copilot-relay 0.4.1 → 0.4.3
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 +3 -3
- package/dist/main.js +986 -338
- package/dist/main.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -13,7 +13,7 @@
|
|
|
13
13
|
- **WebSearch that fits the conversation** — relay-managed search, followed by an answer that can still use your tools.
|
|
14
14
|
- **Your models, your settings** — configurable GPT/Opus routes and reasoning effort; existing selections survive upgrades.
|
|
15
15
|
- **Use the advertised capacity** — discovered context/output limits, without silently shortening your input.
|
|
16
|
-
- **
|
|
16
|
+
- **Use advertised chat models** — catalog-driven endpoint selection, optional effort support, and clear opt-in per-model deep checks.
|
|
17
17
|
- **Choose Claude's upstream protocol** — `claudeUpstreamApi: chat-completions` stays the default; opt into `auto` or `messages` for native Claude transport.
|
|
18
18
|
- **Diagnose offline** — debug mode captures full observed bodies for `copilot-relay replay`; captures contain unredacted prompts and must never be shared wholesale.
|
|
19
19
|
- **Run it your way** — foreground CLI or background service on macOS, Windows, and Linux.
|
|
@@ -49,8 +49,8 @@ copilot-relay models --deep --model claude-opus-5.5
|
|
|
49
49
|
```
|
|
50
50
|
|
|
51
51
|
Deep checks **consume Copilot usage** and test an isolated relay pipeline, not the
|
|
52
|
-
running daemon.
|
|
53
|
-
`copilot-relay stop` when finished.
|
|
52
|
+
running daemon. Add `--details` for safe failure evidence and private replay hints.
|
|
53
|
+
Use `copilot-relay status --deep` for daemon health, and `copilot-relay stop` when finished.
|
|
54
54
|
|
|
55
55
|
## Go further
|
|
56
56
|
|