test: address Codex review of property tests (PR 3)

- llm: generator now emits finish chunks (the finish-defaults property was
  vacuously green); add a property asserting streaming and one-shot assembly
  agree on usage and finish
- agent-loop: assert the synchronous burst batches into exactly one turn; add
  a mixed-schedule property (send/settle interleavings); recordStatus returns
  its disposer; per-run timeouts so a hang loses no seed
- session: randomize the noise/message interleaving (was a fixed alternation)
- tools: exclude non-finite doubles from generated numeric args (JSON-real)

packages/agent-loop/tests/properties.spec.ts

@@ -58,13 +58,14 @@ function nextIdle(ctx: Context, agent: LoopAgent): Promise<void> {
   })
 }
 
-/** Record every status transition for the legal-machine assertion. */
-function recordStatus(ctx: Context, agent: LoopAgent): string[] {
+/** Record every status transition for the legal-machine assertion. Returns
+ * the seen list plus a disposer for the listener (per the registry convention). */
+function recordStatus(ctx: Context, agent: LoopAgent): { seen: string[]; dispose: () => void } {
   const seen: string[] = []
-  ctx.on('agent/status', (subject, status) => {
+  const dispose = ctx.on('agent/status', (subject, status) => {
     if (subject === agent) seen.push(status)
   })
-  return seen
+  return { seen, dispose }
 }
 
 function userMessageTexts(agent: LoopAgent): string[] {
@@ -95,7 +96,7 @@ describe('agent loop scheduling properties', () => {
         const ctx = await harness()
         try {
           const agent = ctx.agentLoop.create('a', { model: 'mock' })
-          const trace = recordStatus(ctx, agent)
+          const { seen: trace } = recordStatus(ctx, agent)
           const idle = nextIdle(ctx, agent)
           // Send all in one synchronous tick: they queue before the loop wakes.
           for (const text of texts) agent.send([{ type: 'text', text }])
@@ -103,15 +104,14 @@ describe('agent loop scheduling properties', () => {
 
           // No message lost: every send appears as a user/message, in order.
           expect(userMessageTexts(agent)).toEqual(texts)
-          // Turn numbers strictly increase.
-          const turns = turnNumbers(agent)
-          for (let i = 1; i < turns.length; i++) expect(turns[i]!).toBeGreaterThan(turns[i - 1]!)
+          // A synchronous burst batches into exactly one turn.
+          expect(turnNumbers(agent)).toEqual([1])
           assertLegalStatusTrace(trace)
         } finally {
           await ctx.fiber.dispose()
         }
       },
-    ), { numRuns: 25 })
+    ), { numRuns: 25, timeout: 2000 })
   })
 
   it('sequential sends each get their own turn with increasing numbers', async () => {
@@ -133,6 +133,44 @@ describe('agent loop scheduling properties', () => {
           await ctx.fiber.dispose()
         }
       },
-    ), { numRuns: 20 })
+    ), { numRuns: 20, timeout: 2000 })
+  })
+
+  it('mixed schedule (send, optionally settle) loses no message and orders turns', async () => {
+    // Each step is a (text, settle?) pair: settle=true awaits idle before the
+    // next send (own turn); settle=false sends in the same tick (batches).
+    const stepArb = fc.record({ text: fc.string({ minLength: 1 }), settle: fc.boolean() })
+    await fc.assert(fc.asyncProperty(
+      fc.array(stepArb, { minLength: 1, maxLength: 6 }),
+      async (steps) => {
+        const ctx = await harness()
+        try {
+          const agent = ctx.agentLoop.create('a', { model: 'mock' })
+          // Capture an idle waiter before EACH send; the last one is guaranteed
+          // to resolve because the final send always triggers (or joins) a turn
+          // that ends idle. Awaiting an already-resolved waiter is a no-op, so a
+          // trailing settle step can't cause a hang.
+          let lastIdle: Promise<void> | undefined
+          for (const step of steps) {
+            const idle = nextIdle(ctx, agent)
+            lastIdle = idle
+            agent.send([{ type: 'text', text: step.text }])
+            if (step.settle) await idle
+          }
+          await lastIdle
+
+          // No message lost or reordered, regardless of batching.
+          expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text))
+          // Turn numbers are a strictly increasing 1..N prefix (N = turn count).
+          const turns = turnNumbers(agent)
+          expect(turns).toEqual(turns.map((_, i) => i + 1))
+          // Every message landed in some turn; turns never exceed messages.
+          expect(turns.length).toBeLessThanOrEqual(steps.length)
+          expect(turns.length).toBeGreaterThanOrEqual(1)
+        } finally {
+          await ctx.fiber.dispose()
+        }
+      },
+    ), { numRuns: 25, timeout: 3000 })
   })
 })

packages/llm/tests/properties.spec.ts

@@ -39,9 +39,12 @@ const chunkArb: fc.Arbitrary<StreamChunk> = indexArb.chain(index => fc.oneof(
     .map((r): StreamChunk => ({ type: 'tool-call-delta', index, id: CallId(r.id), argumentsDelta: r.argumentsDelta })),
   blockEndArb(index),
   fc.constant<StreamChunk>({ type: 'usage', usage: { inputTokens: 1, outputTokens: 1 } }),
+  fc.constant<StreamChunk>({ type: 'finish', reason: { kind: 'stop' } }),
+  fc.constant<StreamChunk>({ type: 'finish', reason: { kind: 'tool-calls' } }),
+  fc.string().map((message): StreamChunk => ({ type: 'finish', reason: { kind: 'error', message } })),
 ))
 
-/** A stream is a list of chunks; we add the terminal `finish` ourselves. */
+/** A stream is an arbitrary list of chunks (we do NOT force a terminal finish). */
 const streamArb = fc.array(chunkArb, { maxLength: 30 })
 
 /** Feed a fresh assembler, return it. */
@@ -115,11 +118,33 @@ describe('BlockAssembler properties', () => {
     }))
   })
 
-  it('result().finish defaults to stop when no finish chunk arrives', () => {
+  it('finish reflects the last finish chunk, or defaults to stop when none arrives', () => {
     fc.assert(fc.property(streamArb, (chunks) => {
       const a = feed(chunks)
-      const hasFinish = chunks.some(c => c.type === 'finish')
-      if (!hasFinish) expect(a.finish).toEqual({ kind: 'stop' })
+      const finishes = chunks.filter(c => c.type === 'finish')
+      if (finishes.length === 0) {
+        expect(a.finish).toEqual({ kind: 'stop' })
+      } else {
+        // last-write-wins: the assembler keeps the most recent finish reason.
+        const last = finishes[finishes.length - 1]
+        if (last?.type === 'finish') expect(a.finish).toEqual(last.reason)
+      }
+    }))
+  })
+
+  it('streaming and one-shot assembly agree on usage and finish', () => {
+    fc.assert(fc.property(streamArb, (chunks) => {
+      // Streaming consumer: push + flush as it goes.
+      const streaming = new BlockAssembler()
+      for (const chunk of chunks) {
+        streaming.push(chunk)
+        streaming.flushReady()
+      }
+      streaming.flushRemaining()
+      // One-shot consumer: push all, then read.
+      const oneShot = feed(chunks)
+      expect(streaming.usage).toEqual(oneShot.usage)
+      expect(streaming.finish).toEqual(oneShot.finish)
     }))
   })
 })

packages/session/tests/properties.spec.ts

@@ -74,19 +74,24 @@ describe('Session properties', () => {
     }))
   })
 
-  it('non-message events never affect derived history', () => {
+  it('non-message events never affect derived history (any interleaving)', () => {
     fc.assert(fc.property(
       fc.array(messageEventArb, { maxLength: 12 }),
       fc.array(nonMessageEventArb, { maxLength: 12 }),
-      (messages, noise) => {
-        // The same message events, with and without interleaved noise, derive
-        // the same history (noise is inserted at arbitrary positions).
+      // An arbitrary merge of the two streams that PRESERVES each stream's
+      // relative order (a random interleaving, not a fixed alternation).
+      fc.infiniteStream(fc.boolean()),
+      (messages, noise, pick) => {
         const clean = build(messages).deriveMessages()
         const interleaved: Appendable[] = []
-        const maxLen = Math.max(messages.length, noise.length)
-        for (let i = 0; i < maxLen; i++) {
-          if (i < noise.length) interleaved.push(noise[i]!)
-          if (i < messages.length) interleaved.push(messages[i]!)
+        let mi = 0
+        let ni = 0
+        const picker = pick[Symbol.iterator]()
+        while (mi < messages.length || ni < noise.length) {
+          // take from noise when chosen and available, else from messages
+          const takeNoise = ni < noise.length && (mi >= messages.length || picker.next().value === true)
+          if (takeNoise) { interleaved.push(noise[ni]!); ni++ }
+          else { interleaved.push(messages[mi]!); mi++ }
         }
         const withNoise = build(interleaved).deriveMessages()
         expect(withNoise).toEqual(clean)

packages/tools/tests/properties.spec.ts

@@ -47,7 +47,7 @@ function specArb(depth: number): fc.Arbitrary<SchemaSpec> {
 function valueForProp(prop: SchemaProp): fc.Arbitrary<unknown> {
   switch (prop.type) {
     case 'string': return prop.enum ? fc.constantFrom(...prop.enum) : fc.string()
-    case 'number': return fc.double({ noNaN: true })
+    case 'number': return fc.double({ noNaN: true, noDefaultInfinity: true })
     case 'boolean': return fc.boolean()
     case 'object': return prop.properties ? validArgsForSpec(prop.properties) : fc.constant({})
     case 'array': return prop.items ? fc.array(valueForProp(prop.items), { maxLength: 3 }) : fc.constant([])