copilot-custom-endpoint 1.3.8 → 1.3.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -1
- package/docs/models/kimi.md +4 -1
- package/docs/models/qwen.md +4 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -116,7 +116,7 @@ VS Code's built-in `view_image` tool only accepts **static images** (PNG, JPG, G
|
|
|
116
116
|
**Video Context MCP** is a small MCP server that bridges that gap. It works with **GitHub Copilot, Cursor, and Claude Code** out of the box, and:
|
|
117
117
|
|
|
118
118
|
- **Extracts frames** from local files or remote URLs (no `ffmpeg` gymnastics required).
|
|
119
|
-
- **Routes them through a multi-provider fallback chain** — `Gemini → GLM 4.6V Flash→ Qwen3.7-plus → Kimi K2.6 → MiMo-V2.5` — so a single `GLM 5V Turbo` rate-limit hiccup doesn't kill your session.
|
|
119
|
+
- **Routes them through a multi-provider fallback chain** — `Gemini → GLM 4.6V Flash → Qwen3.7-plus → Kimi K2.6 → MiMo-V2.5` — so a single `GLM 5V Turbo` rate-limit hiccup doesn't kill your session.
|
|
120
120
|
- **Answers natural-language questions** about the video grounded in actual frames: "what does the speaker click in the last 30 seconds?", "summarize the demo", "find the frame where the error appears".
|
|
121
121
|
- **Extras:** timestamp search, audio transcription with speaker diarization, and video metadata (resolution, duration, codec).
|
|
122
122
|
|
package/docs/models/kimi.md
CHANGED
|
@@ -17,7 +17,10 @@
|
|
|
17
17
|
|
|
18
18
|
## Quick Start
|
|
19
19
|
|
|
20
|
-
1. **Start the proxy
|
|
20
|
+
1. **Start the proxy** — choose one:
|
|
21
|
+
- `npm run proxy:kimi` (from the repo root)
|
|
22
|
+
- `npx copilot-custom-endpoint kimi` (standalone, no clone needed)
|
|
23
|
+
- `npx copilot-custom-endpoint` (also starts the Qwen proxy concurrently)
|
|
21
24
|
2. **Edit `chatLanguageModels.json`** — add the Kimi block from [Setup](#setup) below.
|
|
22
25
|
3. **Set your Moonshot API key** via the Command Palette → **Chat: Manage Language Models**.
|
|
23
26
|
4. **Restart VS Code** and pick "Kimi K2.6" in the chat picker.
|
package/docs/models/qwen.md
CHANGED
|
@@ -32,7 +32,10 @@
|
|
|
32
32
|
|
|
33
33
|
## Quick Start — With Proxy (Dynamic Thinking)
|
|
34
34
|
|
|
35
|
-
1. **Start the proxy
|
|
35
|
+
1. **Start the proxy** — choose one:
|
|
36
|
+
- `npm run proxy:qwen` (from the repo root)
|
|
37
|
+
- `npx copilot-custom-endpoint qwen` (standalone, no clone needed)
|
|
38
|
+
- `npx copilot-custom-endpoint` (also starts the Kimi proxy concurrently)
|
|
36
39
|
2. **Edit `chatLanguageModels.json`** — use the proxy-path block from [Setup § Proxy](#proxy-path) below.
|
|
37
40
|
3. **Set your DashScope API key** via the Language Models UI.
|
|
38
41
|
4. **Restart VS Code.** Reasoning will be visible in plain chat and suppressed on tool turns.
|