pi-freeflow 1.38.2 → 1.38.3

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.38.3
+
+### Patch Changes
+
+- Absorb tool-call argument fragments arriving on terminal finish_reason chunks into buffered prefixes to prevent argument rotation and corrupted JSON loops. Add Reflection AI's Beam Free (1M context) to the OpenCode Zen lineup, and retire deprecated LL Alpha and Muse Spark 1.3 contributor free models.
+
 ## 1.38.2
 
 ### Patch Changes

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow
 
-> 37 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
+> 36 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
 
 Thin by design: a model list, a relay proxy, and a log. The host (`pi-ai`) handles thinking, normalization, and provider behavior.
 
@@ -16,7 +16,7 @@ Thin by design: a model list, a relay proxy, and a log. The host (`pi-ai`) handl
 
 | Feature | What it does | Cost |
 | :--- | :--- | :--- |
-| **37 free models** | 14 from OpenCode Zen, 13 from KiloCode Gateway, 2 from Cline, 8 from OVHcloud AI Endpoints, context windows up to 1M. Full list below. | **$0** |
+| **36 free models** | 13 from OpenCode Zen, 13 from KiloCode Gateway, 2 from Cline, 8 from OVHcloud AI Endpoints, context windows up to 1M. Full list below. | **$0** |
 | **Relay pool** | Route requests through your own Cloudflare Workers, Deno Deploy, and Vercel Edge relays. Traffic spreads across the pool, or stays on one sticky relay. A relay that rate-limits, times out, or drops the connection cools down while healthy ones take its traffic. | **$0** beyond your platforms' free tiers |
 | **Automatic fallback** | When every relay is cooling down, requests go direct to upstream instead of failing. | **$0** |
 | **Short model names** | Most models have a slash-free, colon-free alias, plus an optional `:effort` suffix for thinking depth. You type `freeflow/<name>`; the two Cline models have no alias and must be typed in full. | **$0** |
@@ -197,14 +197,14 @@ The same command set works identically in OMP and Pi:
 
 ---
 
-### 37 models, one command
+### 36 models, one command
 
 ```bash
 /model → freeflow → pick
 ```
 
 Every model specification is reconciled against [models.dev](https://models.dev/), [OpenRouter](https://openrouter.ai/), and OMP's built-in catalog, configured with the highest verified context, output ceiling, and reasoning capabilities across twin models.
-#### OpenCode Zen (14 models), Responses and Chat API
+#### OpenCode Zen (13 models), Responses and Chat API
 
 Good defaults for long coding sessions and agentic work.
 
@@ -212,7 +212,6 @@ Good defaults for long coding sessions and agentic work.
 | :--- | :--- | :--- | :--- | :--- | :--- |
 | `cat-jam-free` | Cat Jam | **256K** (262.144) | **131K** (131.072) | `low … max` | ❌ |
 | `muse-spark-1.2-contributor-free` | Meta Superintelligence Labs | **1M** (1.048.576) | **131K** (131.072) | `minimal … xhigh` | ✅ |
-| `muse-spark-1.3-contributor-free` | Meta Superintelligence Labs | **1M** (1.048.576) | **131K** (131.072) | `minimal … xhigh` | ✅ |
 | `mimo-v2.6-flash-free` | Xiaomi MiMo | **1M** (1.048.576) | **131K** (131.072) | `minimal … xhigh`\* | ✅ |
 | `nemotron-3.5-lightning-free` | NVIDIA | **1M** (1.000.000) | **262K** (262.144) | `minimal … xhigh` | ❌ |
 | `nemotron-3.5-super-vl-free` | NVIDIA | **1M** (1.000.000) | **131K** (131.072) | `minimal … xhigh` | ✅ |
@@ -221,7 +220,7 @@ Good defaults for long coding sessions and agentic work.
 | `space-bunny-free` | Stealth preview (lab undisclosed) | **1M** (1.048.576) | **512K** (524.288) | `low … max` | ✅ |
 | `longcat-2.5-preview-free` | Meituan LongCat | **1M** (1.000.000) | **131K** (131.072) | `minimal … max` | ✅ |
 | `glm-5.3-flash-free` | Zhipu AI | **1M** (1.000.000) | **32K** (32.000) | `minimal … max` | ✅ |
-| `ll-alpha-free` | Undisclosed | **262K** (262.144) | **64K** (65.536) | `low … max` | ❌ |
+| `beam-free` | Reflection AI | **1M** (1.048.576) | **131K** (131.072) | `low … max` | ❌ |
 | `exo-free` | Undisclosed | **1M** (1.048.576) | **131K** (131.072) | `high` | ✅ |
 | `deepseek-v4.1-flash-free` | DeepSeek | **1M** (1.000.000) | **384K** (384.000) | `minimal … max` | ✅ |
 
@@ -368,7 +367,7 @@ pnpm smoke       # verifies extensions/index.ts loads without crashing
 #### Project structure
 
 ```
-├── models.ts                # 37-model catalog definitions
+├── models.ts                # 36-model catalog definitions
 ├── index.ts                 # extension entry, lifecycle hooks
 ├── catalog.ts               # model catalog cache (24h disk)
 ├── proxy.ts                 # local proxy server (127.0.0.1:28180)

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.38.2",
+  "version": "1.38.3",
   "description": "Thin provider for OMP/Pi — model list + dumb relay proxy + log; host pi-ai owns thinking/normalization",
   "main": "extensions/index.ts",
   "types": "src/index.ts",

package/src/catalog.ts

@@ -124,6 +124,12 @@ export const DEAD_MODEL_IDS = new Set<string>([
  // answers 401 PAID_MODEL_AUTH_REQUIRED while the sibling z-ai/glm-5.3-flash
  // answers 200 keyless with the same request shape.
  "stepfun/step-5-preview-free",
+ // ll-alpha-free: decommissioned upstream (2026-10-17) — gone from live
+ // Zen /v1/models list, answers HTTP 410 "Model ll-alpha-free has been deprecated".
+ "ll-alpha-free",
+ // muse-spark-1.3-contributor-free: decommissioned upstream (2026-10-17) — gone from
+ // live Zen /v1/models list, answers HTTP 410 "Model muse-spark-1.3-contributor-free has been deprecated".
+ "muse-spark-1.3-contributor-free",
 ]);
 /**
  * Free-tier allowlist for anything entering the picker via network or stale disk.
@@ -163,7 +169,7 @@ export function sanitizeCatalogModels(models: RegisteredModel[]): RegisteredMode
 }
 /**
  * In-memory cache of currently active/available free models.
- * Initialized with all 37 verified models for 0ms instant availability.
+ * Initialized with all 36 verified models for 0ms instant availability.
  */
 let aliveCatalog: RegisteredModel[] = ALL_MODELS.map((m) => ({
  ...m,

package/src/models.ts

@@ -1,8 +1,8 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 37 verified free models (live-verified 2026-10-16):
- * - 14 OpenCode Zen models (2 Responses API + 12 Chat Completions)
+ * Defines the 36 verified free models (live-verified 2026-10-17):
+ * - 13 OpenCode Zen models (1 Responses API + 12 Chat Completions)
  * - 13 KiloCode Keyless Gateway models (OpenRouter format)
  * - 2 Cline direct-only models (per-user pool)
  * - 8 OVHcloud AI Endpoints models (keyless, direct-only)
@@ -59,24 +59,6 @@ export const OPENCODE_MODELS: ModelDef[] = [
    max: null,
   },
  },
- {
-  id: "muse-spark-1.3-contributor-free",
-  name: "Muse Spark 1.3 [OpenCode]",
-  reasoning: true,
-  contextWindow: 1_048_576,
-  maxTokens: 131_072,
-  api: "openai-responses",
- input: ["text", "image", "video"],
-  thinkingLevelMap: {
-   off: null,
-   minimal: "minimal",
-   low: "low",
-   medium: "medium",
-   high: "high",
-   xhigh: "xhigh",
-   max: null,
-  },
- },
  {
   id: "mimo-v2.6-flash-free",
   name: "MiMo V2.6 Flash [OpenCode]",
@@ -251,23 +233,20 @@ export const OPENCODE_MODELS: ModelDef[] = [
   },
  },
  {
-  // Added 2026-10-16 (issue #71 drift): Zen v1.19.2 added this free id.
-  // Specs agree across pi.dev and models.dev (262,144 ctx / 65,536 max,
-  // text-only) and the boundary probe matches: a marker at 90% depth is
-  // recalled at ~220K words and the gateway refuses ~250K words (400), with
-  // a silent no-recall at ~240K — the window ends right about there.
-  // maxTokens 65,536 published; the gateway accepted 131,072, which is
-  // acceptance, not a cap. Effort ladder: low/medium/high/xhigh/max probed
-  // 200 with visibly different reasoning lengths; `minimal` answers 200 too
-  // but stays hidden because the published ladder starts at low (same class
-  // as nemotron's tolerated-but-hidden `max`); `off` is null like everywhere.
-  // Chat-only (/v1/responses 400 protocol). Text-only: an image probe
-  // produced no answer.
-  id: "ll-alpha-free",
-  name: "LL Alpha [OpenCode]",
+  // Added 2026-10-17: Reflection AI's Beam 501B open-weight MoE model (23B active),
+  // added as a limited-time free model on OpenCode Zen (/zen/v1/models: beam-free).
+  // Live-probed 2026-10-17: 200 with stream:true and tool sextet.
+  // Context window: 1_048_576 tokens (1M), maxTokens: 131_072.
+  // Probed boundary: filler up to 900,000 words (~1.1M tokens) answers 200.
+  // Input: text-only (image probe answers 400 "Beam supports text input only").
+  // Wire format: Chat Completions (/v1/responses answers 400 ModelProtocolUnsupported).
+  // Reasoning effort ladder: minimal is rejected with 400 (unsupported_value),
+  // low/medium/high/xhigh/max all answer 200 with reasoning.
+  id: "beam-free",
+  name: "Beam Free [OpenCode]",
   reasoning: true,
-  contextWindow: 262_144,
-  maxTokens: 65_536,
+  contextWindow: 1_048_576,
+  maxTokens: 131_072,
   input: ["text"],
   thinkingLevelMap: {
    off: null,
@@ -722,7 +701,7 @@ export const MODEL_ALIASES: Record<string, string> = {
  "space-bunny": "space-bunny-free",
  "longcat-2.5-preview": "longcat-2.5-preview-free",
  "longcat": "longcat-2.5-preview-free",
- "ll-alpha": "ll-alpha-free",
+ "beam": "beam-free",
  "deepseek-v4.1-flash": "deepseek-v4.1-flash-free",
  // provider-prefixed short aliases (slash-normalized)
  "laguna-s-2.1:free": "poolside/laguna-s-2.1:free",
@@ -777,7 +756,7 @@ export const OVH_MODEL_IDS = new Set<string>([
   .map(([alias]) => alias),
 ]);
 /**
- * Combined list of all 37 static free models (canonical)
+ * Combined list of all 36 static free models (canonical)
  */
 export const ALL_MODELS: ModelDef[] = [...OPENCODE_MODELS, ...KILO_MODELS, ...CLINE_MODELS, ...OVH_MODELS];
 

package/src/stream-pipe.ts

@@ -442,6 +442,53 @@ function cloakStreamResponsesObject(resp: unknown, cloak: StreamCloakOptions): v
  (resp as Record<string, unknown>).output = kept;
 }
 
+/**
+ * Terminal chunk for chat choice: absorb any tool-call argument fragment
+ * riding the finish_reason chunk into the buffered prefix, then re-emit every
+ * buffered tool call's whole argument packet, repaired.
+ * Returns true if delta was mutated.
+ */
+function flushChatTerminalToolCalls(
+ d: Record<string, unknown>,
+ state: SseStreamCloakState,
+ cloak: StreamCloakOptions,
+ flushedIndices: Set<number>,
+): boolean {
+ if (state.chatArgsByIndex.size === 0) return false;
+
+ for (const tc of Array.isArray(d.tool_calls) ? d.tool_calls : []) {
+  if (!tc || typeof tc !== "object" || Array.isArray(tc)) continue;
+  const rec = tc as Record<string, unknown>;
+  const idx = typeof rec.index === "number" ? rec.index : 0;
+  const fn = rec.function;
+  const fnRec = fn && typeof fn === "object" && !Array.isArray(fn) ? (fn as Record<string, unknown>) : null;
+  if (fnRec && state.chatArgsByIndex.has(idx) && typeof fnRec.arguments === "string") {
+   state.chatArgsByIndex.set(idx, (state.chatArgsByIndex.get(idx) ?? "") + fnRec.arguments);
+  }
+ }
+
+ const flushed: unknown[] = [];
+ for (const [idx, args] of state.chatArgsByIndex) {
+  const name = state.chatNameByIndex.get(idx);
+  if (name === undefined) continue;
+  flushedIndices.add(idx);
+  flushed.push({ index: idx, type: "function", function: { name, arguments: repairToolArguments(name, args, cloak.argSchemas) } });
+ }
+ state.chatArgsByIndex.clear();
+ state.chatNameByIndex.clear();
+
+ if (flushed.length === 0) return false;
+
+ const remaining = (Array.isArray(d.tool_calls) ? d.tool_calls : []).filter((tc) => {
+  if (!tc || typeof tc !== "object" || Array.isArray(tc)) return true;
+  const rec = tc as Record<string, unknown>;
+  const idx = typeof rec.index === "number" ? rec.index : 0;
+  return !flushedIndices.has(idx);
+ });
+ d.tool_calls = [...remaining, ...flushed];
+ return true;
+}
+
 /**
  * Rewrite one Chat Completions SSE block: drop injected delta.tool_calls
  * (including nameless argument continuations via per-index tracking), restore
@@ -489,20 +536,8 @@ function rewriteChatBlock(
   // Indices flushed on this block: their arguments are final, so the
   // per-delta loop below must not buffer them a second time.
   const flushedIndices = new Set<number>();
-  if (c.finish_reason && state.chatArgsByIndex.size > 0) {
-   const flushed: unknown[] = [];
-   for (const [idx, args] of state.chatArgsByIndex) {
-    const name = state.chatNameByIndex.get(idx);
-    if (name === undefined) continue;
-    flushedIndices.add(idx);
-    flushed.push({ index: idx, type: "function", function: { name, arguments: repairToolArguments(name, args, cloak.argSchemas) } });
-   }
-   state.chatArgsByIndex.clear();
-   state.chatNameByIndex.clear();
-   if (flushed.length > 0) {
-    d.tool_calls = [...(Array.isArray(d.tool_calls) ? d.tool_calls : []), ...flushed];
-    changed = true;
-   }
+  if (c.finish_reason && flushChatTerminalToolCalls(d, state, cloak, flushedIndices)) {
+   changed = true;
   }
   if (!Array.isArray(d.tool_calls)) {
    if (Object.keys(d).length > 0) allDeltasEmpty = false;