copilot-relay 0.4.5 → 0.4.6

package/README.md

@@ -16,7 +16,7 @@
 - **Use advertised chat models** — catalog-driven endpoint selection, optional effort support, and clear opt-in per-model deep checks.
 - **Choose Claude's upstream protocol** — `claudeUpstreamApi: chat-completions` stays the default; opt into `auto` or `messages` for native Claude transport.
 - **Diagnose offline** — debug mode captures full observed bodies for `copilot-relay replay`; captures contain unredacted prompts and must never be shared wholesale.
-- **Run it your way** — foreground CLI or background service on macOS, Windows, and Linux.
+- **Run it your way** — foreground CLI or background service on macOS, Windows, and Linux; set `apiKey` to require a client key before binding beyond loopback.
 
 ## Quick start
 
@@ -39,7 +39,8 @@ claude
 
 Configuration lives in `~/.copilot-relay/config.yaml`. Model access depends on your
 account and organization policy; if startup rejects a model, choose an available
-one using the [configuration guide](wiki/EN-Configuration.md).
+one using the [configuration guide](wiki/EN-Configuration.md). Behind a proxy, set
+`upstreamProxy` in `config.yaml` to its URL, or `env`, before `copilot-relay auth`.
 
 Discover models, find the config value for one, and optionally test it:
 
@@ -53,6 +54,18 @@ Deep checks **consume Copilot usage** and test an isolated relay pipeline, not t
 running daemon. Add `--details` for safe failure evidence and private replay hints.
 Use `copilot-relay status --deep` for daemon health, and `copilot-relay stop` when finished.
 
+Check how well prompt caching works per model and upstream route. The report reads
+only local logs and flags rows below a hit-rate goal, 95% by default:
+
+```sh
+copilot-relay cache                  # last 24 hours
+copilot-relay cache --hourly         # or --daily; narrow with --since 6h or --model opus
+copilot-relay cache --json
+```
+
+Check your Copilot plan and quota with `copilot-relay usage`; add `--json` for
+scripts. It asks GitHub with the stored token, so no relay needs to run.
+
 ## Go further
 
 **[Open the Wiki](https://github.com/D0n9X1n/copilot-relay/wiki)** · **[English / 中文](wiki/README.md)**

package/config.default.yaml

@@ -3,7 +3,7 @@
 # This file is copied to ~/.copilot-relay/config.yaml on first start.
 # Edit the user config file, not this template, for local changes.
 # Valid complete edits hot-reload without rewriting this file.
-# host, port, and claudeSetup require restart.
+# host, port, claudeSetup, and upstreamProxy require restart.
 #
 # Values here apply to a fresh install only. copilot-relay writes the resolved
 # config back to disk, so once a key exists in your config.yaml it is yours:
@@ -15,13 +15,32 @@ host: 127.0.0.1
 # Local port for the HTTP server.
 port: 4142
 
+# Optional key that every client request must carry, as x-api-key or
+# Authorization: Bearer. GET /healthz and GET|HEAD /api/hello stay open.
+# Empty disables it. A set key is at least 16 visible ASCII characters;
+# quote one that starts with #. Set a key before binding host beyond
+# loopback: otherwise any client that reaches the port can use your
+# Copilot account. Changes hot-reload, but a client keeps the token it
+# loaded, so update and restart clients after changing it.
+apiKey:
+
 # GitHub Copilot API base URL.
 # Keep this default unless you know your Copilot tenant uses a custom endpoint.
 copilotBaseUrl: https://api.githubcopilot.com
 
+# Outbound proxy for Copilot and GitHub calls, including sign-in.
+# Leave empty to connect directly.
+# env uses HTTPS_PROXY, HTTP_PROXY and NO_PROXY. A background service does not
+# inherit your shell's variables, so prefer a URL there.
+# A URL looks like http://proxy.example:3128 or https://user:password@proxy.example:3128;
+# percent-encode reserved characters in the user name and password.
+upstreamProxy:
+
 # When true, start updates ~/.claude/settings.json with ANTHROPIC_BASE_URL
-# and a dummy ANTHROPIC_AUTH_TOKEN so Claude Code can use this proxy.
-# Also seeds context/output budgets from model discovery when not already set.
+# and ANTHROPIC_AUTH_TOKEN so Claude Code can use this proxy. The token is
+# apiKey when it is set; otherwise a dummy token is written if none is present.
+# Also seeds context/output budgets from model discovery, and
+# CLAUDE_CODE_AUTO_MODE_SERVER=0, when not already set.
 claudeSetup: true
 
 # Log verbosity: