@bman654/clodex 2.4.0 → 2.5.0
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 +10 -0
- package/dist/{chunk-LBEJOEUY.js → chunk-MRO3KE3P.js} +504 -101
- package/dist/chunk-MRO3KE3P.js.map +1 -0
- package/dist/claude-wrapper.js +19 -1
- package/dist/claude-wrapper.js.map +1 -1
- package/dist/cli.js +1392 -213
- package/dist/cli.js.map +1 -1
- package/docs/background-agents.md +15 -0
- package/package.json +1 -1
- package/dist/chunk-LBEJOEUY.js.map +0 -1
package/README.md
CHANGED
|
@@ -105,6 +105,7 @@ Launch Claude Code bridged to OpenAI models. Unrecognized flags (and everything
|
|
|
105
105
|
| `--save-mode` | With `--endpoint`/`--proxy`: save that mode as the `claude` default |
|
|
106
106
|
| `--dry-run` | Run the wizard but print a launch preview instead of launching (never persists anything) |
|
|
107
107
|
| `--trace` | Write debug logs to `~/.clodex/logs/` and show errors on exit |
|
|
108
|
+
| `--fast` | Request Codex fast mode (`service_tier=priority`) for ChatGPT/Codex OAuth routes; equivalent to `CLODEX_SERVICE_TIER=fast` |
|
|
108
109
|
| `--provider <id>` | Boot provider id (`openai` or `openai-oauth`); with `--model`, skips the wizard |
|
|
109
110
|
| `--model <id>` | Boot model id; with `--provider`, skips the wizard |
|
|
110
111
|
| `--help`, `--version` | Help / version |
|
|
@@ -274,6 +275,15 @@ clodex --version # version
|
|
|
274
275
|
secure store instead; see [credential helpers](docs/credential-helpers.md).
|
|
275
276
|
- Proxied routes forward configured provider headers for API-key and OAuth authentication. Anonymous routes preserve non-credential headers while removing authorization, API-key, cookie, token, secret, and credential-bearing header names before dispatch.
|
|
276
277
|
- `CLODEX_CLAUDE_PATH` overrides Claude Code binary discovery.
|
|
278
|
+
- **Codex service tier:** `CLODEX_SERVICE_TIER` accepts `fast` (normalized to
|
|
279
|
+
`priority`), `priority`, `flex`, `auto`, or `default`. Clodex requests the
|
|
280
|
+
resolved value only after selecting a ChatGPT/Codex OAuth route; OpenAI
|
|
281
|
+
API-key and non-OpenAI routes are unaffected. `clodex claude --fast` sets the
|
|
282
|
+
value to `fast` for that invocation, overriding an ambient value, and composes
|
|
283
|
+
the same environment before a dry-run preview. Request diagnostics record
|
|
284
|
+
this pre-dispatch intent, not proof of wire serialization. If the provider
|
|
285
|
+
SDK reports that it omitted the tier for a model, clodex warns once and the
|
|
286
|
+
backend default remains in use.
|
|
277
287
|
- **Outbound proxy:** when `HTTP_PROXY`/`HTTPS_PROXY` (and optionally `NO_PROXY`) are set in clodex's environment, all clodex-originated network calls honor them — OAuth sign-in and token refresh, model-list and models.dev refreshes, upstream OpenAI API calls, and the ChatGPT/Codex OAuth WebSocket transport (tunneled via HTTP CONNECT).
|
|
278
288
|
- **Upstream retries:** set `CLODEX_UPSTREAM_MAX_RETRIES` to an integer from
|
|
279
289
|
`0` through `5` to override the SDK's default of two retries for retryable
|