pi-freeflow 1.38.1 → 1.38.2

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## 1.38.2
+
+### Patch Changes
+
+- Add Exo to the OpenCode free tier — a live preview model with chat, tools, reasoning, and image input that the official free lineup lists.
+- Add GLM-5.3 Flash and LL Alpha to the OpenCode free tier, and retire Step 5 Preview — it is gone from the Zen lineup and demoted to paid on the Kilo lane, so those entries can no longer be selected.
+
 ## 1.38.1
 
 ### Patch Changes

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow
 
-> 36 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
+> 37 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 |
 | :--- | :--- | :--- |
-| **36 free models** | 12 from OpenCode Zen, 14 from KiloCode Gateway, 2 from Cline, 8 from OVHcloud AI Endpoints, context windows up to 1M. Full list below. | **$0** |
+| **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** |
 | **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:
 
 ---
 
-### 36 models, one command
+### 37 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 (12 models), Responses and Chat API
+#### OpenCode Zen (14 models), Responses and Chat API
 
 Good defaults for long coding sessions and agentic work.
 
@@ -220,10 +220,12 @@ Good defaults for long coding sessions and agentic work.
 | `big-pickle` | Big Pickle | **200K** (200.000) | **32K** (32.000) | `high / max` | ❌ |
 | `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` | ✅ |
-| `step-5-preview-free` | StepFun | **1M** (1.000.000) | **64K** (65.536) | `low … high` | ✅ |
+| `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` | ❌ |
+| `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` | ✅ |
 
-#### KiloCode Gateway (14 models), OpenRouter compatible
+#### KiloCode Gateway (13 models), OpenRouter compatible
 
 Keyless access. Short aliases work for every row (the full ID is in parentheses).
 
@@ -241,7 +243,6 @@ Keyless access. Short aliases work for every row (the full ID is in parentheses)
 | `kilo-auto` (`kilo-auto/free`) | Kilo Gateway Auto | **256K** (256.000) | **10K** (10.000) | `minimal…xhigh`\* | ❌ |
 | `openrouter` (`openrouter/free`) | OpenRouter Free | **200K** (200.000) | **65K** (65.536) | `minimal…xhigh`\* | ✅ |
 | `glyph-cluster` (`stealth/glyph-cluster`) | Stealth preview (lab undisclosed) | **256K** (256.000) | **256K** (256.000) | `minimal…xhigh`\* | ❌ |
-| `step-5-preview:kilo` (`stepfun/...:free`) | StepFun | **1M** (1.000.000) | **64K** (65.536) | `minimal…xhigh`\* | ✅ |
 | `inkling-small` (`thinkingmachines/inkling-small:free`) | Thinking Machines | **1M** (1.048.576) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
 
 \* Levels are forwarded as-is through the OpenRouter-style nested `reasoning` parameter; effort mapping is decided by each model. MiMo collapses `minimal→low` and `xhigh→high` upstream, so its selector shows 5 labels but only 3 distinct effort values.
@@ -367,7 +368,7 @@ pnpm smoke       # verifies extensions/index.ts loads without crashing
 #### Project structure
 
 ```
-├── models.ts                # 36-model catalog definitions
+├── models.ts                # 37-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": "1.38.1",
+  "version": "1.38.2",
   "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

@@ -43,8 +43,14 @@ import type {
  * - inclusionai/ling-3.0-flash-fin:free: gone from Kilo (2026-10-01) — keyless chat 404
  *   "The requested model ... does not exist".
  * - mimo-v2.5-free: decommissioned upstream (2026-10-07) — HTTP 401 "Model mimo-v2.5-free is not supported".
- * - exo-free: deprecated upstream (2026-10-09) — HTTP 410 "Model exo-free has
- *   been deprecated." (was 503 "Endpoint is unavailable" on 2026-10-07).
+ *   Re-probed 2026-10-16: 410 "Model mimo-v2.5-free has been deprecated. Use
+ *   mimo-v2.6-flash-free instead." The docs still list it as free; they are stale.
+ * - exo-free: dead-listed 2026-10-09 (410 "Model exo-free has been deprecated")
+ *   but revived upstream on 2026-10-16 — back on the official free lineup and
+ *   answering live through the proxy (chat 200 with tools, stream, reasoning,
+ *   vision; dual-canary recall at ~520K tokens; a 1.2M-word prompt draws the
+ *   empty-bodied 400). Re-registered statically the same day: do NOT add this
+ *   id back to this set unless it dies again.
  * - fledge-alpha-free: withdrawn upstream (2026-10-09) — absent from the live
  *   Zen list, chat 401 "Model fledge-alpha-free is not supported".
  * - inclusionai/ling-3.0-flash-sante:free: demoted to paid on Kilo (2026-10-09) —
@@ -94,7 +100,6 @@ export const DEAD_MODEL_IDS = new Set<string>([
  "ling-3.0-flash-fin-free",
  "inclusionai/ling-3.0-flash-fin:free",
  "mimo-v2.5-free",
- "exo-free",
  "stealth/space-bunny-alpha",
  "qwen/qwen3.8-27b:free",
  "nvidia/nemotron-3.5-content-safety:free",
@@ -110,6 +115,15 @@ export const DEAD_MODEL_IDS = new Set<string>([
  "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",
+ // step-5-preview-free: removed from the Zen free docs (2026-10-16 drift,
+ // v1.19.2) and the endpoint answers 400 "Model is unavailable" on both the
+ // chat and the responses shape — the same retirement signature as
+ // deepseek-v4-flash-free.
+ "step-5-preview-free",
+ // stepfun/step-5-preview-free: demoted to paid on Kilo (2026-10-16) —
+ // 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",
 ]);
 /**
  * Free-tier allowlist for anything entering the picker via network or stale disk.
@@ -149,7 +163,7 @@ export function sanitizeCatalogModels(models: RegisteredModel[]): RegisteredMode
 }
 /**
  * In-memory cache of currently active/available free models.
- * Initialized with all 36 verified models for 0ms instant availability.
+ * Initialized with all 37 verified models for 0ms instant availability.
  */
 let aliveCatalog: RegisteredModel[] = ALL_MODELS.map((m) => ({
  ...m,

package/src/models.ts

@@ -1,9 +1,9 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 36 verified free models (live-verified 2026-10-16):
- * - 12 OpenCode Zen models (2 Responses API + 10 Chat Completions)
- * - 14 KiloCode Keyless Gateway models (OpenRouter format)
+ * Defines the 37 verified free models (live-verified 2026-10-16):
+ * - 14 OpenCode Zen models (2 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)
  */
@@ -216,30 +216,100 @@ export const OPENCODE_MODELS: ModelDef[] = [
   },
  },
  {
- // Added 2026-10-09: replaces fledge-alpha-free (withdrawn upstream —
- // absent from the live list, chat 401 "not supported"). Live on the Zen
- // list; gated-lane 403 matches the working models from a refused egress,
- // so it rides the same fingerprint path. Specs per models.dev
- // (opencode/step-5-preview-free) + StepFun docs, NOT the enrichModelDef
- // substring heuristic (which yields reasoning:false / 262K / text-only):
- // 1M ctx, 64K max output, text+image+video, efforts low/medium/high only.
- // minimal is explicitly null (omitting the key leaves it selectable in
- // the host); xhigh/max are unsupported upstream.
- id: "step-5-preview-free",
- name: "Step 5 Preview [OpenCode]",
- reasoning: true,
- contextWindow: 1_000_000,
- maxTokens: 65_536,
- input: ["text", "image", "video"],
- thinkingLevelMap: {
-  off: null,
-  minimal: null,
-  low: "low",
-  medium: "medium",
-  high: "high",
-  xhigh: null,
-  max: null,
+  // Added 2026-10-16 (issue #71 drift): Zen v1.19.2 added this free id;
+  // served through the fingerprint path (chat 200 with tools + stream).
+  // Not published on pi.dev yet, and models.dev's 200,000 context is
+  // contradicted by probe: a marker planted at 90% depth (~250K words) is
+  // recalled, and only above ~1M words does the gateway refuse with
+  // context_length_exceeded. Declared 1,000,000 like its Zen siblings and
+  // the Kilo twin (z-ai/glm-5.3-flash, 1,048,576 in this catalog); the
+  // 450K/700K-word recall probes timed out upstream and stayed inconclusive.
+  // maxTokens 32,000 per models.dev — the gateway accepted up to 131,072,
+  // and acceptance is not a cap, so the published figure stays the budget.
+  // Effort ladder probed level-by-level 2026-10-16: minimal/low/medium/high/
+  // xhigh/max all answer 200 (an unsupported value answers 400
+  // [invalid_value], so the gateway validates per model), and minimal vs max
+  // visibly changes reasoning length. Chat is the only native shape
+  // (/v1/responses answers 400 "Model does not support this protocol"),
+  // so `api` stays unset. Vision verified live (a 1x1 PNG reads back as a
+  // colour); video/pdf from the published entry stay unverified and are not
+  // offered.
+  id: "glm-5.3-flash-free",
+  name: "GLM-5.3 Flash [OpenCode]",
+  reasoning: true,
+  contextWindow: 1_000_000,
+  maxTokens: 32_000,
+  input: ["text", "image"],
+  thinkingLevelMap: {
+   off: null,
+   minimal: "minimal",
+   low: "low",
+   medium: "medium",
+   high: "high",
+   xhigh: "xhigh",
+   max: "max",
+  },
  },
+ {
+  // 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]",
+  reasoning: true,
+  contextWindow: 262_144,
+  maxTokens: 65_536,
+  input: ["text"],
+  thinkingLevelMap: {
+   off: null,
+   minimal: null,
+   low: "low",
+   medium: "medium",
+   high: "high",
+   xhigh: "xhigh",
+   max: "max",
+  },
+ },
+ {
+  // Added 2026-10-16 (recheck): live free id on the Zen lane, listed on the
+  // official free lineup while models.dev already tags it deprecated — the
+  // tag also sits on live ids (muse-spark-1.2-contributor-free) and on
+  // already-dead ones (mimo-v2.5-free), so the live answer decides: chat 200
+  // with tools + stream, and the tool call round-trips. Chat is the only
+  // native shape (/v1/responses answers 400 "Model does not support this
+  // protocol"), so `api` stays unset. Reasoning: the published ladder lists
+  // `high` only; high streams thinking and the unavailable rungs stay null
+  // so the picker never offers them. Vision verified live (a 1x1 PNG reads
+  // back as "Pink"). Context: published 1,048,576; a dual-canary prompt at
+  // ~400K words (~520K tokens, canaries at ~30%/~97% depth) recalls both
+  // markers, and a 1.2M-word prompt (~1.56M tokens) draws an empty-bodied
+  // 400 — the wall sits between, matching the published figure. maxTokens
+  // 131,072 published; 131,073 accepted (acceptance is not a cap, so the
+  // published figure stays the budget).
+  id: "exo-free",
+  name: "Exo [OpenCode]",
+  reasoning: true,
+  contextWindow: 1_048_576,
+  maxTokens: 131_072,
+  input: ["text", "image"],
+  thinkingLevelMap: {
+   off: null,
+   minimal: null,
+   low: null,
+   medium: null,
+   high: "high",
+   xhigh: null,
+   max: null,
+  },
  },
 {
   // Added 2026-10-15: new free model on the OpenCode Zen lane. Live-verified by
@@ -409,19 +479,6 @@ export const KILO_MODELS: ModelDef[] = [
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
  },
- {
-  // Added 2026-10-09: replaces step-3.7-flash (demoted to paid upstream —
-  // :free ID 404s keyless). Live on Kilo free list (isFree:true, 0/0
-  // pricing, 1M ctx) + keyless chat served (429 provider concurrency).
-  id: "stepfun/step-5-preview-free",
-  name: "Step 5 Preview [Kilo]",
-  reasoning: true,
-  contextWindow: 1_000_000,
- maxTokens: 65_536,
- input: ["text", "image", "video"],
-  thinkingFormat: "openrouter",
-  thinkingLevelMap: KILO_REASONING_MAP,
- },
  {
   id: "thinkingmachines/inkling-small:free",
   name: "Inkling Small [Kilo]",
@@ -656,7 +713,8 @@ export const MODEL_ALIASES: Record<string, string> = {
  "nemotron-3-super": "nvidia/nemotron-3-super-120b-a12b:free",
  "north-mini-code": "cohere/north-mini-code:free",
  "lfm-2.5": "liquid/lfm-2.5-2.6b:free",
- "step-5-preview:kilo": "stepfun/step-5-preview-free",
+ "glm-5.3-flash": "glm-5.3-flash-free",
+ "exo": "exo-free",
  "glyph-cluster": "stealth/glyph-cluster",
  "inkling-small": "thinkingmachines/inkling-small:free",
  "mimo-v2.6-flash": "mimo-v2.6-flash-free",
@@ -664,7 +722,7 @@ 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",
- "step-5-preview": "step-5-preview-free",
+ "ll-alpha": "ll-alpha-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",
@@ -719,7 +777,7 @@ export const OVH_MODEL_IDS = new Set<string>([
   .map(([alias]) => alias),
 ]);
 /**
- * Combined list of all 36 static free models (canonical)
+ * Combined list of all 37 static free models (canonical)
  */
 export const ALL_MODELS: ModelDef[] = [...OPENCODE_MODELS, ...KILO_MODELS, ...CLINE_MODELS, ...OVH_MODELS];