- Transitioned vibe tools to an ephemeral registration model where they are installed only when entering `/vibe` mode and removed upon exit.
- Added `activateVibeTools` and `deactivateVibeTools` methods to `AgentSession` to manage these transient tool registrations.
- Removed vibe tools from the default global tool registry, preventing unnecessary background exposure.
- Implemented Vibe mode to enable worker session management and director-role context injection.
- Added a `/vibe` slash command and integrated status line UI to display mode activity.
- Configured restricted toolsets and guards to prevent concurrent conflicts with existing Goal or Plan modes.
- Provided system prompts and tool templates to support specialized agent communication and task orchestration.
- Centralized task concurrency and delegation logic by moving instructions from individual tool descriptions to the system prompt.
- Introduced conditional system prompt logic to handle model-specific task policies, including support for GPT-5.6.
- Added infrastructure for task concurrency normalization and IRC steering state within the system prompt configuration.
- Refactored prompt inputs and session logic to enable dynamic system prompt updates based on model-specific policy cohorts.
- Introduced `Max` as a first-class reasoning effort tier across all packages, including AI providers, coding agent configurations, and RPC protocols.
- Refactored model effort ladders to use wire-exact mappings and removed legacy effort aliasing (e.g., `max-to-xhigh` mapping).
- Updated model registry and provider configurations to support `Max` tier routing, color themes, and UI icon associations.
- Expanded test suites to provide end-to-end coverage for the new reasoning tier, including updated compatibility and fallback scenarios.
- Persisted an inherited provider prompt-cache key on full session forks while keeping the child OMP session id independent.
- Added --prompt-cache-key and SDK startup inheritance so explicit cache affinity is separate from provider session routing.
- Cleared automatic inherited keys when model, thinking, system prompt, or tool schema inputs change.
Fixes#5035
Interactive sessions defer MCP discovery, so CLI --tools produced an initial built-in-only active set and later MCP refreshes respected that filtered set.
Force-activate deferred MCP tools when MCP discovery mode is disabled, matching the blocking startup path while leaving discovery-mode selection intact.
Fixes#5013
- Enabled comma-separated string splitting within array-based model patterns.
- Expanded deferred model patterns before registration to align with immediate resolution behavior.
- Unified resolution logic to ensure deferred patterns support the same role aliases and chaining as the standard path.
- 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.
Forward unresolved explicit subagent model selectors into child session startup so modelRoles.task cannot disappear during executor preflight and fall through to an unrelated provider default.\n\nFixes #4421
Loaded cached runtime extension provider catalogs before deferred model resolution so dynamic-only providers can satisfy cold-start --model and session resume selection from models.db.\n\nFixes #4216
Wrapped retained rewind reports with completion guidance so the post-rewind turn knows the checkpoint is closed.
Added repeat-rewind recovery errors and regression coverage for both the retained context and no-active-checkpoint path.
Fixes#4187
- Consolidated duplicated inline thinking level comparisons into a unified `concreteThinkingLevel` helper.
- Enhanced legacy tool shims to respect isolated session settings and support legacy options.
- Cleaned up redundant UI render requests and extra status-line updates.
- Refactored `grep` tool shim to configure context dynamically via isolated settings.
- Disabled platform-incompatible shell shim tests on Windows environments.
Follow-up on the review: the widened parseThinkingSuffix recognized :auto unconditionally, so parseModelString and extractExplicitThinkingSelector would silently strip a literal provider/model:auto id before the isLiteralModelId guard the :max path already uses.
- Add allowAutoAlias option and require callers to opt in, mirroring allowMaxAlias.
- MAX_THINKING_SUFFIX_OPTIONS enables both aliases; parseModelPatternWithContext still tries exact match first, so a real :auto id wins there too.
- sdk.ts (session restore x2), agent-session.ts (retry fallback selector, context-promotion/compaction targets), and model-registry.ts (normalizeSuppressedSelector) now pass allowAutoAlias: true alongside allowMaxAlias.
- Regressions: literal example/runtime:auto wins over the sentinel in parseModelPattern, parseModelString (with and without isLiteralModelId), resolveModelFromString, and extractExplicitThinkingSelector; auto is still extracted when the id isn't literal.
The model selector's persistence path dropped the `:auto` selector when parsing role values, producing a warning ('Invalid thinking level "auto"') and rendering the badge as `inherit` instead of `auto`. Reload of the default role also lost the auto state whenever the role value carried an explicit `:auto` suffix instead of relying on `defaultThinkingLevel`.
Widen the resolver chain (`parseThinkingSuffix`, `splitThinkingSuffix`, `parseModelString`, `parseModelPattern*`, `ResolvedModelRoleValue`, `ResolvedRoleModel`, `ResolveCliModelResult`) to carry the `AUTO_THINKING` sentinel end to end, and coerce it back to `undefined` at concrete-only boundaries (glob scope patterns, retry fallback, advisor, commit pipeline, guided-goal, bench).
Regression tests cover:
- `resolveModelRoleValue("provider/model:auto")` returns explicit auto without a warning.
- `ModelSelector` renders `DEFAULT (auto)` and `SMOL (auto)` when the role value has `:auto`.
- `cycleRoleModels` activates auto thinking on entering a `:auto` role.
- Startup resume activates auto thinking when `modelRoles.default` carries `:auto`.
Fixes#4128
- Removed the canonical model variant indexing, selection, and tracking logic from the model registry and resolver.
- Eliminated the `canonical` sub-command, tab view, search tokens, and equivalence configuration structures from the CLI and model selector components.
- Refined model identification, lookup, and provider fallback resolution to bind exclusively to standard, raw model IDs.
- Relocated the equivalence utility script within the catalog package to support script-only policy generation.
- Migrated global service tier settings to a per-model-family architecture (OpenAI, Anthropic, Google).
- Implemented `ServiceTierByFamily` mapping to allow independent configuration and resolution per provider.
- Added automatic migration logic for legacy service tier and fast-mode application settings.
- Updated telemetry, session management, and task execution to support provider-specific tier resolution.
- Added `preferWebsockets` option to `AgentSessionConfig` to expose transport preferences.
- Updated `AgentSession` to manage and forward websocket preferences to sub-sessions.
- Enabled websocket transport by default for benchmark CLI requests.
Passed the provider-capped stream wrapper into AgentSession side-channel requests so /btw, /omfg, IRC auto-replies, and handoff generation share the same per-provider concurrency limit as normal turns.
Added focused coverage for runEphemeralTurn and handoff generation using the configured side stream function.
The per-provider semaphore (e.g. `providers.ollama-cloud.maxConcurrency`) was acquired before `SessionManager.open` and released only after `driveSessionToYield` returned, so it bracketed the whole subagent lifecycle. Any spawn tree wider than `maxConcurrency` deadlocked: parents held every slot while waiting for children that were queued on the same cap — symptoms matched zero LLM requests and tokens=0/requests=0 cancellations.
Moved the bracket into a `StreamFn` wrapper. The wrapper acquires the slot just before each provider HTTP request and releases it the moment the response stream produces 'done'/'error', so a parent's slot is free between turns and child subagents can acquire while their parent's tool calls run. Wraps both the main agent and the advisor (both consume `settingsAwareStreamFn`).
Fixes#3749
The replan-driven title refresh (title.refreshOnReplan, fired after a
`todo init`) called `generateSessionTitle()` without the user's
`TITLE_SYSTEM.md` override, silently falling back to the bundled
`prompts/system/title-system.md` and overwriting auto titles with the
default policy. The override was only ever discovered by main.ts and
passed into the first-input title path on InteractiveMode, never into
`AgentSession.#refreshTitleAfterReplan`. Most visible in Plan Mode,
which initializes todos early.
`AgentSession` now owns the resolved title prompt:
- New `CreateAgentSessionOptions.titleSystemPrompt` threaded by
`createAgentSession()` into the constructor.
- New `AgentSessionConfig.titleSystemPrompt` stored on
`#titleSystemPrompt` with a `get titleSystemPrompt` /
`setTitleSystemPrompt(...)` pair.
- `#refreshTitleAfterReplan` passes `#titleSystemPrompt` as
`customSystemPrompt` to `generateSessionTitle()`.
- `input-controller.ts` reads from `session.titleSystemPrompt`, and
the duplicate `InteractiveMode.titleSystemPrompt` field /
constructor arg / `InteractiveModeContext` field / `runInteractiveMode`
parameter are removed. `InteractiveMode.refreshTitleSystemPrompt`
now calls `session.setTitleSystemPrompt(...)` so a `/move`-style cwd
change keeps the override in sync.
Regression test asserts the prompt handed to `completeSimple()` from
`#refreshTitleAfterReplan` is the configured override, not the bundled
`title-system.md`.
Fixes#3734
- Removed the architectural restriction limiting advisors to read-only tools.
- Updated advisor configuration to permit any built-in tool, including `edit`, `write`, and `bash`.
- Defaulted advisor toolsets to `read`, `grep`, and `glob`, while maintaining strict session isolation for each advisor.
- Introduced comprehensive support for multiple concurrent, independently-configured advisors via `WATCHDOG.yml` files.
- Implemented a full-screen TUI overlay for managing advisor rosters, models, tools, and instructions.
- Added session-wide advisor initialization, telemetry aggregation, and named transcript isolation.
- Enhanced advisor security and observability with secret redaction in tool results and secure XML attribute encoding.
- 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.
AgentSession.#buildAdvisorRuntime constructed the advisor Agent without the provider-shaping options the SDK installs on the main agent: the streamFn wrapper that applies providers.openrouterVariant / providers.antigravityEndpoint / providers.maxInFlightRequests / model.loopGuard.*, the onPayload/onResponse/onSseEvent hooks, the shared providerSessionState map, transformProviderContext (snapcompact, secret obfuscation, image clamping), and a stable promptCacheKey. Advisor turns therefore dropped the OpenRouter sticky-routing variant suffix, used a different prompt_cache_key than the main turn, and skipped the per-session provider hooks — producing intermittent OpenRouter response-cache misses across consecutive advisor calls.
Extract the inline streamFn wrapper in sdk.ts into a shared createSettingsAwareStreamFn helper (packages/coding-agent/src/session/settings-stream-fn.ts) and pass it (plus transformProviderContext) through AgentSessionConfig as advisorStreamFn / transformProviderContext. #buildAdvisorRuntime now hands the advisor Agent the same streamFn, hooks, providerSessionState, promptCacheKey (= advisor session id), and transformProviderContext as the main turn. Adds getAdvisorAgent() accessor on AgentSession for diagnostics and parity tests.
Fixes#3639
- Added formatAdvisorContextPrompt to render project context files into the advisor's system prompt.
- Updated AgentSession to accept and inject advisorContextPrompt into the session system prompt.
- Registered project context files for the advisor to ensure the reviewer evaluates the agent against standing project instructions like AGENTS.md.
- Renamed the `find` and `search` tools to `glob` and `grep` respectively across the codebase to improve command clarity.
- Implemented full-stack support for the renamed tools, including CLI arguments, system prompts, SDK exports, and tool registration.
- Added automated migration logic in `settings` to transform legacy `find` and `search` configuration keys to their new equivalents.
- Updated the `collab-web` renderer registry to ensure backwards compatibility with legacy tool outputs.
- Changed `inlineToolDescriptors` from a boolean to a three-way enum (`auto` | `on` | `off`) to allow per-model defaults.
- Implemented `auto` logic which defaults to inlining descriptors specifically for Gemini models.
- Added a migration to automatically map existing boolean values to `on` or `off` to maintain backward compatibility.
Scoped provider-refusal filtering to live replay so compaction and snapcompact summaries retain the refused turn while outbound provider context still drops the refusal.
Fixes#3592
The createAgentSession default-role resolution ran before extension
factories registered their providers, so a default role pointing at an
extension-provided model (e.g. an openai-compat plugin's
posthog/claude-opus-4-8) returned undefined there. On a fresh launch
(no -c/--resume) the post-extension fallback went straight to
pickDefaultAvailableModel and replaced the user's configured default
with the first bundled provider default that had auth — commonly
openai/gpt-5.5 when OPENAI_API_KEY was set.
The fallback now retries resolveModelRoleValue against the
post-extension allowed-model set before pickDefaultAvailableModel, and
re-applies the role's explicit thinking selector / model host
preconnect.
Fixes#3569
can1357