Merge remote-tracking branch 'origin/codex/goal-session' into codex/commands

packages/ui/jsonrpc/README.md

@@ -8,7 +8,7 @@ The `jsonrpc` plugin serves newline-delimited JSON-RPC over stdio so out-of-proc
 
 ## Config
 
-There are no `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are runtime-only transport seams; production uses process stdio and `process.exit`.
+`maxTokensAsSuccess` defaults to `false`. Set it to `true` for evaluation hosts that distinguish an accepted, token-limited agent result from an infrastructure failure. `JsonRpcConfig.input`, `output`, and `exit` are runtime-only transport seams; production uses process stdio and `process.exit`.
 
 ## stdout is the protocol
 

packages/ui/jsonrpc/src/index.ts

@@ -22,8 +22,10 @@ export const name = 'jsonrpc'
 // Only the agent factory is required; initialize reads the optional LLM seam with ctx.get().
 export const inject = ['agents']
 
-/** Runtime-only test seams; no field is configurable from `cordis.yml`. */
+/** JSON-RPC deployment config plus runtime-only test seams. */
 export interface JsonRpcConfig {
+  /** Report max-token turn/subagent termination as a successful SDK result. */
+  maxTokensAsSuccess?: boolean
   /** Transport input override; production uses `process.stdin`. */
   input?: Readable
   /** Transport output override; production uses `process.stdout`. */
@@ -32,7 +34,9 @@ export interface JsonRpcConfig {
   exit?: (code: number) => void
 }
 
-export const Config: Schema<JsonRpcConfig> = Schema.object({})
+export const Config: Schema<JsonRpcConfig> = Schema.object({
+  maxTokensAsSuccess: Schema.boolean().default(false),
+})
 
 /**
  * Serve SDK requests over the configured streams. Effect disposal shuts down
@@ -41,6 +45,8 @@ export const Config: Schema<JsonRpcConfig> = Schema.object({})
  * owns root-context disposal for EOF and signals.
  */
 export function apply(ctx: Context, config: JsonRpcConfig): void {
+  // Cordis applies the schema default before invoking the plugin.
+  const resolvedConfig = config as JsonRpcConfig & { maxTokensAsSuccess: boolean }
   // The later transport callback must dispose this plugin's fiber, not its ambient context.
   const fiber = ctx.fiber
   /* v8 ignore next -- production stdio wiring; tests always inject the runtime seams */
@@ -51,7 +57,9 @@ export function apply(ctx: Context, config: JsonRpcConfig): void {
   const exit = config.exit ?? ((code: number): void => { process.exit(code) })
 
   const transport = new JsonRpcLineTransport(input, output)
-  const server = new HarnessSdkServer(ctx, transport)
+  const server = new HarnessSdkServer(ctx, transport, {
+    maxTokensAsSuccess: resolvedConfig.maxTokensAsSuccess,
+  })
 
   // Share one exit task and attempt flush and disposal independently before exiting.
   let exitTask: Promise<void> | undefined

packages/ui/jsonrpc/src/server.ts

@@ -57,7 +57,22 @@ function subagentParentOf(carrier: Scoped<SubagentService>): Agent {
   return carrierKeyOf(carrier) as Agent
 }
 
-/** SDK server whose subscriptions and created agents live until {@link shutdown}. */
+/** Deployment-specific status mapping for SDK turn and subagent outcomes. */
+export interface HarnessSdkServerOptions {
+  /** Report max-token termination as an accepted result instead of an infrastructure error. */
+  maxTokensAsSuccess?: boolean
+}
+
+function successStatus(reason: string, options: HarnessSdkServerOptions): 'ok' | 'error' {
+  if (reason === 'completed') return 'ok'
+  return reason === 'max-tokens' && options.maxTokensAsSuccess === true ? 'ok' : 'error'
+}
+
+/**
+ * SDK server over one booted harness context and transport peer. Construction
+ * subscribes to session, agent, and subagent lifecycle events until shutdown;
+ * reinitialization is unsupported.
+ */
 export class HarnessSdkServer {
   private cwd = process.cwd()
   private provider = 'deepseek'
@@ -72,7 +87,9 @@ export class HarnessSdkServer {
   constructor(
     private readonly ctx: Context,
     private readonly transport: JsonRpcTransportPeer,
+    private readonly options: HarnessSdkServerOptions = {},
   ) {
+    const serverOptions = this.options
     this.disposers.push(ctx.on('session/event', (session, event) => {
       if (event.type === 'turn/end') {
         const rec = this.sessions.get(String(session.id))
@@ -99,7 +116,7 @@ export class HarnessSdkServer {
         agentId: String(info.id),
         parentSessionId: String(parent.session.id),
         childSessionId: String(info.id),
-        status: info.stopReason === 'completed' ? 'ok' : 'error',
+        status: successStatus(info.stopReason, serverOptions),
         stopReason: info.stopReason,
         ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }),
       })
@@ -233,7 +250,7 @@ export class HarnessSdkServer {
 
   private finishedStatus(reason: TurnEndReason | undefined): 'ok' | 'error' {
     if (!reason) return 'error'
-    return reason.kind === 'completed' ? 'ok' : 'error'
+    return successStatus(reason.kind, this.options)
   }
 
   private hasAdapterFor(provider: string): boolean {

packages/ui/jsonrpc/tests/server.spec.ts

@@ -656,7 +656,7 @@ describe('HarnessSdkServer', () => {
         signal: new AbortController().signal,
       })
       const transport = new FakeTransport()
-      const server = new HarnessSdkServer(ctx, transport)
+      const server = new HarnessSdkServer(ctx, transport, { maxTokensAsSuccess: true })
 
       missedStartResult.resolve({ output: [], stopReason: 'max-tokens' })
       await missedStartRun.result
@@ -692,7 +692,7 @@ describe('HarnessSdkServer', () => {
           agentId: 'fallback-child-session',
           parentSessionId: 'fallback-parent',
           childSessionId: 'fallback-child-session',
-          status: 'error',
+          status: 'ok',
           stopReason: 'max-tokens',
           lastAssistantMessage: [],
         },
@@ -782,6 +782,24 @@ describe('HarnessSdkServer', () => {
     }
   })
 
+  it('can report max-token turn termination as an accepted evaluation result', async () => {
+    const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-max-tokens-success-'))
+    const ctx = await makeHarness(storageDir)
+    try {
+      const server = new HarnessSdkServer(ctx, new FakeTransport(), { maxTokensAsSuccess: true }) as unknown as {
+        finishedStatus(reason: unknown): 'ok' | 'error'
+        shutdown(): Promise<Record<string, never>>
+      }
+
+      expect(server.finishedStatus({ kind: 'max-tokens' })).toBe('ok')
+      expect(server.finishedStatus({ kind: 'error' })).toBe('error')
+      await server.shutdown()
+    } finally {
+      await ctx.fiber.dispose()
+      await rm(storageDir, { recursive: true, force: true })
+    }
+  })
+
   it('reports no adapter when the LLM service is absent', async () => {
     const ctx = new Context()
     try {