- Add `onFirstChatDispatch` hook to `CreateAgentSessionOptions` to track the boundary between session creation and the initial model request.
- Update `runSubprocess` and `TaskTool` to measure and log detailed latency metrics across the subagent lifecycle, including semaphore queue wait, setup time, and dispatch latency.
- Introduced a centralized `discoverAuthStorage` mechanism across packages to unify credential retrieval and configuration resolution.
- Added support for new Gemini and Moonshot model variants while updating context window and effort configuration for existing models.
- Resolved provider-specific 400 errors for OpenRouter and GLM models by refining reasoning effort mapping and retry logic.
- Standardized credential management in both the coding-agent and model catalog by migrating to the unified authentication broker.
- 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.
- 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.
- Added utility functions to strip descriptions from JSON schemas and tool definitions for optimized token output.
- Integrated `pruneToolDescriptions` configuration across agent loops and sessions to enable optional schema pruning.
- Updated agent context and snapshot logic to propagate pruning settings and maintain fingerprinting integrity.
- Verified schema structural integrity and removal of annotation descriptions through new unit tests.
Fix all Windows-specific test failures caused by path handling problems
and EBUSY errors from unclosed SQLite database handles.
Root causes fixed:
1. POSIX path assumptions: replaced hard-coded file:///tmp, /repo, etc.
with pathToFileURL/path.resolve/path.join computed expectations
2. shortenPath() now normalizes backslashes to forward slashes after ~
and respects home directory boundaries
3. HistoryStorage.resetInstance() leaked its Database — added #close()
that finalizes all prepared statements and closes the DB
4. AgentStorage gained the same resetInstance()/#close() pattern
5. SqliteAuthCredentialStore.close() leaked one-off prepared statements
from inline this.#db.prepare() calls — wrapped each in try/finally
6. model-cache.ts used a process-global DB even for custom dbPath —
now opens/closes per-call via withModelCacheDb
7. createAgentSession leaked AuthStorage on construction failure —
added ownsAuthStorage cleanup in catch block
8. MnemopiBackend.removeDbFiles() now truly best-effort (catches errors)
9. TempDir retry window expanded from 4x10ms to 40x25ms
10. TempDir prefix convention: non-@ prefixes created dirs relative to
cwd instead of os.tmpdir() — all test temp dirs now use @ prefix
11. Shell-escaped interpolated paths in bash tool tests
12. git core.autocrlf false in autoresearch test repo init
All 522 previously-failing Windows tests now pass.
- 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.
- Refactor deep imports by targeting specific sub-modules in `@oh-my-pi/pi-ai` to reduce barrel file overhead.
- Utilize jitless ArkType scopes in schema definitions to reduce startup JIT codegen costs by approximately 65%.
- Reorganize internal `auth-storage` exports to maintain clean boundaries between core and broker-specific functionality.
- 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.
Restored StringEnum's plain string enum wire schema and returned legacy coding tool placeholders that let createAgentSession keep the real built-in tools active.
Fixes#2858
Added compatibility exports for legacy plugin validation, including defineTool, StringEnum, TypeBox bare imports, frontmatter helpers, SettingsManager, and createCodingTools.
Updated SDK settingsManager alias handling and regression coverage for the affected shim surfaces.
Fixes#2858
- Kept `resolveDialect("auto")` on the legacy GLM fallback when a tool-less model has no catalog-recognized dialect.
- Added `sdk-dialect` coverage for unclassified tool-less models alongside MiniMax preferred dialect routing.
- Updated the coding-agent changelog entry to mention MiniMax auto-mode routing.
- Routed `resolveDialect("auto")` through `preferredDialect(model.id)` when a tool-less model exposes an id, preserving the legacy GLM fallback for id-less models.
- Added `sdk-dialect` coverage for MiniMax and Qwen auto owned dialect selection while keeping native and explicit dialect behavior unchanged.
- Updated getApiKey signatures to accept a Model and return ApiKey or ApiKeyResolver.
- Updated stream key handling to resolve credentials per model and use seedApiKeyResolver for retries.
- Added antigravityEndpointMode setting with auto/production/sandbox endpoint selection.
- Added 429/5xx endpoint failover for Gemini stream, usage, search, and image calls.
- Sanitized artifact filenames by normalizing tool names before composing spill paths.
- Applied `wrapToolWithMetaNotice` to custom tool adapters and RPC-host tools in agent-session setup.
- Wrapped SDK-registered extension/custom tools with the same meta-notice adapter during session creation.
Route stale OpenAI GPT default roles through canonical Codex selection when the catalog prefers the Codex OAuth transport, and rank shared provider defaults by canonical provider priority.\n\nFixes #2807
- Forwarded `parentAgentId` through task and eval launch paths when spawning subagents.
- Mapped `parentAgentId` to `parentId` in `createAgentSession`.
- Passed each caller's session `getAgentId` (or `MAIN_AGENT_ID`) as the parent for spawned agents.
Connected createAgentSession ToolSession instances to AgentSession.getImageAttachments so inspect_image can resolve Image #N and attachment://N in real sessions. Added coverage that the real inspect_image tool session sees live user attachments.
Recognized max in provider/model selector parsing where a concrete model lookup can preserve literal :max IDs before falling back to the xhigh alias.\n\nFixes #2727
- 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.
- 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.
- Suppressed MCP connecting and LSP startup event renders when startup.quiet is enabled.\n- Added regression coverage for quiet MCP and LSP startup event handling.\n\nFixes #2639
- Renamed ToolCallSyntax type to Dialect and Grammar interface to DialectDefinition across all packages.
- Moved grammar directory to dialect and updated all import paths in agent, ai, catalog, and coding-agent packages.
- Added renderTranscript and renderThinking methods to DialectDefinition, enabling native dialect-aware conversation serialization.
- Consolidated rendering utilities into new dialect/rendering.ts with shared helpers for ChatML, legacy text, and dialect-specific formatting.
- Updated conversation serialization in agent and coding-agent to use dialect.renderTranscript() for native turn envelope rendering.
- 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 an abortOnFabricatedToolResult option to Agent and AgentLoopConfig to choose whether in-band fabricated tool results are aborted or drained.
- Propagated the option through agent loop wiring into wrapInbandToolStream so fabrication is aborted only when enabled.
- Exposed the setting in coding-agent as tools.abortOnFabricatedResult and wired it through session creation with a true default.
- Added optional Agent and SDK tool-call syntax controls (`toolCallSyntax`, `PI_OWNED_TOOLS`) for owned calls.
- Added in-band grammar scanners and renderers for Anthropic, DeepSeek, GLM, Hermes, Kimi, PI, and Qwen3.
- Added supportsTools propagation and model schema updates to route unsupported models to fallback syntax.
- Replaced stream-markup parsing with syntax-specific in-band scanners and event conversion.
- Normalized agent `setSystemPrompt` to wrap string inputs into one-item arrays.
- Updated session creation to accept string `systemPrompt` values and normalize callback or direct results to string arrays.
- Adjusted extension result handling and test fixtures to accept string `systemPrompt` and missing `assistant_message` fields without crashing.
Deferred MCP discovery wrote 'Connecting to MCP servers: …' straight to process.stderr while the TUI owned the terminal, overdrawing the chat input box border. onMCPConnecting now emits McpConnectingEvent on the mcp:connecting channel; InteractiveMode subscribes and renders it via showStatus (status container), mirroring the LSP-startup pattern. New mcp/startup-events.ts holds the channel, type, and formatMCPConnectingMessage.
- 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