Merge origin/master into feat/plan-mode

packages/core/tools/tests/code-mode.spec.ts

@@ -8,13 +8,12 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
 import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
 import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools'
 import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
-import { AgentId } from '@deepseek-ai/dsh-agent'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { Session, SessionId } from '@deepseek-ai/dsh-session'
 import type { SessionEventMap } from '@deepseek-ai/dsh-session'
 
 /**
- * Code Mode unit tier (per the RFC's plan): provider contribution per mode,
+ * Code Mode unit tier (per the Agent Note's plan): provider contribution per mode,
  * misconfiguration rejections, the run_code dispatch bridge (serialization,
  * abort, JSON normalization, error mapping, events, quiescence), and HMR
  * safety — all against an in-repo fake runtime, exactly the
@@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) {
 
 /** Mint one production-shaped agent scope that can register scoped tool policy. */
 async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> {
-  const agent = { id: AgentId(name) } as Agent
+  const agent = { id: SessionId(name) } as Agent
   let scope!: Scope
   await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) },
     { inject: ['tools', 'systemPrompt'] }))
@@ -488,7 +487,6 @@ describe('the run_code dispatch bridge', () => {
           additionalContexts: [{
             content: [{ type: 'text' as const, text: `context for ${exec.callId}` }],
             source: { kind: 'plugin' as const, plugin: 'test' },
-            envelope: 'raw' as const,
             meta: { callId: exec.callId },
           }],
         })
@@ -506,13 +504,11 @@ describe('the run_code dispatch bridge', () => {
       {
         content: [{ type: 'text', text: 'context for call-1:code:1' }],
         source: { kind: 'plugin', plugin: 'test' },
-        envelope: 'raw',
         meta: { callId: 'call-1:code:1' },
       },
       {
         content: [{ type: 'text', text: 'context for call-1:code:2' }],
         source: { kind: 'plugin', plugin: 'test' },
-        envelope: 'raw',
         meta: { callId: 'call-1:code:2' },
       },
     ])

packages/core/tools/tests/execution-mode.spec.ts

@@ -0,0 +1,136 @@
+/** Covers fail-closed per-call classification and model-schema isolation. */
+
+import { describe, expect, expectTypeOf, it } from 'vitest'
+import { Context } from 'cordis'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry, {
+  defineTool,
+  type ToolDefinition,
+  type ToolExecutionInput,
+  type ToolExecutionMode,
+} from '@deepseek-ai/dsh-tools'
+
+async function setup() {
+  const ctx = new Context()
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  return ctx
+}
+
+function exec(name: string, args: unknown): ToolExecutionInput {
+  return { callId: CallId('c1'), name, arguments: args }
+}
+
+describe('ToolRegistry.executionMode', () => {
+  it('returns parallel only for an explicit true classifier', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'safe',
+      description: 'parallel-safe',
+      parameters: {},
+      isConcurrencySafe: () => true,
+      async execute() { return [] },
+    }))
+    expect(ctx.tools.executionMode(exec('safe', {}))).toEqual({ kind: 'parallel' })
+  })
+
+  it('defaults to exclusive for a tool with no isConcurrencySafe declaration', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'plain',
+      description: 'no declaration',
+      parameters: {},
+      async execute() { return [] },
+    }))
+    expect(ctx.tools.executionMode(exec('plain', {}))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('returns exclusive for an unknown tool', async () => {
+    const ctx = await setup()
+    expect(ctx.tools.executionMode(exec('nonexistent', {}))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('returns exclusive when the classifier returns false for these args', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'rw',
+      description: 'read or write',
+      parameters: { mode: { type: 'string', required: true } },
+      isConcurrencySafe: args => args.mode === 'read',
+      async execute() { return [] },
+    }))
+    expect(ctx.tools.executionMode(exec('rw', { mode: 'read' }))).toEqual({ kind: 'parallel' })
+    expect(ctx.tools.executionMode(exec('rw', { mode: 'write' }))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('classifies invalid defineTool arguments as exclusive without throwing', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'needs-mode',
+      description: 'requires mode',
+      parameters: { mode: { type: 'string', required: true } },
+      isConcurrencySafe: () => true,
+      async execute() { return [] },
+    }))
+    expect(ctx.tools.executionMode(exec('needs-mode', {}))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('treats a throwing raw classifier as exclusive', async () => {
+    const ctx = await setup()
+    const raw: ToolDefinition = {
+      name: 'thrower',
+      description: 'classifier throws',
+      parameters: { type: 'object', properties: {} },
+      isConcurrencySafe() { throw new Error('boom') },
+      async execute() { return [] },
+    }
+    ctx.tools.register(raw)
+    expect(ctx.tools.executionMode(exec('thrower', {}))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('treats a truthy non-boolean raw result as exclusive', async () => {
+    const ctx = await setup()
+    const raw = {
+      name: 'truthy',
+      description: 'classifier returns a truthy string',
+      parameters: { type: 'object', properties: {} },
+      isConcurrencySafe() { return 'yes' },
+      async execute() { return [] },
+    } as unknown as ToolDefinition
+    ctx.tools.register(raw)
+    expect(ctx.tools.executionMode(exec('truthy', {}))).toEqual({ kind: 'exclusive' })
+  })
+
+  it('passes parsed arguments directly to a raw definition', async () => {
+    const ctx = await setup()
+    let seen: unknown
+    ctx.tools.register({
+      name: 'raw-safe',
+      description: 'raw',
+      parameters: { type: 'object', properties: {} },
+      isConcurrencySafe(args) { seen = args; return true },
+      async execute() { return [] },
+    })
+    expect(ctx.tools.executionMode(exec('raw-safe', { anything: 1 }))).toEqual({ kind: 'parallel' })
+    expect(seen).toEqual({ anything: 1 })
+  })
+
+  it('isConcurrencySafe never reaches the model-facing schemas() projection', async () => {
+    const ctx = await setup()
+    ctx.tools.register(defineTool({
+      name: 'safe',
+      description: 'parallel-safe',
+      parameters: { x: { type: 'string', required: true } },
+      isConcurrencySafe: () => true,
+      async execute() { return [] },
+    }))
+    const schema = ctx.tools.schemas()[0] as unknown as Record<string, unknown>
+    expect(Object.keys(schema).sort()).toEqual(['description', 'name', 'parameters'])
+    expect(schema.isConcurrencySafe).toBeUndefined()
+  })
+
+  it('ToolExecutionMode is the object-tagged union', () => {
+    expectTypeOf<ToolExecutionMode>().toEqualTypeOf<{ kind: 'parallel' } | { kind: 'exclusive' }>()
+  })
+})

packages/core/tools/tests/gen-tool-catalog.spec.ts

@@ -49,6 +49,19 @@ describe('gen-tool-catalog collectToolCatalog', () => {
     expect(bash?.source).toBe('packages/bash/tool-bash/src/index.ts')
   })
 
+  it('harvests search tools without depending on the generator process PATH', async () => {
+    const oldPath = process.env.PATH
+    try {
+      process.env.PATH = ''
+      const catalog = await collectToolCatalog()
+      const search = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-fs-search')
+      expect(search?.schemas.map(s => s.name).sort()).toEqual(['glob', 'grep'])
+    } finally {
+      if (oldPath === undefined) delete process.env.PATH
+      else process.env.PATH = oldPath
+    }
+  })
+
   it('records the shipped `subagent_fork` alias in a note (config-driven tool name)', async () => {
     // `tool-subagent`'s registered name is the load-time `toolName` config, so the shipped
     // agents surface this one package as both `subagent` and `subagent_fork`.

packages/core/tools/tests/properties.spec.ts

@@ -1,8 +1,8 @@
 /**
- * Property-based tests for the tool-schema DSL (the property-testing RFC), including
+ * Property-based tests for the tool-schema DSL (the property-testing Agent Note), including
  * the the property-testing ↔ runtime-validation composition composition: generated args that satisfy a SchemaSpec must
  * pass validateArgs, and targeted corruptions must be rejected. This closes the
- * validator/InferArgs drift risk noted in the arg-validation RFC.
+ * validator/InferArgs drift risk noted in the arg-validation Agent Note.
  */
 
 import { describe, expect, it } from 'vitest'

packages/core/tools/tests/scoped.spec.ts

@@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
 import ToolRegistry from '@deepseek-ai/dsh-tools'
 import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools'
-import type { Agent, AgentId } from '@deepseek-ai/dsh-agent'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+
 import { CallId } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock } from '@deepseek-ai/dsh-llm'
+import type { SessionId } from '@deepseek-ai/dsh-session'
 
 /** Mount the registry (with its systemPrompt dependency) on a fresh context. */
 async function mount(): Promise<Context> {
@@ -20,7 +22,7 @@ async function mount(): Promise<Context> {
 
 /** Mint a scope whose key doubles as a minimal Agent-like object. */
 async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> {
-  const key = { id: name as AgentId } as Agent
+  const key = { id: name as SessionId } as Agent
   let scope!: Scope
   // The scoped context resolves services through the MINTING plugin's
   // dependency chain — the minter must inject what scope holders will reach
@@ -62,7 +64,7 @@ describe('scoped tool registration', () => {
   it('files a scoped tool in its layer: visible/executable for that scope only', async () => {
     const ctx = await mount()
     const { scope, key } = await mintAgentScope(ctx, 'a')
-    const other = { id: 'other' as AgentId } as Agent
+    const other = { id: 'other' as SessionId } as Agent
     ctx.tools.register(tool('shared'))
     scope.ctx.tools.register(tool('mine'))
 
@@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => {
   it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => {
     const ctx = await mount()
     const { scope, key } = await mintAgentScope(ctx, 'a')
-    const other = { id: 'other' as AgentId } as Agent
+    const other = { id: 'other' as SessionId } as Agent
     ctx.tools.register(tool('t'))
 
     const seen: (string | undefined)[] = []
@@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => {
   it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => {
     const ctx = await mount()
     const { scope, key } = await mintAgentScope(ctx, 'a')
-    const other = { id: 'other' as AgentId } as Agent
+    const other = { id: 'other' as SessionId } as Agent
     let bodyCalls = 0
     ctx.tools.register({
       ...tool('t'),
@@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => {
   it('uses one input snapshot for the normalized error shell', async () => {
     const ctx = await mount()
     const { scope, key } = await mintAgentScope(ctx, 'accepted')
-    const driftAgent = { id: 'drift' as AgentId } as Agent
+    const driftAgent = { id: 'drift' as SessionId } as Agent
     ctx.tools.register(tool('parent'))
     ctx.tools.register(tool('t'))
     let parent!: ToolExecutionToken
@@ -580,13 +582,18 @@ describe('scoped execution dispatch', () => {
     ctx.on('tools/result', () => {
       throw { toString: () => { throw new Error('coercion trap') } }
     })
+    ctx.on('tools/result', () => Promise.reject(new Error('async observer failure')) as never)
     ctx.on('tools/result', (_exec, result) => { seen.push(result.isError) })
 
     const result = await ctx.tools.execute({ callId: CallId('final'), name: 't', arguments: {}, agent: key })
+    await Promise.resolve()
     expect(result).toMatchObject({ isError: true, content: [{ type: 'text', text: 'outer failure' }] })
     expect(seen).toEqual([true, true])
     expect(dispatchModes).toEqual(['emit'])
-    expect(warn).toHaveBeenCalledOnce()
-    expect(String(warn.mock.calls[0]?.[0])).toContain('<unprintable thrown value>')
+    expect(warn).toHaveBeenCalledTimes(2)
+    expect(warn.mock.calls.map(call => String(call[0]))).toEqual(expect.arrayContaining([
+      expect.stringContaining('<unprintable thrown value>'),
+      expect.stringContaining('async observer failure'),
+    ]))
   })
 })

packages/core/tools/tests/tools.spec.ts

@@ -384,7 +384,7 @@ describe('ToolRegistry', () => {
       parameters: {},
       async execute(_args, exec) {
         exec.deferContext({ content: [{ type: 'text', text: 'nested-1' }], source: { kind: 'plugin', plugin: 'nested-1' }, meta: { n: 1 } })
-        exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' }, envelope: 'raw' })
+        exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' } })
         return [{ type: 'text', text: 'done' }]
       },
     }))
@@ -418,7 +418,6 @@ describe('ToolRegistry', () => {
       { kind: 'plugin', plugin: 'post' },
     ])
     expect(result.additionalContexts?.[0]?.meta).toEqual({ n: 1 })
-    expect(result.additionalContexts?.[1]?.envelope).toBe('raw')
   })
 
   it('keeps deferred contexts when a composite tool throws, but drops them when the outer call is blocked', async () => {
@@ -1174,7 +1173,7 @@ describe('ToolRegistry.get', () => {
   })
 })
 
-describe('validateArgs (the runtime-validation RFC, part 1)', () => {
+describe('validateArgs (the runtime-validation Agent Note, part 1)', () => {
   it('returns [] for valid args and is total over malformed input', () => {
     const spec = {
       path: { type: 'string', required: true },
@@ -1274,7 +1273,7 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => {
   })
 })
 
-describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
+describe('defineTool validation (the runtime-validation Agent Note, part 1)', () => {
   it('returns an isError result with the violations when the model sends bad args', async () => {
     const ctx = await setup()
     ctx.tools.register(defineTool({