@caupulican/pi-adaptative 0.80.100 → 0.80.103

package/dist/core/agent-session.d.ts

@@ -29,6 +29,7 @@ import { type CustomMessage } from "./messages.ts";
 import { type ModelCapabilityProfile } from "./model-capability.ts";
 import type { ModelRegistry } from "./model-registry.ts";
 import { type StoredFitnessReport } from "./models/fitness-store.ts";
+import { type LocalRuntimeDeps, OllamaRuntime } from "./models/local-runtime.ts";
 import { type PromptTemplate } from "./prompt-templates.ts";
 import { type ModelFitnessReport } from "./research/model-fitness.ts";
 import { type ResearchRunResult } from "./research/research-runner.ts";
@@ -91,6 +92,10 @@ export type AgentSessionEvent = Exclude<AgentEvent, {
     success: boolean;
     attempt: number;
     finalError?: string;
+} | {
+    type: "routing_start";
+} | {
+    type: "routing_end";
 };
 /** Listener function for agent session events */
 export type AgentSessionEventListener = (event: AgentSessionEvent) => void;
@@ -148,6 +153,12 @@ export interface AgentSessionConfig {
      * defaults to the real, best-effort collector.
      */
     collectWorkspaceSources?: typeof collectWorkspaceSources;
+    /**
+     * Injected fetch/spawn/exists for the local (Ollama) runtime health-check + boot used by the
+     * model router before a turn routed to a local model (see _ensureLocalModelReady). Unit tests
+     * inject fakes so they never hit a real network/process; production defaults to the real ones.
+     */
+    localRuntimeDeps?: LocalRuntimeDeps;
 }
 export interface ExtensionBindings {
     uiContext?: ExtensionUIContext;
@@ -345,6 +356,8 @@ export declare class AgentSession {
     private readonly _brainCurator;
     private _lastCurationSkipReason;
     private _inertExtensionWarnings;
+    /** Extensions the active resource profile removed from the runtime set (surfaced in /context). */
+    private _profileDeniedExtensionCount;
     private _lastPreDigestSkipReason;
     private _unboundToolGrantWarnings;
     private _toolArtifactStore;
@@ -370,6 +383,12 @@ export declare class AgentSession {
     private _cwd;
     private _agentDir;
     private _collectWorkspaceSources;
+    private _localRuntimeDeps?;
+    /** Lazy, cached by baseUrl so the router path and any other caller share one instance per server. */
+    private _localRuntimes;
+    /** Server URLs confirmed reachable THIS session — skips the health-check round trip on every
+     * local-routed turn once warm. Keyed the same way as _localRuntimes. */
+    private _localRuntimeConfirmedUp;
     private _extensionRunnerRef?;
     private _initialActiveToolNames?;
     private _allowedToolNames?;
@@ -673,6 +692,16 @@ export declare class AgentSession {
     private _emit;
     private _emitQueueUpdate;
     private _lastAssistantMessage;
+    /**
+     * User messages already painted to the UI by an early, synthetic `message_start` fired from
+     * `_promptUnserialized` — before the model-router judge's bounded LLM call — so the prompt
+     * appears immediately instead of hanging until routing finishes. The real agent-loop run emits
+     * its own authoritative `message_start` for the SAME message object once the turn actually
+     * starts; `_handleAgentEvent` consumes (deletes) it from this set to suppress that one duplicate
+     * listener notification. Persistence is untouched: it stays keyed off `message_end`, which is
+     * never added here and never suppressed.
+     */
+    private _earlyDisplayedUserMessages;
     /** Internal handler for agent events - shared by subscribe and reconnect */
     private _handleAgentEvent;
     private _willRetryAfterAgentEnd;
@@ -797,13 +826,41 @@ export declare class AgentSession {
     private _buildSituationSoulPrompt;
     private _buildSelfModificationPrompt;
     private _buildAutonomyPrompt;
+    private _buildSystemPromptOptionsForToolNames;
     private _rebuildSystemPrompt;
+    /**
+     * Build a system prompt for a specific tool surface WITHOUT touching the session's base prompt
+     * state. Used for a router-swapped turn (G4): the routed model runs against a filtered tool set,
+     * so it must also receive a system prompt whose tool guidelines/snippets match that filtered
+     * surface — but the change is per-turn, so it must not mutate `_baseSystemPromptOptions` (which
+     * later turns and extension events read).
+     */
+    private _buildSystemPromptForToolNames;
     private _runAgentPrompt;
     private _isModelAvailableAndAuthed;
     private _resolveExecutorRoute;
     /** True if a run_toolkit_script tool result since `fromIndex` actually EXECUTED (not error/ambiguous). */
     private _executorTurnExecutedScript;
     private _buildExecutorRefinedPrompt;
+    /**
+     * Shared {@link OllamaRuntime} for a given server, lazily created and cached by baseUrl so every
+     * caller — the router's readiness gate below and any host UI's own model-lifecycle commands
+     * (e.g. `/models`) — sees and can stop the SAME pi-managed process instead of each tracking its
+     * own untracked child.
+     */
+    getLocalRuntime(baseUrl?: string): OllamaRuntime;
+    /** models.json registers a local model's baseUrl as `<server>/v1` (OpenAI-compat); the runtime's
+     * own health/boot endpoints are on the Ollama-native server root. */
+    private _deriveOllamaServerUrl;
+    /**
+     * If the last assistant message in this session was an error from THIS exact local server, a
+     * cached "confirmed up" flag would be stale (the server may have died mid-session) — drop it so
+     * the next ensure-check is a real one instead of trusting stale state.
+     */
+    private _invalidateLocalRuntimeIfLastCallFailed;
+    private _ensureLocalModelReady;
+    private _maybeInstallOllamaOnConsent;
+    private _ensureRouteModelReady;
     private _resolveModelRouterTurnRoute;
     private _resolveModelRouterModelForIntent;
     private _resolveConfiguredTierModel;
@@ -1021,6 +1078,21 @@ export declare class AgentSession {
     private _isToolOrCommandAllowedByProfile;
     private _hasToolOrCommandProfileGate;
     private _filterExtensionsForRuntime;
+    /**
+     * /context observations for skills/prompts/extensions the active resource profile removed from
+     * listings — the analog of the withheld-AGENTS.md warning. Strict UAC makes these silently absent,
+     * so a lean profile's effect on the resource surface stays visible. Counts are profile-scoped
+     * (skills/prompts via the profile-independent discovery universe filtered by the live profile
+     * filter; extensions via the runtime filter's denied tally). Empty when nothing is withheld.
+     *
+     * Uses `isResourceDeniedByActiveProfile` (profile-only), not `isResourceAllowedByProfile` (which
+     * also folds in the user's own legacy `disabledResources` list): a plain user-disabled resource
+     * must never be misattributed to "the active resource profile" — that case is already surfaced by
+     * the G14 disable-wins warning. With no active profile at all, the helper always reports nothing
+     * denied, so this naturally stays silent (extensions keep their own runtime-filter-derived count,
+     * which is already correctly zero absent a profile).
+     */
+    private _profileDeniedResourceObservations;
     private _reapplyActiveProfileModelSettings;
     private _initializeMemory;
     /** Register a memory provider contributed by an extension; applied on the next memory (re)init. */