@poncho-ai/harness 0.52.0 → 0.52.1

package/.turbo/turbo-build.log

@@ -1,5 +1,5 @@
 
-> @poncho-ai/harness@0.52.0 build /home/runner/work/poncho-ai/poncho-ai/packages/harness
+> @poncho-ai/harness@0.52.1 build /home/runner/work/poncho-ai/poncho-ai/packages/harness
 > node scripts/embed-docs.js && tsup src/index.ts --format esm --dts
 
 [embed-docs] Generated poncho-docs.ts with 4 topics
@@ -8,9 +8,9 @@
 CLI tsup v8.5.1
 CLI Target: es2022
 ESM Build start
-ESM dist/index.js            536.18 KB
+ESM dist/index.js            536.24 KB
 ESM dist/isolate-F2PPSUL6.js 53.82 KB
-ESM ⚡️ Build success in 234ms
+ESM ⚡️ Build success in 235ms
 DTS Build start
-DTS ⚡️ Build success in 7615ms
-DTS dist/index.d.ts 92.18 KB
+DTS ⚡️ Build success in 8126ms
+DTS dist/index.d.ts 92.40 KB

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @poncho-ai/harness
 
+## 0.52.1
+
+### Patch Changes
+
+- [`0e8fff1`](https://github.com/cesr/poncho-ai/commit/0e8fff12aed9d5efe1821ed3560ead48a16113c1) Thanks [@cesr](https://github.com/cesr)! - Only send `temperature` to the model when the agent explicitly sets one. The harness previously defaulted to `temperature: 0.2` and always passed it to `streamText`, which returns a 400 ("`temperature` is deprecated for this model") on models that removed sampling params (Fable 5, Opus 4.7+). `temperature` is now omitted from the request when undefined — the same treatment `maxTokens` already had — and `defaultAgentDefinition` no longer hard-codes a `temperature` line into the generated frontmatter (pass `temperature` explicitly to set one).
+
 ## 0.52.0
 
 ### Minor Changes

package/dist/index.d.ts

@@ -737,7 +737,12 @@ interface DefaultAgentDefinitionOptions {
     modelProvider?: "anthropic" | "openai" | "openai-codex";
     /** Model name. Default: "claude-opus-4-5". */
     modelName?: string;
-    /** Sampling temperature. Default: 0.2. */
+    /**
+     * Sampling temperature. When unset, it is omitted from the generated
+     * frontmatter entirely and the harness sends no temperature (provider
+     * default). Newer models (Fable 5, Opus 4.7+) reject `temperature` — leave
+     * this unset for them.
+     */
     temperature?: number;
     /** Max tool-call steps per run. Default: 20. */
     maxSteps?: number;

package/dist/index.js

@@ -588,7 +588,8 @@ var defaultAgentDefinition = (opts = {}) => {
   const description = opts.description ?? DEFAULT_AGENT_DESCRIPTION;
   const modelProvider = opts.modelProvider ?? DEFAULT_MODEL_PROVIDER;
   const modelName = opts.modelName ?? DEFAULT_MODEL_NAME;
-  const temperature = opts.temperature ?? DEFAULT_TEMPERATURE;
+  const temperatureLine = opts.temperature !== void 0 ? `
+  temperature: ${opts.temperature}` : "";
   const maxSteps = opts.maxSteps ?? DEFAULT_MAX_STEPS;
   const timeout = opts.timeout ?? DEFAULT_TIMEOUT;
   return `---
@@ -597,8 +598,7 @@ id: ${id}
 description: ${description}
 model:
   provider: ${modelProvider}
-  name: ${modelName}
-  temperature: ${temperature}
+  name: ${modelName}${temperatureLine}
 limits:
   maxSteps: ${maxSteps}
   timeout: ${timeout}
@@ -10832,7 +10832,7 @@ ${textContent}` };
           cachedCoreMessages = [...cachedCoreMessages, ...newCoreMessages];
           convertedUpTo = messages.length;
           const coreMessages = cachedCoreMessages;
-          const temperature = agent.frontmatter.model?.temperature ?? 0.2;
+          const temperature = agent.frontmatter.model?.temperature;
           const maxTokens = agent.frontmatter.model?.maxTokens;
           const cachedMessages = skipTailCache ? coreMessages : addPromptCacheBreakpoints(
             coreMessages,
@@ -10860,7 +10860,7 @@ ${textContent}` };
             ...useStaticCache ? {} : { system: systemPrompt },
             messages: messagesForStep,
             tools: toolsForStep,
-            temperature,
+            ...typeof temperature === "number" ? { temperature } : {},
             abortSignal: input.abortSignal,
             ...typeof maxTokens === "number" ? { maxTokens } : {},
             experimental_telemetry: {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@poncho-ai/harness",
-  "version": "0.52.0",
+  "version": "0.52.1",
   "description": "Agent execution runtime - conversation loop, tool dispatch, streaming",
   "repository": {
     "type": "git",

package/src/default-agent.ts

@@ -26,7 +26,12 @@ export interface DefaultAgentDefinitionOptions {
   modelProvider?: "anthropic" | "openai" | "openai-codex";
   /** Model name. Default: "claude-opus-4-5". */
   modelName?: string;
-  /** Sampling temperature. Default: 0.2. */
+  /**
+   * Sampling temperature. When unset, it is omitted from the generated
+   * frontmatter entirely and the harness sends no temperature (provider
+   * default). Newer models (Fable 5, Opus 4.7+) reject `temperature` — leave
+   * this unset for them.
+   */
   temperature?: number;
   /** Max tool-call steps per run. Default: 20. */
   maxSteps?: number;
@@ -55,7 +60,10 @@ export const defaultAgentDefinition = (
   const description = opts.description ?? DEFAULT_AGENT_DESCRIPTION;
   const modelProvider = opts.modelProvider ?? DEFAULT_MODEL_PROVIDER;
   const modelName = opts.modelName ?? DEFAULT_MODEL_NAME;
-  const temperature = opts.temperature ?? DEFAULT_TEMPERATURE;
+  // Opt-in: only emit a `temperature:` line when explicitly provided, so the
+  // harness sends no temperature otherwise (newer models reject it).
+  const temperatureLine =
+    opts.temperature !== undefined ? `\n  temperature: ${opts.temperature}` : "";
   const maxSteps = opts.maxSteps ?? DEFAULT_MAX_STEPS;
   const timeout = opts.timeout ?? DEFAULT_TIMEOUT;
 
@@ -65,8 +73,7 @@ id: ${id}
 description: ${description}
 model:
   provider: ${modelProvider}
-  name: ${modelName}
-  temperature: ${temperature}
+  name: ${modelName}${temperatureLine}
 limits:
   maxSteps: ${maxSteps}
   timeout: ${timeout}

package/src/harness.ts

@@ -2907,7 +2907,12 @@ Code is wrapped in an async IIFE — use \`return\` to return a value to the too
         convertedUpTo = messages.length;
         const coreMessages = cachedCoreMessages;
 
-        const temperature = agent.frontmatter.model?.temperature ?? 0.2;
+        // Only send temperature when the agent explicitly set one. Newer
+        // models (Fable 5, Opus 4.7+) removed sampling params entirely and
+        // return a 400 ("`temperature` is deprecated for this model") on any
+        // value — forcing a default here broke them. Treated like maxTokens
+        // below: omitted from the request when undefined.
+        const temperature = agent.frontmatter.model?.temperature;
         const maxTokens = agent.frontmatter.model?.maxTokens;
         // Place the tail breakpoint before any untruncated tool-result so
         // we cache only the stable prefix when prior-run tool results are
@@ -2971,7 +2976,7 @@ Code is wrapped in an async IIFE — use \`return\` to return a value to the too
           ...(useStaticCache ? {} : { system: systemPrompt }),
           messages: messagesForStep,
           tools: toolsForStep,
-          temperature,
+          ...(typeof temperature === "number" ? { temperature } : {}),
           abortSignal: input.abortSignal,
           ...(typeof maxTokens === "number" ? { maxTokens } : {}),
           experimental_telemetry: {