@botbotgo/agent-harness 0.0.40 → 0.0.42

package/README.md

@@ -2,36 +2,26 @@
 
 ## Product Overview
 
-`@botbotgo/agent-harness` solves the gap between an agent execution engine and a real multi-agent application runtime.
+`@botbotgo/agent-harness` is a workspace-shaped application runtime for real agent products.
 
-The problem:
+It is not a new agent framework. It is the layer that sits around LangChain v1 and DeepAgents so an application can be assembled, configured, operated, and recovered as one runtime.
 
-- agent logic, tools, MCP, routing, memory, and approvals usually end up scattered across code and scripts
-- execution frameworks can run agents, but they do not give you a workspace-shaped product runtime by themselves
-- applications need persisted threads, resumability, approvals, and operational control, not just model calls
+The package is built for the gap between:
 
-What this package provides:
+- agent execution semantics owned by LangChain v1 and DeepAgents
+- application runtime concerns such as persisted threads, approvals, recovery, routing, maintenance, and local resource loading
 
-- a workspace runtime for multi-agent applications
-- YAML-defined agents, models, routing, and maintenance policy
-- local tools and SKILL packages loaded from `resources/`
-- DeepAgents-first execution with LangChain v1 compatibility
-- feature-level runtime APIs for runs, threads, approvals, and events
-
-Core API:
+What it provides:
 
-- `createAgentHarness(...)`
-- `run(...)`
-- `subscribe(...)`
-- `listThreads(...)`
-- `getThread(...)`
-- `listApprovals(...)`
-- `getApproval(...)`
-- `stop(...)`
+- a small runtime API centered on `createAgentHarness(...)`, `run(...)`, `subscribe(...)`, inspection methods, and `stop(...)`
+- YAML-defined runtime assembly for hosts, models, routing, recovery, concurrency, MCP, and maintenance policy
+- DeepAgents-first execution with LangChain v1 compatibility
+- local `resources/tools/` and `resources/skills/` loading
+- persisted runs, threads, approvals, events, and resumable checkpoints
 
 ## Quick Start
 
-Install the package:
+Install:
 
 ```bash
 npm install @botbotgo/agent-harness
@@ -54,19 +44,17 @@ your-workspace/
     skills/
 ```
 
-Use the standard layout only. Agent entry files must live under `config/agents/`.
-
 Minimal usage:
 
 ```ts
 import { createAgentHarness, run, stop } from "@botbotgo/agent-harness";
 
-const runtime = await createAgentHarness("/absolute/path/to/your-workspace");
+const runtime = await createAgentHarness("/absolute/path/to/workspace");
 
 try {
   const result = await run(runtime, {
     agentId: "auto",
-    input: "Summarize what this workspace is for.",
+    input: "Explain what this workspace is for.",
   });
 
   console.log(result.output);
@@ -77,13 +65,16 @@ try {
 
 ## Feature List
 
-- Workspace runtime with DeepAgents-first execution and LangChain v1 compatibility
-- YAML-defined host routing through `config/workspace.yaml`
-- Auto-discovered local tools and SKILL packages from `resources/tools/` and `resources/skills/`
-- MCP bridge support for agent-declared servers
-- MCP server support for exposing an agent toolset to other clients
-- Persisted threads, approvals, run lifecycle, and resumable checkpoints
+- Workspace runtime for multi-agent applications
+- DeepAgents-first execution with LangChain v1 compatibility
+- YAML-defined host routing
+- Auto-discovered local tools and SKILL packages
+- MCP bridge support for agent-declared MCP servers
+- MCP server support for exposing harness tools outward
+- Persisted threads, runs, approvals, and lifecycle events
+- Recovery policy and resumable checkpoints
 - Background checkpoint maintenance
+- Runtime-level concurrency control
 
 ## How To Use
 
@@ -95,13 +86,9 @@ import { AgentHarnessRuntime, createAgentHarness } from "@botbotgo/agent-harness
 const runtime: AgentHarnessRuntime = await createAgentHarness("/absolute/path/to/workspace");
 ```
 
-Or:
-
-```ts
-const runtime = await createAgentHarness(workspaceBundle);
-```
+You can also create a runtime from a precompiled `WorkspaceBundle`.
 
-`createAgentHarness(workspaceRoot)` loads one `WorkspaceBundle`, resolves `resources/`, initializes persistence under `runRoot`, and starts runtime maintenance.
+`createAgentHarness(...)` loads one workspace, resolves `resources/`, initializes persistence under `runRoot`, and starts runtime maintenance.
 
 ### Run A Request
 
@@ -110,22 +97,34 @@ import { run } from "@botbotgo/agent-harness";
 
 const result = await run(runtime, {
   agentId: "orchestra",
-  input: "Explain the available agents in this workspace.",
+  input: "Summarize the runtime design.",
+  context: {
+    requestId: "req-123",
+  },
+  state: {
+    visitCount: 1,
+  },
 });
 ```
 
-Each run creates or continues a persisted thread. The result includes `threadId`, `runId`, `state`, and `output`.
+Each run creates or continues a persisted thread and returns `threadId`, `runId`, `state`, and `output`.
+
+When the upstream LangChain v1 or DeepAgents graph expects extra invocation data, the runtime passes it through directly instead of inventing a parallel harness abstraction:
+
+- `context` is forwarded as runtime context
+- `state` is merged into the invocation input
+- `files` is merged into the invocation input for state-backed DeepAgents files, memories, and skills
 
 ### Let The Runtime Route
 
 ```ts
 const result = await run(runtime, {
   agentId: "auto",
-  input: "Inspect this repository and explain the release flow.",
+  input: "Inspect the repository and explain the release flow.",
 });
 ```
 
-`agentId: "auto"` evaluates ordered `routing.rules` first, then falls back to `routing.defaultAgentId`, and only uses model routing when `routing.modelRouting: true`.
+`agentId: "auto"` evaluates ordered `routing.rules`, then `routing.defaultAgentId`, and only falls back to model routing when `routing.modelRouting: true`.
 
 ### Stream Output And Events
 
@@ -144,9 +143,9 @@ const result = await run(runtime, {
 });
 ```
 
-The runtime emits typed lifecycle events for output, state changes, approvals, and delegations. `subscribe(...)` is a read-only observer surface.
+`subscribe(...)` is a read-only observer surface over stored lifecycle events.
 
-### Query Threads And Approvals
+### Inspect Threads And Approvals
 
 ```ts
 import {
@@ -162,21 +161,7 @@ const approvals = await listApprovals(runtime, { status: "pending" });
 const approval = approvals[0] ? await getApproval(runtime, approvals[0].approvalId) : null;
 ```
 
-These methods return stored runtime data, not raw persistence, workspace, or backend instances.
-
-### Use Skills And Local Tools
-
-`agent-harness` treats `resources/skills/` as SKILL packages and `resources/tools/` as executable local tools.
-
-```yaml
-spec:
-  skills:
-    - path: resources/skills/reviewer
-  tools:
-    - ref: tool/local-toolset
-```
-
-Tool modules are discovered from `resources/tools/*.js`, `resources/tools/*.mjs`, and `resources/tools/*.cjs`. The preferred format is exporting `tool({...})`.
+These methods return runtime-facing records, not raw persistence or backend objects.
 
 ### Bridge MCP Servers Into Agents
 
@@ -189,10 +174,9 @@ spec:
     - name: docs
       transport: http
       url: https://example.com/mcp
-      token: ${DOCS_MCP_TOKEN}
 ```
 
-The runtime discovers MCP tools, filters them through agent config, and exposes them like any other tool.
+The runtime discovers MCP tools, filters them through agent configuration, and exposes them like other tools.
 
 ### Expose Runtime Tools As An MCP Server
 
@@ -215,33 +199,41 @@ await stop(runtime);
 
 Core workspace files:
 
-- `config/workspace.yaml`: runtime defaults such as `runRoot`, routing, and maintenance
-- `config/agent-context.md`: shared bootstrap context for agents
-- `config/models.yaml`: named model presets
-- `config/agents/direct.yaml`: optional lightweight side-path host
-- `config/agents/orchestra.yaml`: default DeepAgent execution host
-- `resources/package.json`: resource package boundary
-- `resources/tools/`: local tool modules
-- `resources/skills/`: local skills
+- `config/workspace.yaml`
+- `config/agent-context.md`
+- `config/models.yaml`
+- `config/agents/direct.yaml`
+- `config/agents/orchestra.yaml`
+- `resources/package.json`
+- `resources/tools/`
+- `resources/skills/`
 
 ### `config/workspace.yaml`
 
-Use this file for:
+Use this file for runtime-level policy:
 
 - `runRoot`
-- ordered `routing.rules`
+- `routing.rules`
+- `routing.defaultAgentId`
 - `routing.systemPrompt`
+- `routing.modelRouting`
+- `concurrency.maxConcurrentRuns`
+- `recovery.enabled`
+- `recovery.resumeOnStartup`
+- `recovery.maxRecoveryAttempts`
 - `maintenance.checkpoints.*`
 
 If `runRoot` is omitted, the runtime defaults to `<workspace-root>/run-data`.
 
 ### `config/agent-context.md`
 
-Use this file for shared bootstrap context that agents read at construction time. Put stable project context here, not long-term mutable memory.
+Use this file for shared startup context loaded into agents at construction time.
+
+Put stable project context here. Do not use it as mutable long-term memory.
 
-### Agent YAML
+### `config/agents/*.yaml`
 
-Use `config/agents/*.yaml` to configure agents. Common fields include:
+Use agent YAML for upstream-facing agent assembly. Common fields include:
 
 - `modelRef`
 - `systemPrompt`
@@ -251,19 +243,39 @@ Use `config/agents/*.yaml` to configure agents. Common fields include:
 - `checkpointer`
 - `store`
 - `backend`
+- `middleware`
 - `subagents`
+- `mcpServers`
 
-### Resource Package
+### `resources/`
 
-Use `resources/` for executable extensions:
+Use `resources/` for executable local extensions:
 
-- `resources/tools/` for local tool modules
+- `resources/tools/` for tool modules
 - `resources/skills/` for SKILL packages
 
-Keep runtime extension source under `resources/`. Keep tests outside the published source tree, for example under the repository `test/` folder.
+Tool modules are discovered from `resources/tools/*.js`, `resources/tools/*.mjs`, and `resources/tools/*.cjs`.
+
+The preferred tool module format is exporting `tool({...})`.
+
+Keep runtime extension source under `resources/`. Keep tests outside the published source tree, for example under repository `test/`.
 
-### Skills And MCP
+## Design Notes
 
-- Use `resources/skills/` for reusable skill packages
-- Use `mcpServers:` in `config/agents/*.yaml` to bridge external MCP tools into an agent
-- Use `createToolMcpServer(...)` or `serveToolsOverStdio(...)` when you want the runtime to act as an MCP server for another client
+- `agent-harness` should express LangChain v1 and DeepAgents concepts as directly as possible
+- agent-level execution behavior stays upstream
+- application-level orchestration and lifecycle management stays in the harness
+- checkpoint resume is treated as a system-managed runtime behavior, not a primary public abstraction
+
+## API Summary
+
+- `createAgentHarness(...)`
+- `run(...)`
+- `subscribe(...)`
+- `listThreads(...)`
+- `getThread(...)`
+- `listApprovals(...)`
+- `getApproval(...)`
+- `createToolMcpServer(...)`
+- `serveToolsOverStdio(...)`
+- `stop(...)`

package/dist/config/workspace.yaml

@@ -102,3 +102,17 @@ spec:
   #     sqlite:
   #       sweepBatchSize: 200
   #       vacuum: false
+
+  # agent-harness feature: runtime-managed recovery policy for interrupted runs.
+  # This keeps checkpoint resume as an internal lifecycle concern instead of a primary user-facing API concept.
+  #
+  # Current support:
+  # - startup recovery of runs already in `resuming` state
+  # - persisted approval-decision intent for cross-restart resume continuation
+  # - bounded retry attempts to avoid infinite restart loops
+  #
+  # Example:
+  # recovery:
+  #   enabled: true
+  #   resumeResumingRunsOnStartup: true
+  #   maxRecoveryAttempts: 3

package/dist/contracts/types.d.ts

@@ -86,9 +86,13 @@ export type LangChainAgentParams = {
     model: CompiledModel;
     tools: CompiledTool[];
     systemPrompt?: string;
+    stateSchema?: unknown;
     responseFormat?: unknown;
     contextSchema?: unknown;
     middleware?: Array<Record<string, unknown>>;
+    includeAgentName?: "inline";
+    version?: "v1" | "v2";
+    name?: string;
     description: string;
 };
 export type CompiledSubAgent = {
@@ -119,6 +123,8 @@ export type DeepAgentParams = {
     name: string;
     memory: string[];
     skills: string[];
+    generalPurposeAgent?: boolean;
+    taskDescription?: string;
 };
 export type CompiledModel = {
     id: string;
@@ -176,7 +182,7 @@ export type CompiledAgentBinding = {
         runRoot: string;
         workspaceRoot?: string;
         hostFacing: boolean;
-        checkpointer?: Record<string, unknown>;
+        checkpointer?: Record<string, unknown> | boolean;
         store?: Record<string, unknown>;
     };
 };
@@ -262,6 +268,9 @@ export type RunStartOptions = {
     agentId?: string;
     input: MessageContent;
     threadId?: string;
+    context?: Record<string, unknown>;
+    state?: Record<string, unknown>;
+    files?: Record<string, unknown>;
     listeners?: RunListeners;
 };
 export type RunDecisionOptions = {
@@ -396,6 +405,12 @@ export type RuntimeModelResolver = (modelId: string) => unknown;
 export type RuntimeEmbeddingModelResolver = (embeddingModelId: string) => unknown;
 export type RuntimeVectorStoreResolver = (vectorStoreId: string) => unknown;
 export type RuntimeMiddlewareResolver = (binding: CompiledAgentBinding) => unknown[];
+export type RuntimeDeclaredMiddlewareResolver = (input: {
+    kind: string;
+    config: Record<string, unknown>;
+    binding?: CompiledAgentBinding;
+    resolveModel: (model: CompiledModel) => Promise<unknown>;
+}) => unknown | unknown[] | null | undefined | Promise<unknown | unknown[] | null | undefined>;
 export type RuntimeCheckpointerResolver = (binding: CompiledAgentBinding) => unknown;
 export type RuntimeStoreResolver = (binding: CompiledAgentBinding) => unknown;
 export type RuntimeBackendResolver = (binding: CompiledAgentBinding) => unknown;
@@ -405,6 +420,7 @@ export type RuntimeAdapterOptions = {
     embeddingModelResolver?: RuntimeEmbeddingModelResolver;
     vectorStoreResolver?: RuntimeVectorStoreResolver;
     middlewareResolver?: RuntimeMiddlewareResolver;
+    declaredMiddlewareResolver?: RuntimeDeclaredMiddlewareResolver;
     checkpointerResolver?: RuntimeCheckpointerResolver;
     storeResolver?: RuntimeStoreResolver;
     backendResolver?: RuntimeBackendResolver;

package/dist/package-version.d.ts

@@ -1 +1 @@
-export declare const AGENT_HARNESS_VERSION = "0.0.39";
+export declare const AGENT_HARNESS_VERSION = "0.0.41";

package/dist/package-version.js

@@ -1 +1 @@
-export const AGENT_HARNESS_VERSION = "0.0.39";
+export const AGENT_HARNESS_VERSION = "0.0.41";

package/dist/persistence/file-store.d.ts

@@ -8,6 +8,36 @@ type ThreadMeta = {
     status: RunState;
     latestRunId: string;
 };
+type RunMeta = {
+    runId: string;
+    threadId: string;
+    agentId: string;
+    executionMode: string;
+    createdAt: string;
+    updatedAt: string;
+};
+type Lifecycle = {
+    state: RunState;
+    previousState: RunState | null;
+    stateEnteredAt: string;
+    lastTransitionAt: string;
+    resumable: boolean;
+    checkpointRef: string | null;
+};
+type RunIndexRecord = {
+    runId: string;
+    threadId: string;
+    state: RunState;
+    resumable: boolean;
+    updatedAt: string;
+};
+type RecoveryIntent = {
+    kind: "approval-decision";
+    savedAt: string;
+    checkpointRef: string | null;
+    resumePayload: unknown;
+    attempts: number;
+};
 export declare class FilePersistence {
     private readonly runRoot;
     constructor(runRoot: string);
@@ -31,6 +61,7 @@ export declare class FilePersistence {
     setRunState(threadId: string, runId: string, state: RunState, checkpointRef?: string | null): Promise<void>;
     appendEvent(event: HarnessEvent): Promise<void>;
     listSessions(): Promise<ThreadSummary[]>;
+    listRunIndexes(): Promise<RunIndexRecord[]>;
     getSession(threadId: string): Promise<ThreadSummary | null>;
     getThreadMeta(threadId: string): Promise<ThreadMeta | null>;
     listThreadRuns(threadId: string): Promise<ThreadRunRecord[]>;
@@ -38,6 +69,8 @@ export declare class FilePersistence {
     listApprovals(): Promise<ApprovalRecord[]>;
     getApproval(approvalId: string): Promise<ApprovalRecord | null>;
     getRunApprovals(threadId: string, runId: string): Promise<ApprovalRecord[]>;
+    getRunMeta(threadId: string, runId: string): Promise<RunMeta>;
+    getRunLifecycle(threadId: string, runId: string): Promise<Lifecycle>;
     listDelegations(): Promise<DelegationRecord[]>;
     createApproval(record: ApprovalRecord): Promise<void>;
     resolveApproval(threadId: string, runId: string, approvalId: string, status: ApprovalRecord["status"]): Promise<ApprovalRecord>;
@@ -47,5 +80,8 @@ export declare class FilePersistence {
     listArtifacts(threadId: string, runId: string): Promise<ArtifactListing>;
     appendThreadMessage(threadId: string, message: TranscriptMessage): Promise<void>;
     listThreadMessages(threadId: string, limit?: number): Promise<TranscriptMessage[]>;
+    saveRecoveryIntent(threadId: string, runId: string, intent: RecoveryIntent): Promise<void>;
+    getRecoveryIntent(threadId: string, runId: string): Promise<RecoveryIntent | null>;
+    clearRecoveryIntent(threadId: string, runId: string): Promise<void>;
 }
 export {};

package/dist/persistence/file-store.js

@@ -1,4 +1,5 @@
 import path from "node:path";
+import { rm } from "node:fs/promises";
 import { readdir } from "node:fs/promises";
 import { ensureDir, fileExists, readJson, writeJson } from "../utils/fs.js";
 export class FilePersistence {
@@ -168,6 +169,14 @@ export class FilePersistence {
         }));
         return records.sort((a, b) => b.updatedAt.localeCompare(a.updatedAt));
     }
+    async listRunIndexes() {
+        const runIndexDir = path.join(this.runRoot, "indexes", "runs");
+        if (!(await fileExists(runIndexDir))) {
+            return [];
+        }
+        const entries = (await readdir(runIndexDir)).sort();
+        return Promise.all(entries.map((entry) => readJson(path.join(runIndexDir, entry))));
+    }
     async getSession(threadId) {
         const filePath = path.join(this.runRoot, "indexes", "threads", `${threadId}.json`);
         if (!(await fileExists(filePath))) {
@@ -249,6 +258,12 @@ export class FilePersistence {
         const entries = (await readdir(approvalsDir)).sort();
         return Promise.all(entries.map((entry) => readJson(path.join(approvalsDir, entry))));
     }
+    async getRunMeta(threadId, runId) {
+        return readJson(path.join(this.runDir(threadId, runId), "meta.json"));
+    }
+    async getRunLifecycle(threadId, runId) {
+        return readJson(path.join(this.runDir(threadId, runId), "lifecycle.json"));
+    }
     async listDelegations() {
         const delegationsDir = path.join(this.runRoot, "indexes", "delegations");
         if (!(await fileExists(delegationsDir))) {
@@ -321,4 +336,21 @@ export class FilePersistence {
         const current = await readJson(messagesPath);
         return current.items.slice(-limit);
     }
+    async saveRecoveryIntent(threadId, runId, intent) {
+        await writeJson(path.join(this.runDir(threadId, runId), "recovery-intent.json"), intent);
+    }
+    async getRecoveryIntent(threadId, runId) {
+        const intentPath = path.join(this.runDir(threadId, runId), "recovery-intent.json");
+        if (!(await fileExists(intentPath))) {
+            return null;
+        }
+        return readJson(intentPath);
+    }
+    async clearRecoveryIntent(threadId, runId) {
+        const intentPath = path.join(this.runDir(threadId, runId), "recovery-intent.json");
+        if (!(await fileExists(intentPath))) {
+            return;
+        }
+        await rm(intentPath, { force: true });
+    }
 }

package/dist/runtime/agent-runtime-adapter.d.ts

@@ -15,7 +15,6 @@ declare class RuntimeOperationTimeoutError extends Error {
 export declare class AgentRuntimeAdapter {
     private readonly options;
     constructor(options?: RuntimeAdapterOptions);
-    private canUseSimpleDeepAgentFastPath;
     private resolveBindingTimeout;
     private resolveStreamIdleTimeout;
     private withTimeout;
@@ -27,6 +26,7 @@ export declare class AgentRuntimeAdapter {
     private resolveModel;
     private buildToolNameMapping;
     private buildAgentMessages;
+    private buildInvocationRequest;
     private buildRawModelMessages;
     private resolveTools;
     private normalizeInterruptPolicy;
@@ -40,7 +40,15 @@ export declare class AgentRuntimeAdapter {
     route(input: MessageContent, primaryBinding: CompiledAgentBinding, secondaryBinding: CompiledAgentBinding, options?: {
         systemPrompt?: string;
     }): Promise<string>;
-    invoke(binding: CompiledAgentBinding, input: MessageContent, threadId: string, runId: string, resumePayload?: unknown, history?: TranscriptMessage[]): Promise<RunResult>;
-    stream(binding: CompiledAgentBinding, input: MessageContent, threadId: string, history?: TranscriptMessage[]): AsyncGenerator<RuntimeStreamChunk | string>;
+    invoke(binding: CompiledAgentBinding, input: MessageContent, threadId: string, runId: string, resumePayload?: unknown, history?: TranscriptMessage[], options?: {
+        context?: Record<string, unknown>;
+        state?: Record<string, unknown>;
+        files?: Record<string, unknown>;
+    }): Promise<RunResult>;
+    stream(binding: CompiledAgentBinding, input: MessageContent, threadId: string, history?: TranscriptMessage[], options?: {
+        context?: Record<string, unknown>;
+        state?: Record<string, unknown>;
+        files?: Record<string, unknown>;
+    }): AsyncGenerator<RuntimeStreamChunk | string>;
 }
 export { AgentRuntimeAdapter as RuntimeAdapter, AGENT_INTERRUPT_SENTINEL_PREFIX, AGENT_INTERRUPT_SENTINEL_PREFIX as INTERRUPT_SENTINEL_PREFIX, RuntimeOperationTimeoutError, };