pi-freeflow 1.36.0 → 1.36.3

package/CHANGELOG.md

@@ -1,5 +1,50 @@
 # Changelog
 
+## 1.36.3
+
+### Patch Changes
+
+- Restore OpenCode free models following upstream endpoint and gate migration
+
+  OpenCode free models were failing with HTTP 403 FreeTierError after upstream deprecated the older endpoint and moved free inference traffic to the v1 inference gateway. Upstream also requires public authorization and non-empty schema declarations on compatibility tools.
+
+  Requests now route to the active endpoint with the required public credentials and schema declarations, restoring free model access across both direct connections and deployed relays.
+
+## 1.36.2
+
+### Patch Changes
+
+- Auto-recover OpenCode Zen 403 FreeTierError: when upstream OpenCode Zen refuses a session with `403 FreeTierError` ("OpenCode's free tier can only be used from within OpenCode"), the local proxy now catches the gate error in-flight and transparently fails over to a healthy KiloCode fallback model on the same wire API, rather than bubbling the 403 back to the coding agent.
+- Prune decommissioned `ling-3.1-flash-free` from the active catalog and add it to the exclusion list, locking the verified catalog to 36 models.
+- Update OpenCode version fallback to 1.19.0.
+
+## 1.36.1
+
+### Patch Changes
+
+- Fix tool calls being rejected as invalid JSON on every model, and tool names coming back under a name the host never registered.
+
+  - A tool whose arguments arrived carrying the tail of the previous call is now repaired for **every** tool, not only tools declaring a nested object or array. The most-used tool, the shell command tool, declares nothing but scalars, so it was never repaired at all — the call was rejected and the turn looped on the same broken payload.
+  - Buffered tool arguments are released when a stream ends without its normal ending event, instead of being dropped: a truncated stream used to deliver a call with no arguments at all.
+  - The tool-name restore now runs on the Cline and OVH lanes too. Those lanes send a renamed tool upstream but never took it back, so a client received a call for a tool it does not have.
+  - A caller that declares both file-pattern and semantic-search tools now keeps both. The two share a name across hosts but are different tools, and collapsing them handed the model one tool under the other's shape.
+  - A truncated number is refused rather than completed, and an inner object is never promoted over the wrapper that declares it.
+  - A non-streaming answer from the Kilo lane is repaired like a streamed one.
+  - The free tier is the only lane that renames a tool now. The other lanes carry
+    the caller's own names in both directions, so the host dispatches natively
+    instead of waiting for a name that never comes back.
+  - Tools that declare an optional value as "value or nothing" are repaired
+    again. Both hosts describe optional settings that way when a tool is declared
+    strictly, and reading that as "always send it" silently switched repair off
+    for the shell command tool — the one that matters most.
+  - A model answering an optional setting with the word "none" as text, instead of
+    leaving it empty, is now corrected rather than rejected. Affects roughly one
+    model in nine.
+  - A streamed Anthropic-format answer is now repaired and mapped like the other
+    two formats. It was forwarded untouched.
+  - A stream that ends without an answer says so, instead of reporting an empty
+    successful one.
+
 ## 1.36.0
 
 ### Minor Changes

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.36.0",
+  "version": "1.36.3",
   "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

@@ -105,6 +105,12 @@ export const DEAD_MODEL_IDS = new Set<string>([
  "cline-free/deepseek-v4.1-flash",
  "cline-free/kimi-k3",
  "cline-free/solar-pro4",
+ // ling-3.1-flash-free: removed from upstream free docs (2026-10-15).
+ "ling-3.1-flash-free",
+ // inclusionai/ling-3.1-flash: demoted to paid on Kilo (2026-10-15) — answers 401 PAID_MODEL_AUTH_REQUIRED.
+ "inclusionai/ling-3.1-flash",
+ // ovh-free/Mistral-7B-Instruct-v0.3: removed upstream by OVH (2026-10-15) — answers 404 no route matched.
+ "ovh-free/Mistral-7B-Instruct-v0.3",
 ]);
 /**
  * Free-tier allowlist for anything entering the picker via network or stale disk.

package/src/config.ts

@@ -2,7 +2,7 @@
  * Configuration and path resolution for pi-freeflow
  */
 
-import { createHash, randomBytes, randomUUID } from "node:crypto";
+import { createHash, randomBytes } from "node:crypto";
 import { homedir } from "node:os";
 import path from "node:path";
 import { fileURLToPath } from "node:url";
@@ -21,7 +21,7 @@ try {
 export { PKG_VERSION };
 
 // ── Upstream endpoints ──────────────────────────────────────────────
-export const UPSTREAM_OPENCODE = "https://opencode.ai/zen";
+export const UPSTREAM_OPENCODE = "https://opencode.ai/inference";
 export const KILO_CHAT_URL = "https://api.kilo.ai/api/gateway/chat/completions";
 export const KILO_RESPONSES_URL = "https://api.kilo.ai/api/gateway/responses";
 export const OPENCODE_API_URL = `${UPSTREAM_OPENCODE}/v1`;
@@ -74,7 +74,7 @@ export const PORT = resolvePort();
 // OPENCODE_VERSION_FLOOR pins the minimum; OPENCODE_VERSION_FALLBACK is the
 // last-known-good npm version used when the live lookup is stale/offline.
 export const OPENCODE_VERSION_FLOOR = "1.17.0";
-export const OPENCODE_VERSION_FALLBACK = "1.18.34";
+export const OPENCODE_VERSION_FALLBACK = "1.19.0";
 /** Live npm lookup TTL: 6h — within one window the cached UA is reused. */
 export const OPENCODE_VERSION_TTL_MS = 6 * 60 * 60 * 1_000;
 /** Env override: exact `opencode/<version>` UA (or bare version) for tests/pins. */
@@ -250,14 +250,19 @@ export const OPENCODE_SESSION = createOpenCodeSessionId();
 
 export function opencodeHeaders(): Record<string, string> {
  const sessionId = OPENCODE_SESSION;
+ // Real OpenCode CLI (captured 2.0.28) does NOT send x-opencode-request on
+ // /inference/v1. Emitting msg_* there is treated as a non-OpenCode client and
+ // returns 403 FreeTierError — keep the helper for ID-shape tests, but omit
+ // the header on the wire.
  return {
+  Authorization: "Bearer public",
   "User-Agent": getOpenCodeUserAgent(),
   "x-opencode-client": OPENCODE_CLIENT,
   "x-opencode-project": OPENCODE_PROJECT,
   "x-opencode-session": sessionId,
   "x-opencode-session-id": sessionId,
   "x-session-affinity": sessionId,
-  "x-opencode-request": createOpenCodeRequestId(),
+  "x-session-id": sessionId,
  };
 }
 

package/src/index.ts

@@ -185,6 +185,7 @@ export default async function(pi: ExtensionAPI): Promise<void> {
    buildProviderConfig(models, actualPort),
   );
  };
+ registerCatalog(registeredCatalog);
  const ensureDaemon = async (ui?: ExtensionUIContext): Promise<void> => {
   const reattach = (port: number): void => {
    if (port !== actualPort) {

package/src/models.ts

@@ -1,18 +1,18 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 37 verified free models (live-verified 2026-10-13):
- * - 11 OpenCode Zen models (2 Responses API + 9 Chat Completions)
- * - 15 KiloCode Keyless Gateway models (OpenRouter format)
+ * Defines the 34 verified free models (live-verified 2026-10-15):
+ * - 10 OpenCode Zen models (2 Responses API + 8 Chat Completions)
+ * - 14 KiloCode Keyless Gateway models (OpenRouter format)
  * - 2 Cline direct-only models (per-user pool)
- * - 9 OVHcloud AI Endpoints models (keyless, direct-only)
+ * - 8 OVHcloud AI Endpoints models (keyless, direct-only)
  */
 
 import type { ModelDef, ThinkingLevelMap, Upstream } from "./types.ts";
 
 /**
  * OpenCode Zen free models verified against the live catalog and inference APIs.
- * Endpoint: https://opencode.ai/zen/v1
+ * Endpoint: https://opencode.ai/inference/v1
  */
 export const OPENCODE_MODELS: ModelDef[] = [
  {
@@ -200,23 +200,6 @@ export const OPENCODE_MODELS: ModelDef[] = [
   max: null,
  },
  },
- {
-  id: "ling-3.1-flash-free",
-  name: "Ling 3.1 Flash Free [OpenCode]",
-  reasoning: true,
-  contextWindow: 262_144,
-  maxTokens: 32_768,
-  input: ["text"],
-  thinkingLevelMap: {
-   off: null,
-   minimal: "minimal",
-   low: "low",
-   medium: "medium",
-   high: "high",
-   xhigh: "xhigh",
-   max: "max",
-  },
- },
 ];
 
 /**
@@ -386,17 +369,6 @@ export const KILO_MODELS: ModelDef[] = [
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
  },
- {
-  // Added 2026-10-07: live on Kilo free list (isFree:true, 0/0 pricing, 262K ctx)
-  id: "inclusionai/ling-3.1-flash",
-  name: "Ling 3.1 Flash [Kilo]",
-  reasoning: true,
-  contextWindow: 262_144,
-  maxTokens: 32_768,
-  input: ["text"],
-  thinkingFormat: "openrouter",
-  thinkingLevelMap: KILO_REASONING_MAP,
- },
 ];
 
 /**
@@ -569,14 +541,6 @@ export const OVH_MODELS: ModelDef[] = [
   maxTokens: 16_384,
   input: ["text", "image"],
  },
- {
-  id: "ovh-free/Mistral-7B-Instruct-v0.3",
-  name: "Mistral 7B Instruct v0.3 [OVH]",
-  reasoning: false,
-  contextWindow: 65_536,
-  maxTokens: 65_536,
-  input: ["text"],
- },
  {
   id: "ovh-free/Meta-Llama-3_3-70B-Instruct",
   name: "Meta Llama 3.3 70B Instruct [OVH]",
@@ -625,8 +589,6 @@ export const MODEL_ALIASES: Record<string, string> = {
  "longcat-2.5-preview": "longcat-2.5-preview-free",
  "longcat": "longcat-2.5-preview-free",
  "step-5-preview": "step-5-preview-free",
- "ling-3.1-flash": "ling-3.1-flash-free",
- "ling-3.1-flash:kilo": "inclusionai/ling-3.1-flash",
  // provider-prefixed short aliases (slash-normalized)
  "laguna-s-2.1:free": "poolside/laguna-s-2.1:free",
  "laguna-xs-2.1:free": "poolside/laguna-xs-2.1:free",
@@ -640,7 +602,6 @@ export const MODEL_ALIASES: Record<string, string> = {
 "qwen3.6-27b": "ovh-free/Qwen3.6-27B",
 "qwen3.8-27b": "ovh-free/Qwen3.8-27B",
 "mistral-small-3.2": "ovh-free/Mistral-Small-3.2-24B-Instruct-2506",
-"mistral-7b-v0.3": "ovh-free/Mistral-7B-Instruct-v0.3",
 "llama-3.3-70b": "ovh-free/Meta-Llama-3_3-70B-Instruct",
 };
 

package/src/opencode-fingerprint.ts

@@ -26,6 +26,7 @@
  * per-request map (never module-global).
  */
 import {
+ COMPAT_FINGERPRINT_SCHEMAS,
  COMPAT_TOOL_DESCRIPTION,
  OMP_FINGERPRINT_DEFS,
  OPENCODE_FINGERPRINT_TOOLS,
@@ -105,7 +106,7 @@ export function isPlaceholderToolName(name: unknown): boolean {
  * functions below.
  */
 function fingerprintFill(name: FingerprintToolName, omp: boolean): { description: string; schema: Record<string, unknown> } {
- if (!omp || name === "edit") return { description: COMPAT_TOOL_DESCRIPTION, schema: { type: "object", properties: {} } };
+ if (!omp || name === "edit") return { description: COMPAT_TOOL_DESCRIPTION, schema: COMPAT_FINGERPRINT_SCHEMAS[name] };
  const def = OMP_FINGERPRINT_DEFS[name];
  return { description: def.description, schema: { ...(def.parameters as Record<string, unknown>) } };
 }
@@ -557,8 +558,11 @@ export function enforceOpencodeFingerprint(
  const injected = missing.filter((n) => !ompLike || n === "edit");
  const injectedReal = ompLike ? missing.filter((n) => n !== "edit") : [];
 
+ // Zen alone asks for a rename: its free-tier gate looks for the sextet name
+ // `glob`, so a Pi caller that sent `find` needs it renamed into that slot.
+ // Every other lane accepts the caller's own names untouched.
  if (Array.isArray(body.tools)) {
-  body.tools = translateToolsForPath(body.tools, pathname);
+  body.tools = translateToolsForPath(body.tools, pathname, { forFingerprint: true });
  }
 
  const before = Array.isArray(body.tools) ? body.tools.length : 0;
@@ -881,10 +885,14 @@ export function sseToResponsesJson(
   }
  } catch { }
 
+ // Nothing in the stream carried a response object: the upstream turn ended
+ // without one. Report that honestly — a `completed` answer with zero output
+ // reads to the host as "the model chose to say nothing", which is a
+ // different (and wrong) claim than "the stream was cut".
  return {
   id: "resp_fallback",
   object: "response",
-  status: "completed",
+  status: "incomplete",
   output: [],
  };
 }
@@ -895,8 +903,11 @@ export function sseToResponsesJson(
  * never see tool_use: stray placeholder input folds to text, matching the
  * SSE aggregator fallback below. Ids ride verbatim; `input` is repaired
  * against the caller's declared schema when the emitted shape cannot be right.
+ *
+ * Exported so the streaming cloak applies these identical rules to a `message`
+ * frame that arrives mid-stream, instead of forwarding it verbatim.
  */
-function cloakMessagesContent(
+export function cloakMessagesContent(
  msg: unknown,
  callerHadTools: boolean,
  caseRestore?: CaseRestoreMap,
@@ -1089,7 +1100,79 @@ export function convertSseToJson(
    return JSON.stringify(sseToMessagesJson(trimmed, callerHadTools, caseRestore, findGlob, injected, argSchemas));
   }
   return JSON.stringify(sseToChatCompletionJson(trimmed, callerHadTools, caseRestore, findGlob, injected, argSchemas));
+ } catch (error) {
+  // Every caller has already committed to `content-type: application/json`
+  // by the time this runs, so handing back the raw SSE bytes would deliver a
+  // parse error with no diagnosis. Say what happened, and keep the payload
+  // reachable under `raw` so nothing is silently destroyed.
+  return JSON.stringify({
+   error: {
+    message: "upstream stream could not be aggregated into a JSON answer",
+    detail: String(error).slice(0, 300),
+    raw: sseText.slice(0, 2000),
+   },
+  });
+ }
+}
+
+/**
+ * Repair the tool calls inside an already-JSON answer body.
+ *
+ * A lane that passes the caller's `stream` through untouched (Kilo) answers a
+ * non-streaming caller with a plain `chat.completion` / `response` object, not
+ * SSE. The SSE aggregators above never see that body, so the malformed
+ * arguments reached the host unrepaired on exactly the requests that asked for
+ * no stream. Repairs each call in place and re-serializes only when something
+ * actually changed, so a well-formed answer keeps its byte-identical body.
+ * Returns the input string untouched when it is not JSON or has no tool calls.
+ */
+export function repairJsonToolArguments(
+ bodyText: string,
+ pathname: string,
+ argSchemas: ReadonlyMap<string, Record<string, unknown>> | undefined,
+): string {
+ if (argSchemas === undefined || argSchemas.size === 0 || !bodyText.trimStart().startsWith("{")) return bodyText;
+ let parsed: unknown;
+ try {
+  parsed = JSON.parse(bodyText);
  } catch {
-  return sseText;
+  return bodyText;
+ }
+ if (parsed === null || typeof parsed !== "object" || Array.isArray(parsed)) return bodyText;
+ const body = parsed as Record<string, unknown>;
+ let changed = false;
+ const repairCall = (name: string, args: string): string => {
+  const repaired = repairToolArguments(name, args, argSchemas);
+  if (repaired !== args) changed = true;
+  return repaired;
+ };
+ if (pathname.endsWith("/responses")) {
+  const output = body.output;
+  if (!Array.isArray(output)) return bodyText;
+  for (const item of output) {
+   if (item === null || typeof item !== "object" || Array.isArray(item)) continue;
+   const rec = item as Record<string, unknown>;
+   if (rec.type !== "function_call" || typeof rec.name !== "string" || typeof rec.arguments !== "string") continue;
+   rec.arguments = repairCall(rec.name, rec.arguments);
+  }
+ } else {
+  const choices = body.choices;
+  if (!Array.isArray(choices)) return bodyText;
+  for (const choice of choices) {
+   if (choice === null || typeof choice !== "object" || Array.isArray(choice)) continue;
+   const message = (choice as Record<string, unknown>).message;
+   if (message === null || typeof message !== "object" || Array.isArray(message)) continue;
+   const calls = (message as Record<string, unknown>).tool_calls;
+   if (!Array.isArray(calls)) continue;
+   for (const call of calls) {
+    if (call === null || typeof call !== "object" || Array.isArray(call)) continue;
+    const fn = (call as Record<string, unknown>).function;
+    if (fn === null || typeof fn !== "object" || Array.isArray(fn)) continue;
+    const fnRec = fn as Record<string, unknown>;
+    if (typeof fnRec.name !== "string" || typeof fnRec.arguments !== "string") continue;
+    fnRec.arguments = repairCall(fnRec.name, fnRec.arguments);
+   }
+  }
  }
+ return changed ? JSON.stringify(body) : bodyText;
 }

package/src/probe.ts

@@ -1,4 +1,4 @@
-import { opencodeHeaders } from "./config.ts";
+import { OPENCODE_API_URL, opencodeHeaders } from "./config.ts";
 import { ensureChatFingerprintTools } from "./opencode-fingerprint.ts";
 
 /**
@@ -17,7 +17,7 @@ export interface RelayProbeOptions {
  /**
   * Probe mode:
   * - "models" (default): GET /v1/models (reachability probe)
-  * - "chat": POST /zen/v1/chat/completions (verifies free tier inference & spoofing)
+ * - "chat": POST /inference/v1/chat/completions (verifies free tier inference & spoofing)
   */
  endpoint?: "models" | "chat";
  /** Model to use for chat probe (defaults to "nemotron-3.5-lightning-free") */
@@ -76,7 +76,7 @@ async function probeRelayOnce(
 
   if (isDirectOpenCode) {
    if (isChat) {
-    fetchUrl = "https://opencode.ai/zen/v1/chat/completions";
+    fetchUrl = `${OPENCODE_API_URL}/chat/completions`;
     method = "POST";
     headers["content-type"] = "application/json";
     const probePayload: Record<string, unknown> = {
@@ -88,15 +88,15 @@ async function probeRelayOnce(
     ensureChatFingerprintTools(probePayload);
     body = JSON.stringify(probePayload);
    } else {
-    fetchUrl = "https://opencode.ai/zen/v1/models";
+    fetchUrl = `${OPENCODE_API_URL}/models`;
    }
   } else {
    if (isChat) {
-    fetchUrl = `${cleanUrl}/zen/v1/chat/completions`;
+    fetchUrl = `${cleanUrl}/inference/v1/chat/completions`;
     method = "POST";
     headers["content-type"] = "application/json";
     headers["x-relay-target"] = "https://opencode.ai";
-    headers["x-relay-path"] = "/zen/v1/chat/completions";
+    headers["x-relay-path"] = "/inference/v1/chat/completions";
     const probePayload: Record<string, unknown> = {
      model: opts?.model || "nemotron-3.5-lightning-free",
      max_tokens: 1,
@@ -108,7 +108,7 @@ async function probeRelayOnce(
    } else {
     fetchUrl = `${cleanUrl}/v1/models`;
     headers["x-relay-target"] = "https://opencode.ai";
-    headers["x-relay-path"] = "/zen/v1/models";
+    headers["x-relay-path"] = "/inference/v1/models";
    }
   }