copilot-api-node20 0.46.0-preview.1 → 0.47.0

package/README.md

@@ -21,6 +21,7 @@ Want Claude Code on GPT and other non-Claude models? Pick one from your Copilot
   OpenAI SDK    ─┤  /v1/chat/        └─────────────┘      │     Responses API
   curl          ─┤  completions                           │     Embeddings
   Any tool      ─┘                                        │     Images
+                                                          │     Decisions
                                                           │
                                                           ├─▶ Microsoft Foundry /
                                                           │   Azure OpenAI
@@ -66,6 +67,7 @@ Want Claude Code on GPT and other non-Claude models? Pick one from your Copilot
 | **Copilot fallback** | `--fallback copilot`: Copilot answers when Foundry rate-limits, errors or times out, and finishes a Claude Code turn on an OpenAI deployment whose stream fails before any output; then traffic moves back to Foundry |
 | **Web search** | Optional web search for Claude Code and Codex sessions, via **Tavily and/or Exa** with automatic failover |
 | **Image generation & editing** | OpenAI **Images API** on Copilot's **GPT Image 2.5 Flare**: text-to-image, edits and multi-image composition, exact text rendering, transparent PNGs — see [Image Generation](#image-generation) |
+| **Decision models** | OpenAI **Decisions API** (`/v1/decisions`) on Copilot's **GPT-6 Luna Decisions**: yes/no, choice and score questions about text and images, each answer with a probability — see [Decision Models](#decision-models) |
 | **Dual API compatibility** | OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses APIs side by side |
 | **HTTPS with auto-generated certs** | Self-signed TLS certs with configurable SANs -- works across VMs, containers, and LAN |
 | **Zero configuration** | Single command to start -- authenticates via GitHub device-code OAuth |
@@ -220,6 +222,26 @@ Good to know:
 - `gpt-image-2.5-flare` works only on the Images endpoints, not on Chat Completions or Responses. Streaming (`stream: true`) is not supported by Copilot yet.
 - Edit uploads are limited to 100 MB per request. Image endpoints are Copilot-only (not available with `--provider foundry`).
 
+### Decision Models
+
+Copilot also serves a decision model, **GPT-6 Luna Decisions** (`gpt-6-luna-decisions`). It does not write text. It answers `predicate` (yes/no), `choice` and `score` questions about your input and returns a probability for each answer. The proxy exposes it through the **OpenAI Decisions API** (`POST /v1/decisions`). The request goes to Copilot unchanged, so the [OpenAI Decisions guide](https://developers.openai.com/api/docs/guides/decisions) applies, with one change: the guide examples use `"model": "gpt-6-luna"`, but on Copilot that name is a chat model and `/v1/decisions` rejects it with `model_not_supported`. Send `"model": "gpt-6-luna-decisions"`. The decision model does not work on `/v1/chat/completions`, `/v1/responses` or `/v1/messages`.
+
+```bash
+curl -s http://localhost:4141/v1/decisions \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-6-luna-decisions",
+    "input": "I was charged twice for my order.",
+    "questions": [
+      {"type": "choice", "name": "department", "instructions": "Which team should handle this?",
+       "choices": [{"value": "billing"}, {"value": "technical"}]},
+      {"type": "predicate", "name": "angry", "instructions": "Is the customer angry?"}
+    ]
+  }'
+# {"answers":[{"type":"choice","name":"department","choice":"billing","confidence":1,...},
+#             {"type":"predicate","name":"angry","probability":0.42}],"usage":{...}}
+```
+
 ### Claude Cowork
 
 Use Claude's desktop app ([Cowork](https://claude.ai/desktop)) with your Copilot subscription. Requires [Tailscale](https://tailscale.com) (free for personal use) for a real Let's Encrypt TLS certificate — no self-signed cert headaches.
@@ -330,6 +352,8 @@ All endpoints are served at `http://localhost:4141` by default (`https://` when
 | `POST` | `/v1/images/generations` | OpenAI Images: generate (for example `gpt-image-2.5-flare`) |
 | `POST` | `/v1/images/edits` | OpenAI Images: edit (multipart/form-data, 100 MB body limit) |
 | `POST` | `/images/generations`, `/images/edits` | OpenAI Images without the `/v1` prefix |
+| `POST` | `/v1/decisions` | OpenAI Decisions API (for example `gpt-6-luna-decisions`) |
+| `POST` | `/decisions` | OpenAI Decisions API without the `/v1` prefix |
 | `GET` | `/v1/models` | OpenAI Models |
 | `GET` | `/models` | OpenAI Models without the `/v1` prefix |
 | `GET` | `/usage` | GitHub Copilot usage and quota information |