free-coding-models 0.5.43 → 0.5.45

package/README.md

@@ -466,28 +466,27 @@ When a tool mode is active (via `Z`), models incompatible with that tool are hig
 
 ---
 
-## π Pi Extension — FCM-Pi
+## π Pi Extension — FCM-Pi ⚠️ BETA
 
 **FCM-Pi** is a native [Pi coding agent](https://pi.dev) extension that integrates `free-coding-models` directly into your Pi session. It auto-selects the best free model on startup, shows a live animated scan in the Pi status bar, and lets you hot-swap models mid-session.
 
+> **BETA** — The extension is under active development and not yet published to npm. Install via local path only.
+>
 > **Requires**: Pi coding agent (pi.dev) + free-coding-models installed and configured with at least one API key.
 
 ### Installation
 
-Add the extension to your Pi settings (`~/.pi/agent/settings.json`):
+Add the extension path to `~/.pi/agent/settings.json` (the extension is **not yet on npm** — local path only for now):
 
 ```json
 {
   "packages": [
-    "../../Documents/GitHub/free-coding-models/pi-extension"
+    "/Users/yourname/Documents/GitHub/free-coding-models/pi-extension"
   ]
 }
 ```
 
-Or install directly from the Pi shell once published to npm:
-```bash
-pi install npm:fcm-pi
-```
+Then restart Pi. The extension loads automatically.
 
 ### What it does
 

package/changelog/v0.5.44.md

@@ -0,0 +1,30 @@
+# Changelog v0.5.44 - 2026-07-08
+
+### Added
+- **Provider catalog audit (all 20 providers)** — refreshed every provider against live official docs/endpoints via the `update_models` skill.
+- **NVIDIA NIM**: added Qwen3 Coder 480B, Mistral Nemotron, Llama 3.3 Nemotron Super 49B v1.5, DeepSeek V3.2, Qwen2.5 Coder 32B, Magistral Small 2506, Nemotron 3 Nano, Llama 4 Scout (A+ / 10M ctx); GLM-5.1 → GLM-5.2.
+- **GitHub Models**: added GPT-5 / GPT-5 Mini / GPT-5 Nano / GPT-5 Chat, GPT-4o / GPT-4o Mini, o3 / o4-mini / o3-mini / o1 / o1-mini / o1-preview, DeepSeek-R1 / R1-0528, Cohere Command A, Phi-4 family (20 models).
+- **Cerebras**: added Gemma 4 31B.
+- **Mistral**: added Ministral 3 family (14B / 8B / 3B); Magistral Medium 1.2 retired.
+- **Cloudflare**: added QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, Llama 3.1 8B Instruct (Fast); removed deprecated Kimi K2.5 and Mistral 7B v0.2.
+- **OpenRouter**: added Tencent Hy3, Qwen3 Coder, Poolside Laguna XS 2.1, Llama 3.3 70B, Hermes 3 405B, Qwen3 Next 80B, Llama 3.2 3B, Dolphin Mistral 24B, Nemotron 3.5 Content Safety, LFM 2.5 1.2B (instruct + thinking); removed Owl Alpha; renamed Nemotron Nano 30B → Nemotron 3 Nano 30B.
+- **Codestral**: added Codestral 2.
+- **Z.ai**: added GLM-4.6V-Flash; GLM-4.7-Flash ctx 200k → 203k.
+- **Scaleway**: added GLM 5.2, Mistral Medium 3.5 128B, Gemma 4 26B MoE, Pixtral 12B; dropped `mistral/` prefix on Mistral Large 675B id.
+- **Qwen**: added Qwen3.7 Plus, Qwen3.6 Max Preview, Qwen3 Coder 480B, Qwen3.5 397B/122B/35B/27B, Qwen3 Next 80B (thinking + instruct), Qwen3 30B; Qwen3 235B & Qwen3 32B ctx corrected 256k → 128k.
+- **LLM7**: added Claude Opus 4.8 / Sonnet 5 / Fable 5, GPT-5.5 / GPT-5.4 / GPT-5.4-mini, GLM 5.2, MiniMax M2.7; removed Qwen3 235B & Mistral Small 3.2; ctx fixes on DeepSeek V4 Flash (1M), Kimi K2.6 (240k), Devstral Small 2 (255k).
+- **Ollama Cloud**: removed 7 paid/locked models (MiniMax M2.7, GLM-5.1, Kimi K2.6, DeepSeek V4 Pro/Flash, Qwen3.5 397B, Mistral Large 3); added 17 free-tier models (Gemma 3 4B/12B/27B, MiniMax M2/M2.1/M2.5, Ministral 3 3B/8B/14B, GLM 4.6, Cogito 2.1 671B, Devstral Small 2 24B, Nemotron 3 Nano 30B, Qwen3 Next 80B, Qwen3 VL 235B + instruct, RNJ 1 8B); ctx fixes on Devstral 2, Nemotron 3 Ultra/Super, GLM-4.7, MiniMax M3.
+- **Novita**: corrected Qwen3.6 Plus SWE score (78.8%) and MiniMax M2 HER ctx (66k).
+- **Routeway**: removed MiniMax M2 and Mistral Nemo free tiers.
+
+### Fixed
+- **Cerebras**: corrected both model context windows from 8k → 128k.
+- **GitHub Models**: Llama 4 Scout ctx 1M → 10M.
+- **NVIDIA NIM**: Kimi K2.6 ctx 256k → 262k; Nemotron 3 Nano 30B ctx 128k → 1M.
+
+### Changed
+- **audit_state.json** regenerated for all 20 providers (total catalog: 257 models, up from 157).
+- Catalog arrays now grouped by tier with inline tier comments for easier review.
+
+### Notes
+- Low/medium-confidence sources (Ollama Cloud third-party probe, Routeway chimera/umbra, LLM7 guessed tiers, Novita free-status) were applied as-is per request; verify before relying on them in production.

package/changelog/v0.5.45.md

@@ -0,0 +1,11 @@
+# Changelog v0.5.45 - 2026-07-08
+
+### Changed
+- **SWE-bench Verified scores refreshed for all 257 models.** 12 web-research agents audited every model family against the SWE-bench Verified leaderboard (swebench.com), SWE-Rebench, Artificial Analysis, and official model cards.
+- **68 models went from `-` (unknown) to a real SWE-bench Verified score** (e.g. GPT-4.1 → 54.6%, GPT-5 → 74.9%, DeepSeek V4 Pro → 80.6%, Qwen3.7 Max → 80.4%, Gemini 2.5 Pro → 63.8%, GLM-5.2 → 82.8%, Kimi K2.6 → 80.2%, Llama 4 Maverick → 74.8%, Nemotron 3 Ultra → 71.9%).
+- **Tiers recomputed from real SWE-bench Verified scores** using the project scale (S+ ≥70%, S 60–70%, A+ 50–60%, A 40–50%, A- 35–40%, B+ 30–35%, B 20–30%, C <20%). Several models dropped tiers to match verified numbers (e.g. Llama 3.3 70B A- → B at 22.0%; GPT-OSS-20B A → B+ at 50.3%; Mistral Small 4 S → A- after its public score was not found, kept manual estimate).
+- **Existing scores corrected** where research disagreed with prior self-reported/manual values (e.g. GPT-OSS-120B 60% → 62.4%; Qwen3.6 Plus 72% → 78.8%; MiniMax M2.7 80.2% confirmed; Gemini 3.1 Pro 78% → 80.6%).
+
+### Notes
+- **55 models remain `-`** (no public SWE-bench Verified score): embeddings (bge, Qwen3-Embedding), vision-only (Pixtral, Llama vision, GLM-4.6V), small/edge models (Phi-4, Ministral 3B, Granite, Gemma 3 4B/12B), routers (Kilo, OpenRouter Free, Mimo, Nex, RNJ, Big Pickle, Poolside where not listed), reasoning-only (Nemotron Nano Omni), and unverifiable/fictionally-named entries (Claude Fable 5, Claude Sonnet 5 returned scores but are unverified; Claude Opus 4.8 returned 88.6% but is unverified). Their tiers retain the prior manual estimates.
+- Source scores are self-reported / leaderboard-aggregated and drift over time; re-run the audit periodically.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.43",
+  "version": "0.5.45",
   "description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
   "keywords": [
     "nvidia",