- Updated auth refresh to return generation booleans and return false for missing, non-oauth, or null-rotation creds.
- Added stream auth retry logic by wrapping streamSimple and retrying once with a fresh key for pre-start 401 only.
- Added changelog note on streaming auth retries and coding-agent onAuthError flow to refresh stale credentials.
- Added snapshot and stream auth tests for headers/no-store, 304 transitions, long-poll wakes, and retry limits.
- Added generation-aware snapshot contracts with generation, serverNowMs, refresher, and rotatesInMs fields.
- Reworked /v1/snapshot serving and client fetching for If-None-Match long-poll with 304/200 status handling.
- Added status checks in remote-store and SDK/CLI snapshot paths, applying updates only when fetch returns 200.
- Added StreamOptions.onAuthError and stream one-shot 401 retry dispatch using refreshed credentials.
- Added fire-and-forget `preconnectModelHost` to prime DNS/TCP/TLS/H2 before the first API call, saving 100–300ms on transcontinental connections.
- Skipped LSP warmup for non-UI (print/script) sessions to avoid CPU contention with LLM stream consumers.
- Added `omp auth-gateway serve/token/status` — a forward-proxy injecting broker credentials for OpenAI Chat, Anthropic Messages, and OpenAI Responses wire formats.
- Added `GET /v1/usage` to auth-broker and auth-gateway; usage cache switched to 5-min per-credential TTL with jitter and last-good fallback on failure.
- Added `AuthStorage.setConfigApiKey/removeConfigApiKey/clearConfigApiKeys` so `models.yml` `apiKey` beats OAuth tokens without overriding `--api-key`.
- Added `omp auth-broker migrate --from-local` for idempotent upload of local SQLite/env credentials to the broker.
- Added `AuthBrokerClient`, `RemoteAuthCredentialStore`, `AuthBrokerRefresher`, and `startAuthBroker` server in `packages/ai/src/auth-broker`.
- Renamed `AuthCredentialStore` class to `SqliteAuthCredentialStore`; extracted `AuthCredentialStore` as a persistence interface.
- Added `exportSnapshot`, `forceRefreshCredentialById`, `disableCredentialById`, and `upsertCredential` to `AuthStorage` for broker wire protocol.
- Added `omp auth-broker` CLI subcommand (serve, token, login, logout, import, status) and `discoverAuthStorage` broker-mode path keyed on `OMP_AUTH_BROKER_URL`.
- Updated `raceWithDeadline` to track whether the timeout branch won the race before logging.
- Deferred the startup scan timeout warning until after the race completed with a deferred result.
- Task tool sessions now expose and forward parent OpenTelemetry config when creating subagent tasks.
- Subprocess execution now derives child telemetry from the parent config with the subagent identity and child session conversation handling.
- Subagent creation now records a handoff span using the resolved parent telemetry handle before running the child loop.
- Added opt-in telemetry configuration to Agent and session APIs, including Agent#setTelemetry mutator.
- Implemented OpenTelemetry spans for invoke_agent, chat, execute_tool, and handoff paths with metadata and step tracking.
- Added a telemetry helper module, OpenTelemetry request/usage types, and dependency wiring with no-op behavior when tracer SDK is absent.
- Added OTEL end-to-end tests and fixed coding-agent OutputSink realignment and artifact-link newline output issues.
When initialServiceTier is resolved from settings (e.g. the user has
serviceTier: priority configured as a default), sdk.ts wrote model_change
and thinking_level_change entries for the new session but omitted
service_tier_change. The stats parser derives priority-tier premium counts
from service_tier_change entries, so sessions started in fast mode without
an explicit /fast toggle had no tier entry and were undercounted in omp-stats.
Mirror the thinking_level_change pattern: write service_tier_change
alongside the other initial entries when initialServiceTier is set.
- Added GoalRuntime with wall-clock and token accounting, budget steering, and lifecycle operations (create, pause, resume, drop, complete).
- Exposed goal tool as a hidden agent tool, activated only when goal mode is enabled.
- Integrated goal continuation loop in InteractiveMode with auto-submit between turns.
- Added status line segment and theme icons for goal mode state.
- Removed ExitPlanModeTool and deleted exit-plan-mode docs/tests, dropping the old approval contract outputs.
- Replaced plan-mode approval flow from exit_plan_mode to resolve across session, SDK, controllers, and discovery.
- Added standing resolve handler accessors and updated resolve routing for queued or standing approval handlers.
- Added PlanApprovalDetails and enforced normalized, validated approval titles with readable plan-file requirements.
- Extended resolve schema and invocation signatures with optional extra metadata and reason trimming behavior updates.
- Updated plan and resolve prompts and changelog guidance to require resolve action, reason, and extra.title for apply/discard.
- Adds omp acp subcommand that launches the agent as an ACP stdio server
- Registers the subcommand in the CLI dispatcher
- Threads terminal-auth args and ACP flags through the launch and main orchestrators
- Exports AgentSession on the public SDK surface
- Updates skills loader to support skill→slash-command conversion and prompt injection
- Updates input-controller to dispatch ACP built-in slash commands
The SDK default-model fallback used `modelRegistry.getAll()` and only
filtered by stored credentials, ignoring the path-scoped `enabledModels`
allow-list. When the configured `modelRoles.default` was filtered out by
`disabledProviders`, the fallback could pick a model from a provider that
`enabledModels` did not permit for the current path.
Add `resolveAllowedModels(modelRegistry, settings, prefs)` which returns
`getAvailable()` intersected with the path-scoped `enabledModels`
patterns (or just `getAvailable()` when no patterns are configured), and
use it for both the default-role resolution and the fallback scan. When
`enabledModels` is set but no allowed model has usable credentials, the
fallback now surfaces a message instead of silently picking a disallowed
provider.
Fixes#1022.
Adds `pi.on("credential_disabled", handler)` so extensions can react to
soft-disabled credentials (e.g. OAuth invalid_grant) without regex-matching
`agent_end` errorMessages.
`AuthStorage.onCredentialDisabled(listener)` returns an unsubscribe function;
multiple listeners fire for every event with per-listener exception isolation
and FIFO buffer-and-replay (cap 32) when none are attached. The constructor
option from #991 stays as sugar for an immediate permanent subscription.
`createAgentSession()` subscribes the per-session extension runner to
`modelRegistry.authStorage` immediately after resolution and unsubscribes on
dispose / startup failure. Events are forwarded via
`ExtensionRunner.emitCredentialDisabled(event)`, which buffers (cap 32,
drop-oldest) until `runner.initialize(...)` runs in the mode controller so
extension handlers see real UI/runtime context, not the constructor no-op
defaults.
Supersedes #997. Builds on #991.
Co-Authored-By: omp <noreply@oh-my-pi.dev>
- Added ownerId metadata to async jobs and to task/bash progress items from the session agent id.
- Extended async job registration and query methods with optional owner filters, and updated cancelAll to target matching owners.
- Updated session handoff and disposal so subagents inherit the parent manager, top-level sessions own it, and teardown cancels own jobs only.
- Added owner-aware async-job tests using hold/AbortSignal and scoped cancelAll assertions for running versus cancelled jobs.
- Added parent-to-subagent artifact manager adoption so subagents reuse the parent `ArtifactManager` and write artifacts into a shared directory with shared IDs.
- Passed the shared artifact manager through tool/session context into subagent executor startup and exposed it via `SessionManager` and `ToolSession` for lookup.
- Updated kernel environment and artifact-resolution paths to prefer `PI_ARTIFACTS_DIR`, falling back to existing session-file-based behavior when absent.
- Added process-wide singleton instances for InternalUrlRouter, AsyncJobManager, and MCPManager.
- Changed internal URL protocols to resolve through registered sessions and scan all active roots/datasets for matches.
- Refactored agent, artifact, memory, rule, skill, jobs, and mcp handlers to use shared manager and rule/skill state.
- Removed per-session protocol/tool wiring and switched tests to initialize and reset global singleton state.
- Pre-registered agents in the global registry before rebuilding the system prompt so peers can discover each other in initial IRC blocks.
- Replaced immediate registry replacement with attachSession to bind the live session and latest sessionFile to the pre-registered entry.
- Ensured pre-registered agents are unregistered during creation failure cleanup when no session was established.
- Added `listWorkspace` native binding and API types, exporting bounded workspace trees with AGENTS.md candidates.
- Reworked `buildWorkspaceTree` and `buildDirectoryTree` to call `listWorkspace` with 5s timeout defaults.
- Replaced startup AGENTS.md discovery with workspace-tree-only scanning and removed legacy AgentsMdSearch session plumbing.
- Updated `WorkspaceTree` and system prompt context to expose `agentsMdFiles` and aligned tests/changelog expectations.
Anthropic counts sessions by metadata.user_id. Without this fix, OMP
generated fresh random entropy on every API request, inflating the
session count and preventing backend attribution to the authenticated
account.
Changes:
packages/ai:
- resolveAnthropicMetadataUserId() now accepts JSON-format user_id
matching real Claude Code's getAPIMetadata shape
({ session_id, account_uuid, ... }). Previously only the legacy
cloaking format was accepted on OAuth, causing stable caller-supplied
values to be silently discarded.
- AnthropicOAuthFlow.exchangeToken() and refreshAnthropicToken() now
populate OAuthCredentials.{accountId, email} from the token response
account block, removing the need for a separate /api/oauth/profile
round-trip.
- AuthStorage.getOAuthAccountId(provider, sessionId) returns the OAuth
accountId for the session-sticky credential, used to build
account_uuid in metadata.user_id. Guards against misattribution for
API-key, runtime-override, env-key, and fallback-resolver paths that
do not record a session credential.
packages/agent:
- Agent.metadataForProvider(provider) resolves request metadata for
the given provider via the installed resolver, or returns the static
metadata value. The plain metadata getter now returns only the static
value; provider-aware resolution is explicit.
- Agent.setMetadataResolver(fn) installs a (provider: string) resolver
evaluated per LLM request in agent-loop, after getApiKey records the
session-sticky credential, so account_uuid reflects the credential
actually used.
- AgentLoopConfig.metadataResolver is called with config.model.provider
after getApiKey, overriding the static metadata field.
packages/coding-agent:
- AgentSession.#syncAgentSessionId installs a metadata resolver that
builds { user_id: JSON.stringify({ session_id, account_uuid? }) },
matching the Anthropic session attribution format. account_uuid is
only included for provider="anthropic" to avoid leaking the OAuth
identity to third-party Anthropic-format-compatible providers.
- sessionId getter prefers providerSessionId when supplied via
AgentSessionConfig so all API paths (getApiKey, direct calls,
metadata resolver) share the same provider-facing session ID.
- prepareSimpleStreamOptions stamps session metadata on direct calls
(runEphemeralTurn, compaction, branch summary, title generation) so
they share the same session bucket as Agent.prompt requests.
- generateBranchSummary and generateSessionTitle accept a
(provider: string) metadata resolver evaluated after their own
getApiKey call for correct credential attribution.
- Added a 5-second `Promise.race` deadline around `buildAgentsMdSearch` and `buildWorkspaceTree` in `createAgentSession` to prevent startup blocking on slow scans.
- Changed startup handling to forward `undefined` to `ToolSession` when scans time out so `buildSystemPromptInternal` can re-run them through its existing `withDeadline` path.
Subagents previously re-ran buildAgentsMdSearch and buildWorkspaceTree on
every spawn, repeating the slowest part of system-prompt construction for
each task tool invocation. On large/pathological repos those scans
exceeded the 5s preparation deadline and tripped the per-subagent
'system prompt preparation timed out' warning.
Forward the parent's already-resolved AgentsMdSearch and WorkspaceTree
through createAgentSession (alongside the existing contextFiles, skills,
and promptTemplates inheritance):
- Add agentsMdSearch and workspaceTree to CreateAgentSessionOptions;
createAgentSession short-circuits the parallel scan promises when
these are provided.
- Resolve them with contextFiles before constructing ToolSession; expose
on ToolSession so the task tool can read the parent's values.
- Thread them through ExecutorOptions (task/executor.ts) into the
subagent's createAgentSession call, and pass them from the task tool
(task/index.ts) on both the worktree-isolated and non-isolated paths.
- Added hideThinkingSummary options across stream, agent, and session payload paths.
- Routed Coding-Agent hideThinkingBlock toggles to agent hideThinkingSummary during session updates.
- Updated OpenAI, Azure OpenAI, and Codex requests to omit reasoning.summary when hide/ summary is null.
- Reworked system-prompt preparation with per-step timeouts, fallback defaults, and step-level warnings.
- Added optional `loadMode` and `summary` fields to `AgentTool` and related type declarations.
- Added `loadMode` and `summary` metadata to built-in tool classes for discoverable/essential behavior.
- Replaced `BUILTIN_TOOL_METADATA` with per-tool fields in discovery code paths.
- Updated `search_tool_bm25` and discovery indexing to use each tool's `summary` text.
- Updated discovery tests to validate tool `loadMode` and summary completeness.
Restore BUILTIN_TOOLS to Record<string, ToolFactory> so external SDK callers can
still invoke BUILTIN_TOOLS.read(session) directly, and move per-tool discovery
metadata (loadMode, summary) into a dedicated BUILTIN_TOOL_METADATA map. All
internal callers (computeEssentialBuiltinNames, getBuiltinDiscoverableEntries,
createTools, sdk.ts initial-tool filter, agent-session built-in collection) now
read metadata through the new map.
Restore the legacy MCP discovery API on AgentSession: getDiscoverableMCPTools()
returns DiscoverableMCPTool[] with description, and getDiscoverableMCPSearchIndex()
returns the legacy DiscoverableMCPSearchIndex whose documents expose
tool.description while remaining usable by searchDiscoverableTools (summary is
populated from description so the BM25 corpus still scores correctly). Generic
discovery via getDiscoverableTools / getDiscoverableToolSearchIndex is unchanged.
Centralize discovery cache invalidation in #invalidateDiscoveryCaches and call it
from #applyActiveToolsByName, refreshMCPTools, and refreshRpcHostTools so the
generic search index can no longer return tools that have already been activated
or registry entries that have been replaced.
Restrict #collectDiscoverableBuiltinTools to entries whose
BUILTIN_TOOL_METADATA[name].loadMode === "discoverable", which keeps hidden
tools (resolve, yield, exit_plan_mode, report_finding, report_tool_issue) and
unknown extension/custom registry entries out of the discovery corpus.
Tests: add coverage for callable BUILTIN_TOOLS factories, legacy MCP description
shape on getDiscoverableMCPTools / getDiscoverableMCPSearchIndex, stale-index
invalidation on setActiveToolsByName, and hidden-tool exclusion from
getDiscoverableTools({ source: "builtin" }).
Wired the generic discovery methods on AgentSession into the tool
factory session, resolved the effective discovery mode (tools.discovery
Mode wins; mcp.discoveryMode as back-compat alias for "mcp-only"),
and threaded the resulting flag into rebuildSystemPrompt so the prompt
template fires the discovery hint for both legacy and new modes.
Added the load-bearing filter in createAgentSession: when the
effective mode is "all", drop any built-in tool whose loadMode is
"discoverable" from the initial tool set unless it is essential per
computeEssentialBuiltinNames, was explicitly listed via
options.toolNames, or was restored from persistence. The model finds
hidden tools via search_tool_bm25 and activates them on demand.
Built-in activation persistence is intentionally limited to the
existing MCP persistence store for this PR; full discovered-tool
persistence is a follow-up.
- Converted systemPrompt APIs and state types to ordered `string[]` across agent, AI, and coding-agent surfaces.
- Added `normalizeSystemPrompts` and applied it to context normalization before building provider request payloads.
- Updated AI providers to emit separate normalized prompt blocks/messages instead of a single merged system prompt.
- Removed dedicated `projectPrompt` state and remapped that context into system-context buckets in session, dump, and token accounting.
- Aligned tests and changelogs to pass and assert `systemPrompt` as arrays with ordered prompt semantics.
- Added DirectoryTree, DirectoryTreeOptions, and buildDirectoryTree exports for configurable tree rendering.
- Changed read tool directory output to use buildDirectoryTree with depth and exclusion limits.
- Added read.summarize settings and summary-mode parseable read output behavior when no selector is used.
- Added tests for truncated root/child listings and hidden or excluded entry filtering.
- Added `WorkspaceTree` and `buildWorkspaceTree` APIs for working-directory tree rendering with limits.
- Extended `buildSystemPrompt` and `createAgentSession` to resolve and pass workspace tree context for system prompts.
- Updated the system prompt template to include a `<workspace-tree>` section with truncation notices before append output.
- Added workspace-tree and system-prompt tests covering sorting, truncation, exclusions, and prompt ordering.
- Added `HindsightSessionState` to `AgentSession` and bound hindsight lifecycle hooks to session state.
- Removed global hindsight state/queue handling and replaced it with per-session `HindsightRetainQueue` batching and scoped flushing.
- Reworked recall, reflect, and retain tools to use `session.getHindsightSessionState()` instead of sessionId-based lookup.
- Updated SDK/task/backend/controller flows to pass `session`/`parentHindsightSessionState`, scope `/memory` behavior, and document it in changelog.
- Added `memory.backend` and `hindsight.*` settings schema with migration from `memories.enabled` legacy mode.
- Added Hindsight memory backend runtime modules for resolved config, client creation, bank ID derivation, and state lifecycle.
- Added off/local/hindsight backends and resolver wiring across SDK, commands, and compaction context.
- Added `hindsight_recall`, `hindsight_reflect`, and `hindsight_retain` tools with schema validation and backend gating.
- Added Memory tab metadata and symbols to expose backend selection in the settings UI.
- Added package export barrels and tests for bank ID, content formatting, and hindsight config env precedence.
- Consolidated AI provider imports through register-builtins and moved Gemini/Antigravity header helpers to a shared module.
- Added lazy loading for heavy providers and SDK-backed modules with cached initialization to trim startup cost.
- Converted markdown conversion helpers to async and awaited htmlToBasicMarkdown in affected scraper and kernel output paths.
- Parsed bundled agent definitions on-demand and moved BrowserTool prompt rendering behind a memoized getter.
- Added cached validation/error handling paths by replacing AJV runtime checks with Value.Check and trimming validation error output.
The warmup path no longer produces prelude docs, so the cached-session
warmup it implemented added no value over the create-on-first-execute
path that withKernelSession already covers. Remove warmPythonEnvironment,
the backend warm() hook, the eval-tool warmup loop, the createTools
warmup preflight, and the forcePythonWarmup option. Simplify
ExecutorBackendCallOptions into ExecutorBackendExecOptions since execute
is now the only consumer.
- Added a unified eval framework with parser grammar, backend interfaces, and JS/Python execution result types.
- Added eval tool docs and updated prompts for fenced cells, `eval.py`/`eval.js`, and fallback behavior.
- Replaced the built-in `python` tool with `eval` across registry, rendering, interactive modes, and tool settings.
- Migrated Python execution runtime from `src/ipy` to `src/eval/py`, renamed state fields, and removed legacy introspection.
- Refactored browser tooling from in-process VM helpers to worker-managed tab supervisors and protocol transport.
- Added eval parser fallback and JS tool-bridge tests, updated imports, and removed obsolete python-mode suites.
The signature in #computeAppliedToolSignature hashed the full raw
instructions string, but rebuildSystemPrompt truncates each server
instruction at 4000 chars before embedding it. A change past character
4000 produced an identical prompt but a different signature, causing a
spurious rebuild and a cache miss on every such reconnect.
Fix: hoist MAX_MCP_INSTRUCTIONS_LENGTH to module scope in sdk.ts and
apply the same truncation in the getMcpServerInstructions callback
before returning. The session now hashes exactly the strings that end
up in the prompt.
Regression test: changes only past char 4000 do not trigger a rebuild;
changes within the first 4000 chars do.
Two cache-stability fixes for Anthropic prompt caching during MCP server
reconnects, which happen routinely (~5 min per server) in long sessions
due to SSE transport keepalive timeouts.
1) MCPManager: deterministic tool ordering
`#tools` is now sorted by name after every mutation. The previous
filter-out + push-to-end pattern in `#replaceServerTools` moved the
reconnecting server's tools to the end of the array, producing a new
byte order whenever the reconnect sequence differed from the initial
discovery sequence. With multiple healthy servers, each reconnect of
the non-last server flipped the order and invalidated the tools
cache breakpoint sent to Anthropic.
Sort applies in `discoverAndConnect` (initial population) and
`#replaceServerTools` (used by `reconnectServer` and
`refreshServerTools`). The comparator is character-code based,
locale-independent and deterministic. `sortMCPToolsByName` is
exported as a small generic helper and unit-tested.
2) AgentSession: skip system-prompt rebuild when inputs are unchanged
`#applyActiveToolsByName` (called from `refreshMCPTools` after every
reconnect) used to unconditionally call `rebuildSystemPrompt` and
`setSystemPrompt` even when the resulting prompt was byte-identical.
This wasted CPU on every flap and risked silent cache invalidation
if the rebuild path ever became non-deterministic.
Now `#applyActiveToolsByName` computes a stable signature of the
inputs `rebuildSystemPrompt` reads and skips the rebuild when the
signature matches the last successful one. The signature covers:
- active tool names in render order
- active tool labels and descriptions (rendered as `{{label}}:
\`{{name}}\`` in the prompt body)
- when MCP discovery is on, every registry tool's name + label +
description (the prompt summarizes discoverable-but-inactive
MCP tools)
- per-server MCP `instructions` text (embedded under "## MCP
Server Instructions" in the appended prompt; can change on
server upgrade while tool list stays identical)
Server instructions are read via a new optional
`getMcpServerInstructions` callback on `AgentSessionConfig`, wired
from the SDK as `() => mcpManager.getServerInstructions()`.
`refreshBaseSystemPrompt()` continues to rebuild unconditionally and
refreshes the cached signature, so explicit refreshes still pick up
ambient changes (edit-mode toggles, memory writes, etc.) that the
signature does not cover.
Signature inputs deliberately NOT covered: tool input schemas, memory
instructions read from disk, and other ambient state. Callers that
mutate those must call `refreshBaseSystemPrompt()` explicitly; existing
hooks (`#syncEditToolModeAfterModelChange`, memory hooks, `/clear`)
already do.
- Parallelized startup by deferring plugin preload and running AGENTS.md scan plus context/template/command discovery in parallel.
- Added AgentsMdSearch exports and options so prebuilt search results were passed into system-prompt construction.
- Reworked logger timing to use AsyncLocalStorage-backed nested spans, initialize a root span, and emit hierarchical summaries.
- Added PI_TIMING-gated TS/TSX module-load timing via side-effect module-timer registration and wrapped key init/request paths with logger.time.
Add optional defaultLevel to ThinkingConfig schema/type so models.yml can
declare a preferred starting thinking level per model. On model switch
the agent session adopts model.thinking.defaultLevel when present (with
explicit caller-supplied level still winning); otherwise current behavior
is preserved. SDK initial selection prefers the model's defaultLevel
before falling back to the global defaultThinkingLevel setting.
Fixes#775
- Added a localProtocolOptions field to session and executor option types for configurable local:// behavior.
- Passed localProtocolOptions through to LocalProtocolHandler creation and subagent session bootstrap.
- Propagated parent session local protocol settings from TaskTool so subprocess subagents share the same local:// artifacts and session context.
- Renamed MCP tool IDs from `mcp_<server>_<tool>` to `mcp__<server>_<tool>`, and changed built-in `grep` to `search`.
- Updated `parseMCPToolName()` and bridge helpers to require and trim the `mcp__` prefix.
- Updated cursor, manager, and session discovery flows to require `mcp__`-prefixed tool names.
- Updated MCP tests and assertion fixtures to use `mcp__`-prefixed tool IDs and expected system prompts.
- Renamed the built-in `grep` content-search tool to `search` across settings, schemas, and SDK exports.
- Switched execution wiring so `Task`, `Plan`, cursor, and shell mapping now invoke `search` instead of `grep`.
- Updated prompts, plan-mode docs, and example tool lists to replace `grep`/`ls` references with `search` guidance.
- Aligned `Grep*`/`grep` event, renderer, and hook types to `Search*`/`search` across runtime and tests.
- Documented and fixed `search` result rendering budget behavior and added internal-URL/path-list transcript notes.
- Added agent identity and registry fields to session configuration and session creation, enabling relay routing metadata for agent sessions.
- Implemented non-persistent IRC relay emission to forward incoming and reply observations from non-main agents into the main session UI.
- Updated IRC UI rendering to support `irc:relay` messages with participant-aware arrow formatting and body display.
- Updated `formatMatchLine` to emit `*` for matched lines, a leading space for context, and a `|` anchor/content separator.
- Revised grep/hashline mismatch messages and prompts to describe the new marker and separator format.
- Aligned affected atom and hashline tests with the updated match-line prefixes and separators.
- Added `AgentRegistry` singleton with session registration/unregistration and IRC routing metadata for peer lookups.
- Added IRC messaging prompts and tooling with `irc.enabled` setting, `list/send` tool paths, and peer roster rendering.
- Changed `/btw` to session-side `runEphemeralTurn`, added background IRC exchange flushing, and fixed empty-input checks.
- Added unit tests for IRC tool and BtwController ephemeral behavior, including disabled, busy, not-found, and abort cases.
- Added `openai` and `openai-codex` as image providers and let `providers.image=auto` prefer GPT images.
- Updated settings, selector, and SDK wiring so OpenAI image providers pass through `setPreferredImageProvider`.
- Replaced Gemini-only image tooling with `image-gen` and added OpenAI/Codex hosted-image execution with SSE parsing.
- Added image-gen and handoff tests, including final-yield no-compaction regression and OpenAI payload/header assertions.
can1357