ghc-proxy 0.8.1 → 0.9.0
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.mjs +699 -359
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -121,7 +121,7 @@ bunx ghc-proxy@latest selfcheck # Probe the packaged bundle (loads every to
|
|
|
121
121
|
| `--idle-timeout` | -- | `120` | Bun server idle timeout in seconds (`0` disables; Bun max is `255`; streaming routes disable idle timeout automatically) |
|
|
122
122
|
| `--upstream-timeout` | -- | `1800` | Upstream request timeout in seconds (0 to disable) |
|
|
123
123
|
| `--upstream-queue-concurrency` | -- | `10` | Maximum concurrent Copilot upstream requests |
|
|
124
|
-
| `--upstream-queue-retries` | -- | `5` | Maximum retries for transient upstream responses (
|
|
124
|
+
| `--upstream-queue-retries` | -- | `5` | Maximum retries for transient upstream responses. Completion requests (`/v1/messages`, `/chat/completions`, `/responses`) retry only `429`/`529`; effect-free requests also retry `408`, `500`, `502`, `503`, `504` |
|
|
125
125
|
| `--upstream-queue-base-delay` | -- | `2` | Base delay in seconds for upstream retry backoff when `Retry-After` is absent |
|
|
126
126
|
| `--upstream-queue-max-delay` | -- | `60` | Maximum delay in seconds for upstream retry backoff |
|
|
127
127
|
| `--ghe-domain` | `--ghe` | -- | GitHub Enterprise Cloud company domain (e.g. `company.ghe.com`). Required for GHE.com device login on first run; persisted automatically for later runs. |
|
|
@@ -204,9 +204,9 @@ All fields are optional. The full schema:
|
|
|
204
204
|
| `responsesApiParameterFiltersReplaceDefault` | `boolean` | `false` | Disable the built-in reasoning-model default rule so only your `responsesApiParameterFilters` apply |
|
|
205
205
|
| `responsesOfficialEmulator` | `boolean` | `false` | Enable local OpenAI-style Responses state emulation for `previous_response_id`, `conversation`, retrieve, input_items, delete, and input_tokens |
|
|
206
206
|
| `responsesOfficialEmulatorTtlSeconds` | `number` | `14400` | In-memory TTL for locally emulated Responses state |
|
|
207
|
-
| `modelReasoningEfforts` | `Record<string, string>` | -- | Per-model reasoning effort defaults for Anthropic-to-Responses translation. Each value must be one of `none`, `minimal`, `low`, `medium`, `high`, or `
|
|
207
|
+
| `modelReasoningEfforts` | `Record<string, string>` | -- | Per-model reasoning effort defaults for Anthropic-to-Responses translation. Each value must be one of `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, or `max` (ascending) |
|
|
208
208
|
| `upstreamQueueConcurrency` | `number` | `10` | Maximum concurrent Copilot upstream requests |
|
|
209
|
-
| `upstreamQueueMaxRetries` | `number` | `5` | Maximum retries for transient upstream responses (
|
|
209
|
+
| `upstreamQueueMaxRetries` | `number` | `5` | Maximum retries for transient upstream responses. Completion requests (`/v1/messages`, `/chat/completions`, `/responses`) retry only `429`/`529`; effect-free requests also retry `408`, `500`, `502`, `503`, `504` |
|
|
210
210
|
| `upstreamQueueBaseDelaySeconds` | `number` | `2` | Base delay (seconds) for upstream retry backoff when `Retry-After` is absent |
|
|
211
211
|
| `upstreamQueueMaxDelaySeconds` | `number` | `60` | Maximum delay (seconds) for upstream retry backoff |
|
|
212
212
|
| `gheDomain` | `string` | -- | GitHub Enterprise Cloud company domain (persisted automatically after GHE.com auth) |
|