloned into a literal <id>:max model id with the
reasoning level dropped. This hit every exact-selector funnel
(parseModelPattern -> resolveCliModel/--model, resolveModelRoleValue/modelRoles
+ model picker, SDK default role) for the dominant aggregator provider.
Exclude max via parseThinkingSuffix(.., MAX_THINKING_SUFFIX_OPTIONS) so the
pattern falls through to the existing max-aware selector split. Literal :max
ids stay safe (none exist under openrouter; nanogpt literals win via exact
lookup before this path). Adds an openrouter/<id>:max regression test.
The dispose() disconnect added by this PR awaited mcpManager.disconnectAll()
unbounded. An owned manager holding an HTTP/SSE server whose session-
termination DELETE hangs would block dispose for the full MCP request timeout
(30s default, unbounded when OMP_MCP_TIMEOUT_MS=0), stalling /exit and
print-mode shutdown on a broken remote endpoint.
Wrap the disconnect in withTimeout(..., 3_000) — mirroring the bounded
async-job teardown two lines above and the startup bound from issue #2100.
stdio close (the subprocess reap this PR targets) completes well within the
bound; a slow transport close is left to finish detached.
Adds a regression test driving the real MCPManager.disconnectAll() with a
stalled transport close.
Resolved Amazon Bedrock application inference profile ARNs through the provider-specific model resolver and routed Bedrock requests to the ARN region.
Fixes#3004
roboomp