codex-as-api 0.10.2__tar.gz → 1.0.0__tar.gz
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.
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/PKG-INFO +38 -25
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/README.md +37 -24
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/RELEASES.md +10 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/pyproject.toml +1 -1
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/__init__.py +1 -1
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/anthropic_adapter.py +397 -31
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/provider.py +689 -17
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/reasoning_signature.py +38 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/server.py +398 -19
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_anthropic_adapter.py +180 -106
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_provider.py +277 -6
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_server.py +310 -22
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/.gitignore +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/LICENSE +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/THIRD_PARTY_NOTICES.md +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/config/codex-upstream-contract.json +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/config/o200k_base.tiktoken +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/config/verified-hidden-models.json +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/requirements.txt +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/rust/THIRD_PARTY_NOTICES.md +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/check_no_static_model_catalog.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/check_package_versions.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/check_registry_release.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/check_release_artifacts.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/generate_rust_third_party_notices.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/scripts/package_rust_release.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/auth.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/browser_login.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/codex_config.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/codex_version.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/device_login.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/messages.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/model_capabilities.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/o200k_tokenizer.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/protocol.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/src/codex_as_api/strict_json.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/__init__.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/conftest.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/fixtures/o200k_base_encode_ordinary.json +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_auth.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_browser_login.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_codex_config.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_codex_version.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_device_login.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_login_commit_races.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_login_generation.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_login_http_real_store.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_management_body.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_messages.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_model_capabilities.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_no_static_model_catalog.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_o200k_tokenizer.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_package_versions.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_protocol.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_registry_release.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_release_artifacts.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_rust_third_party_notices.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_standalone_login_api.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_strict_json.py +0 -0
- {codex_as_api-0.10.2 → codex_as_api-1.0.0}/tests/test_ultrafast.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: codex-as-api
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 1.0.0
|
|
4
4
|
Summary: Use ChatGPT/Codex OAuth as a local OpenAI-compatible API server.
|
|
5
5
|
Project-URL: Homepage, https://github.com/CHOAM-CO/codex-as-api
|
|
6
6
|
Project-URL: Repository, https://github.com/CHOAM-CO/codex-as-api
|
|
@@ -44,7 +44,7 @@ Use ChatGPT / Codex OAuth as a local OpenAI-compatible API server.
|
|
|
44
44
|
|
|
45
45
|
## Features
|
|
46
46
|
|
|
47
|
-
- **OpenAI & Anthropic compatible** — Chat Completions, Messages, and `GET /v1/models`
|
|
47
|
+
- **OpenAI & Anthropic compatible** — Responses (`/v1/responses`, `/v1/responses/compact`), Chat Completions, Messages, and `GET /v1/models`
|
|
48
48
|
- **Claude Code ready** — use Codex models directly from Claude Code CLI
|
|
49
49
|
- **Streaming** — full SSE streaming for both OpenAI and Anthropic protocols
|
|
50
50
|
- **Tool calling** — function calls, tool results, and parallel tool calls
|
|
@@ -392,7 +392,7 @@ it; continuation uses the complete provider Response items saved behind
|
|
|
392
392
|
|
|
393
393
|
Anthropic Messages compatibility endpoint for any client, including Claude Code and Scheherazade. It supports streaming (`stream: true`) and non-streaming without a client-identification header. A live Codex model ID routes directly. A `claude-*` facade ID uses the configured Codex backend model, or the authenticated catalog default when no backend model is configured. Other unknown IDs fail. The response preserves the client-supplied model name.
|
|
394
394
|
|
|
395
|
-
`max_tokens` is a required positive compatibility hint: the private Codex OAuth transport does not expose a matching output-token cap. Valid ephemeral `cache_control` hints are accepted and stripped for every client; their TTL and breakpoint semantics are not forwarded. An optional `x-claude-code-session-id` provides stable hashed cache affinity, not permission to use the endpoint. `metadata
|
|
395
|
+
`max_tokens` is a required positive compatibility hint: the private Codex OAuth transport does not expose a matching output-token cap. Valid ephemeral `cache_control` hints are accepted and stripped for every client; their TTL and breakpoint semantics are not forwarded. An optional `x-claude-code-session-id` provides stable hashed cache affinity, not permission to use the endpoint. Anthropic `metadata` objects with string or null entries (including `user_id` and additional client metadata keys) are accepted and not forwarded.
|
|
396
396
|
|
|
397
397
|
```bash
|
|
398
398
|
curl http://localhost:18080/v1/messages \
|
|
@@ -435,12 +435,21 @@ On the following assistant-history request, recognized envelopes restore the ori
|
|
|
435
435
|
|
|
436
436
|
Multiple summary parts share one thinking block per reasoning item. Encrypted-only items use an empty thinking string with a non-empty signature. Streaming sends `signature_delta` before the matching `content_block_stop`. `display: "omitted"` hides the summary but can preserve an encrypted-only signed block for continuity; disabled thinking suppresses thinking output. Items without encrypted content retain unsigned-summary compatibility behavior.
|
|
437
437
|
|
|
438
|
-
Hosted Anthropic `web_search` declarations
|
|
439
|
-
|
|
440
|
-
|
|
441
|
-
|
|
442
|
-
|
|
443
|
-
|
|
438
|
+
Hosted Anthropic `web_search` declarations (`web_search`, `web_search_20250305`,
|
|
439
|
+
and `web_search_20260209`, including `allowed_domains`, `user_location`,
|
|
440
|
+
`tool_choice: {"type": "tool", "name": "web_search"}`, and positive integer
|
|
441
|
+
`max_uses`, which is validated and accepted for Anthropic compatibility without
|
|
442
|
+
upstream enforcement) are supported when Classic Responses is active
|
|
443
|
+
(`responses_lite: false`, or `"auto"` on models that use Classic Responses) and
|
|
444
|
+
map to Codex hosted `web_search` with `web_search_call.action.sources`,
|
|
445
|
+
projecting `search`, `open_page`, and `find_in_page` `web_search_call` actions into
|
|
446
|
+
`server_tool_use` and `web_search_tool_result` blocks alongside
|
|
447
|
+
`usage.server_tool_use` (and preserving the raw `web_search_call` items on `/v1/responses`).
|
|
448
|
+
`blocked_domains` and `strict: true` on `web_search`,
|
|
449
|
+
or hosted `web_search` when Responses Lite is active, return HTTP 400. Replayed
|
|
450
|
+
`server_tool_use`, `web_search_tool_result`, text/content `document`, and
|
|
451
|
+
`search_result` blocks in conversation history are rendered into structured
|
|
452
|
+
text context.
|
|
444
453
|
|
|
445
454
|
Completed responses require authoritative final token usage and a real
|
|
446
455
|
`response.completed` event. Emitted function calls map to `tool_calls` or
|
|
@@ -512,7 +521,7 @@ curl http://localhost:18080/v1/messages/count_tokens \
|
|
|
512
521
|
|
|
513
522
|
### `POST /v1/messages/compact`
|
|
514
523
|
|
|
515
|
-
Anthropic-compatible alias for remote conversation compaction. Accepts Anthropic Messages-shaped bodies and returns compacted checkpoint content. Live GPT model IDs select the matching backend model, and Claude Code effort and Fast Mode controls use the same mappings as `/v1/messages`. Its
|
|
524
|
+
Anthropic-compatible alias for remote conversation compaction. Accepts Anthropic Messages-shaped bodies and returns compacted checkpoint content. Live GPT model IDs select the matching backend model, and Claude Code effort and Fast Mode controls use the same mappings as `/v1/messages`. Its optional non-forwarded `max_tokens` (validated as a positive integer when provided), sampling/stop compatibility fields (`temperature`, `top_p`, `top_k`, empty `stop_sequences: []`), `tool_choice`, and valid `cache_control` hints are accepted for every client; the optional Claude Code session header only supplies cache affinity.
|
|
516
525
|
|
|
517
526
|
### `POST /v1/images/generations`
|
|
518
527
|
|
|
@@ -661,7 +670,7 @@ Requests can instead use the Responses-shaped effort/context object:
|
|
|
661
670
|
- Responses Lite uses `all_turns` as the Codex wire default. An explicitly different context is rejected instead of silently overwritten; use `responses_lite: false` when the backend route supports classic Responses and another context is required.
|
|
662
671
|
- Remote compact keeps its existing private Codex `reasoning_effort` field but does not accept public `reasoning.mode` or `reasoning.context`.
|
|
663
672
|
|
|
664
|
-
Anthropic `thinking` values map as `enabled → high` and `adaptive → medium`. Disabled thinking selects `none` when available, otherwise the lowest supported catalog effort, and suppresses reasoning output; it does not claim to eliminate a model's internal reasoning. `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level disabled thinking takes precedence over ambient `output_config.effort` for auxiliary calls such as WebFetch. Explicit unsupported effort requests still fail. Hosted Anthropic
|
|
673
|
+
Anthropic `thinking` values map as `enabled → high` and `adaptive → medium`. Disabled thinking selects `none` when available, otherwise the lowest supported catalog effort, and suppresses reasoning output; it does not claim to eliminate a model's internal reasoning. `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level disabled thinking takes precedence over ambient `output_config.effort` for auxiliary calls such as WebFetch. Explicit unsupported effort requests still fail. Hosted Anthropic `web_search` declarations are bridged when Classic Responses is active (`responses_lite: false`, or `"auto"` on Classic-default models), while Responses Lite rejects hosted `web_search` with HTTP 400. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro, non-null public cache policy/breakpoints, and any supplied `safety_identifier` fail explicitly on the private Codex provider.
|
|
665
674
|
|
|
666
675
|
Anthropic's `JSONOutputFormat` carries a schema but no name. When Claude Code
|
|
667
676
|
sends that official shape, the proxy follows pinned Codex 0.153.3 and supplies
|
|
@@ -670,10 +679,11 @@ or fallback role. An explicit proxy-extension name is preserved only when it is
|
|
|
670
679
|
already a valid Responses format name, and is never sanitized or truncated.
|
|
671
680
|
|
|
672
681
|
The pinned official Codex HTTP request has no `stop` field. Omitted OpenAI
|
|
673
|
-
`stop`,
|
|
674
|
-
any
|
|
675
|
-
|
|
676
|
-
|
|
682
|
+
`stop`, explicit `stop: null`, and empty `stop: []` are omitted from the private
|
|
683
|
+
request as no-ops; any non-empty OpenAI `stop` value returns HTTP 400. Anthropic
|
|
684
|
+
`stop_sequences` allows omission and empty `stop_sequences: []`, while explicit
|
|
685
|
+
`stop_sequences: null` or any non-empty array returns HTTP 400 because the
|
|
686
|
+
private transport cannot apply stop sequences.
|
|
677
687
|
|
|
678
688
|
The mapping is intentionally transport-aware:
|
|
679
689
|
|
|
@@ -683,7 +693,7 @@ The mapping is intentionally transport-aware:
|
|
|
683
693
|
| `prompt_cache_key` | Forward an explicit value; otherwise use non-empty `client_metadata.session_id` |
|
|
684
694
|
| Non-null `prompt_cache_options` / breakpoint | HTTP 400; `null` is omitted and there is no private field |
|
|
685
695
|
| Any supplied `safety_identifier` | HTTP 400; the optional field is non-nullable and OAuth account/thread IDs are not semantic aliases |
|
|
686
|
-
| Non-
|
|
696
|
+
| Non-empty `stop` / `stop_sequences` (or `stop_sequences: null`) | HTTP 400; empty `[]` (and OpenAI `stop: null`) are omitted |
|
|
687
697
|
| `previous_response_id` | Resolve locally and replay complete Response history over HTTP |
|
|
688
698
|
| `service_tier: "fast"` | Send `service_tier: "priority"` |
|
|
689
699
|
| `service_tier: "default"` | Omit the field |
|
|
@@ -894,12 +904,15 @@ CODEX_AS_API_MODEL=gpt-5.6-terra \
|
|
|
894
904
|
codex-as-api
|
|
895
905
|
```
|
|
896
906
|
|
|
897
|
-
Claude Code hosted
|
|
898
|
-
|
|
899
|
-
|
|
900
|
-
|
|
901
|
-
|
|
902
|
-
|
|
907
|
+
Claude Code hosted `web_search` (`web_search`, `web_search_20250305`, and
|
|
908
|
+
`web_search_20260209`) is supported when Classic Responses is active
|
|
909
|
+
(`responses_lite: false`, or `"auto"` on models whose catalog sets Classic
|
|
910
|
+
Responses), mapping Codex `web_search` calls and `web_search_call.action.sources`
|
|
911
|
+
into Anthropic `server_tool_use` and `web_search_tool_result` blocks alongside
|
|
912
|
+
`usage.server_tool_use`. On Responses Lite models under `responses_lite: "auto"`,
|
|
913
|
+
hosted `web_search` returns HTTP 400 unless `responses_lite: false` is valid
|
|
914
|
+
and supplied. WebFetch remains a client-side auxiliary request and retains the
|
|
915
|
+
disabled-thinking precedence behavior when process-level effort is enabled.
|
|
903
916
|
|
|
904
917
|
To keep the built-in Fable, Opus, Sonnet, and Haiku rows and append one GPT row, launch the GPT-routed Claude Code process with these variables:
|
|
905
918
|
|
|
@@ -1008,9 +1021,9 @@ registry setup is still required:
|
|
|
1008
1021
|
After bumping every version and passing the local gate, push the matching tag:
|
|
1009
1022
|
|
|
1010
1023
|
```bash
|
|
1011
|
-
python scripts/check_package_versions.py --tag
|
|
1012
|
-
git tag
|
|
1013
|
-
git push origin
|
|
1024
|
+
python scripts/check_package_versions.py --tag v1.0.0
|
|
1025
|
+
git tag v1.0.0
|
|
1026
|
+
git push origin v1.0.0
|
|
1014
1027
|
```
|
|
1015
1028
|
|
|
1016
1029
|
## Tests
|
|
@@ -9,7 +9,7 @@ Use ChatGPT / Codex OAuth as a local OpenAI-compatible API server.
|
|
|
9
9
|
|
|
10
10
|
## Features
|
|
11
11
|
|
|
12
|
-
- **OpenAI & Anthropic compatible** — Chat Completions, Messages, and `GET /v1/models`
|
|
12
|
+
- **OpenAI & Anthropic compatible** — Responses (`/v1/responses`, `/v1/responses/compact`), Chat Completions, Messages, and `GET /v1/models`
|
|
13
13
|
- **Claude Code ready** — use Codex models directly from Claude Code CLI
|
|
14
14
|
- **Streaming** — full SSE streaming for both OpenAI and Anthropic protocols
|
|
15
15
|
- **Tool calling** — function calls, tool results, and parallel tool calls
|
|
@@ -357,7 +357,7 @@ it; continuation uses the complete provider Response items saved behind
|
|
|
357
357
|
|
|
358
358
|
Anthropic Messages compatibility endpoint for any client, including Claude Code and Scheherazade. It supports streaming (`stream: true`) and non-streaming without a client-identification header. A live Codex model ID routes directly. A `claude-*` facade ID uses the configured Codex backend model, or the authenticated catalog default when no backend model is configured. Other unknown IDs fail. The response preserves the client-supplied model name.
|
|
359
359
|
|
|
360
|
-
`max_tokens` is a required positive compatibility hint: the private Codex OAuth transport does not expose a matching output-token cap. Valid ephemeral `cache_control` hints are accepted and stripped for every client; their TTL and breakpoint semantics are not forwarded. An optional `x-claude-code-session-id` provides stable hashed cache affinity, not permission to use the endpoint. `metadata
|
|
360
|
+
`max_tokens` is a required positive compatibility hint: the private Codex OAuth transport does not expose a matching output-token cap. Valid ephemeral `cache_control` hints are accepted and stripped for every client; their TTL and breakpoint semantics are not forwarded. An optional `x-claude-code-session-id` provides stable hashed cache affinity, not permission to use the endpoint. Anthropic `metadata` objects with string or null entries (including `user_id` and additional client metadata keys) are accepted and not forwarded.
|
|
361
361
|
|
|
362
362
|
```bash
|
|
363
363
|
curl http://localhost:18080/v1/messages \
|
|
@@ -400,12 +400,21 @@ On the following assistant-history request, recognized envelopes restore the ori
|
|
|
400
400
|
|
|
401
401
|
Multiple summary parts share one thinking block per reasoning item. Encrypted-only items use an empty thinking string with a non-empty signature. Streaming sends `signature_delta` before the matching `content_block_stop`. `display: "omitted"` hides the summary but can preserve an encrypted-only signed block for continuity; disabled thinking suppresses thinking output. Items without encrypted content retain unsigned-summary compatibility behavior.
|
|
402
402
|
|
|
403
|
-
Hosted Anthropic `web_search` declarations
|
|
404
|
-
|
|
405
|
-
|
|
406
|
-
|
|
407
|
-
|
|
408
|
-
|
|
403
|
+
Hosted Anthropic `web_search` declarations (`web_search`, `web_search_20250305`,
|
|
404
|
+
and `web_search_20260209`, including `allowed_domains`, `user_location`,
|
|
405
|
+
`tool_choice: {"type": "tool", "name": "web_search"}`, and positive integer
|
|
406
|
+
`max_uses`, which is validated and accepted for Anthropic compatibility without
|
|
407
|
+
upstream enforcement) are supported when Classic Responses is active
|
|
408
|
+
(`responses_lite: false`, or `"auto"` on models that use Classic Responses) and
|
|
409
|
+
map to Codex hosted `web_search` with `web_search_call.action.sources`,
|
|
410
|
+
projecting `search`, `open_page`, and `find_in_page` `web_search_call` actions into
|
|
411
|
+
`server_tool_use` and `web_search_tool_result` blocks alongside
|
|
412
|
+
`usage.server_tool_use` (and preserving the raw `web_search_call` items on `/v1/responses`).
|
|
413
|
+
`blocked_domains` and `strict: true` on `web_search`,
|
|
414
|
+
or hosted `web_search` when Responses Lite is active, return HTTP 400. Replayed
|
|
415
|
+
`server_tool_use`, `web_search_tool_result`, text/content `document`, and
|
|
416
|
+
`search_result` blocks in conversation history are rendered into structured
|
|
417
|
+
text context.
|
|
409
418
|
|
|
410
419
|
Completed responses require authoritative final token usage and a real
|
|
411
420
|
`response.completed` event. Emitted function calls map to `tool_calls` or
|
|
@@ -477,7 +486,7 @@ curl http://localhost:18080/v1/messages/count_tokens \
|
|
|
477
486
|
|
|
478
487
|
### `POST /v1/messages/compact`
|
|
479
488
|
|
|
480
|
-
Anthropic-compatible alias for remote conversation compaction. Accepts Anthropic Messages-shaped bodies and returns compacted checkpoint content. Live GPT model IDs select the matching backend model, and Claude Code effort and Fast Mode controls use the same mappings as `/v1/messages`. Its
|
|
489
|
+
Anthropic-compatible alias for remote conversation compaction. Accepts Anthropic Messages-shaped bodies and returns compacted checkpoint content. Live GPT model IDs select the matching backend model, and Claude Code effort and Fast Mode controls use the same mappings as `/v1/messages`. Its optional non-forwarded `max_tokens` (validated as a positive integer when provided), sampling/stop compatibility fields (`temperature`, `top_p`, `top_k`, empty `stop_sequences: []`), `tool_choice`, and valid `cache_control` hints are accepted for every client; the optional Claude Code session header only supplies cache affinity.
|
|
481
490
|
|
|
482
491
|
### `POST /v1/images/generations`
|
|
483
492
|
|
|
@@ -626,7 +635,7 @@ Requests can instead use the Responses-shaped effort/context object:
|
|
|
626
635
|
- Responses Lite uses `all_turns` as the Codex wire default. An explicitly different context is rejected instead of silently overwritten; use `responses_lite: false` when the backend route supports classic Responses and another context is required.
|
|
627
636
|
- Remote compact keeps its existing private Codex `reasoning_effort` field but does not accept public `reasoning.mode` or `reasoning.context`.
|
|
628
637
|
|
|
629
|
-
Anthropic `thinking` values map as `enabled → high` and `adaptive → medium`. Disabled thinking selects `none` when available, otherwise the lowest supported catalog effort, and suppresses reasoning output; it does not claim to eliminate a model's internal reasoning. `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level disabled thinking takes precedence over ambient `output_config.effort` for auxiliary calls such as WebFetch. Explicit unsupported effort requests still fail. Hosted Anthropic
|
|
638
|
+
Anthropic `thinking` values map as `enabled → high` and `adaptive → medium`. Disabled thinking selects `none` when available, otherwise the lowest supported catalog effort, and suppresses reasoning output; it does not claim to eliminate a model's internal reasoning. `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level disabled thinking takes precedence over ambient `output_config.effort` for auxiliary calls such as WebFetch. Explicit unsupported effort requests still fail. Hosted Anthropic `web_search` declarations are bridged when Classic Responses is active (`responses_lite: false`, or `"auto"` on Classic-default models), while Responses Lite rejects hosted `web_search` with HTTP 400. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro, non-null public cache policy/breakpoints, and any supplied `safety_identifier` fail explicitly on the private Codex provider.
|
|
630
639
|
|
|
631
640
|
Anthropic's `JSONOutputFormat` carries a schema but no name. When Claude Code
|
|
632
641
|
sends that official shape, the proxy follows pinned Codex 0.153.3 and supplies
|
|
@@ -635,10 +644,11 @@ or fallback role. An explicit proxy-extension name is preserved only when it is
|
|
|
635
644
|
already a valid Responses format name, and is never sanitized or truncated.
|
|
636
645
|
|
|
637
646
|
The pinned official Codex HTTP request has no `stop` field. Omitted OpenAI
|
|
638
|
-
`stop`,
|
|
639
|
-
any
|
|
640
|
-
|
|
641
|
-
|
|
647
|
+
`stop`, explicit `stop: null`, and empty `stop: []` are omitted from the private
|
|
648
|
+
request as no-ops; any non-empty OpenAI `stop` value returns HTTP 400. Anthropic
|
|
649
|
+
`stop_sequences` allows omission and empty `stop_sequences: []`, while explicit
|
|
650
|
+
`stop_sequences: null` or any non-empty array returns HTTP 400 because the
|
|
651
|
+
private transport cannot apply stop sequences.
|
|
642
652
|
|
|
643
653
|
The mapping is intentionally transport-aware:
|
|
644
654
|
|
|
@@ -648,7 +658,7 @@ The mapping is intentionally transport-aware:
|
|
|
648
658
|
| `prompt_cache_key` | Forward an explicit value; otherwise use non-empty `client_metadata.session_id` |
|
|
649
659
|
| Non-null `prompt_cache_options` / breakpoint | HTTP 400; `null` is omitted and there is no private field |
|
|
650
660
|
| Any supplied `safety_identifier` | HTTP 400; the optional field is non-nullable and OAuth account/thread IDs are not semantic aliases |
|
|
651
|
-
| Non-
|
|
661
|
+
| Non-empty `stop` / `stop_sequences` (or `stop_sequences: null`) | HTTP 400; empty `[]` (and OpenAI `stop: null`) are omitted |
|
|
652
662
|
| `previous_response_id` | Resolve locally and replay complete Response history over HTTP |
|
|
653
663
|
| `service_tier: "fast"` | Send `service_tier: "priority"` |
|
|
654
664
|
| `service_tier: "default"` | Omit the field |
|
|
@@ -859,12 +869,15 @@ CODEX_AS_API_MODEL=gpt-5.6-terra \
|
|
|
859
869
|
codex-as-api
|
|
860
870
|
```
|
|
861
871
|
|
|
862
|
-
Claude Code hosted
|
|
863
|
-
|
|
864
|
-
|
|
865
|
-
|
|
866
|
-
|
|
867
|
-
|
|
872
|
+
Claude Code hosted `web_search` (`web_search`, `web_search_20250305`, and
|
|
873
|
+
`web_search_20260209`) is supported when Classic Responses is active
|
|
874
|
+
(`responses_lite: false`, or `"auto"` on models whose catalog sets Classic
|
|
875
|
+
Responses), mapping Codex `web_search` calls and `web_search_call.action.sources`
|
|
876
|
+
into Anthropic `server_tool_use` and `web_search_tool_result` blocks alongside
|
|
877
|
+
`usage.server_tool_use`. On Responses Lite models under `responses_lite: "auto"`,
|
|
878
|
+
hosted `web_search` returns HTTP 400 unless `responses_lite: false` is valid
|
|
879
|
+
and supplied. WebFetch remains a client-side auxiliary request and retains the
|
|
880
|
+
disabled-thinking precedence behavior when process-level effort is enabled.
|
|
868
881
|
|
|
869
882
|
To keep the built-in Fable, Opus, Sonnet, and Haiku rows and append one GPT row, launch the GPT-routed Claude Code process with these variables:
|
|
870
883
|
|
|
@@ -973,9 +986,9 @@ registry setup is still required:
|
|
|
973
986
|
After bumping every version and passing the local gate, push the matching tag:
|
|
974
987
|
|
|
975
988
|
```bash
|
|
976
|
-
python scripts/check_package_versions.py --tag
|
|
977
|
-
git tag
|
|
978
|
-
git push origin
|
|
989
|
+
python scripts/check_package_versions.py --tag v1.0.0
|
|
990
|
+
git tag v1.0.0
|
|
991
|
+
git push origin v1.0.0
|
|
979
992
|
```
|
|
980
993
|
|
|
981
994
|
## Tests
|
|
@@ -1,5 +1,15 @@
|
|
|
1
1
|
# Release Notes
|
|
2
2
|
|
|
3
|
+
## v1.0.0
|
|
4
|
+
|
|
5
|
+
### Native OpenAI Responses HTTP endpoints, hosted Anthropic WebSearch bridge, and SDK default compatibility across Python, TypeScript, and Rust
|
|
6
|
+
|
|
7
|
+
- Add native OpenAI Responses HTTP endpoints (`POST /v1/responses` for streaming and non-streaming responses and `POST /v1/responses/compact` for remote compaction) across Python, TypeScript, and Rust (`create_response`/`create_responses_stream`/`compact_responses`, `createResponse`/`createResponsesStream`/`compactResponses`, and `create_native_response`/`stream_prepared_native_responses`/`compact_native_responses` on `ChatGPTOAuthProvider`), including local `previous_response_id` chain replay/commit (including `input: []` continuations), `reasoning.summary` (`auto`, `concise`, `detailed`, `none`), `subagent`/`memgen_request` headers, function and hosted `web_search` tool normalization, and synthesized `output_text`.
|
|
8
|
+
- Bridge hosted Anthropic `web_search` tools (`web_search`, `web_search_20250305`, `web_search_20260209`, including `allowed_domains`, `user_location`, `tool_choice: {"type": "tool", "name": "web_search"}`, and positive integer `max_uses` validated and accepted for Anthropic compatibility without upstream enforcement) on Classic Responses (`responses_lite: false` or `"auto"` when the selected model uses Classic Responses) to Codex hosted `web_search` with `include: ["web_search_call.action.sources"]`, and map upstream `web_search_call` items (`search` including multi-query `action.queries`, `open_page`, and `find_in_page` actions) into Anthropic `server_tool_use` and `web_search_tool_result` blocks plus `usage.server_tool_use` while preserving raw `web_search_call` items on `/v1/responses`.
|
|
9
|
+
- Accept replayed Anthropic `document` (plain-text/content sources), `search_result`, `server_tool_use`, and `web_search_tool_result` content blocks in user, assistant, and `tool_result` message history by rendering structured text representations instead of rejecting multi-turn conversations.
|
|
10
|
+
- Accept standard SDK default/no-op controls that match Codex OAuth behavior: empty `stop: []` and `stop_sequences: []`, `store: false`, `user` metadata on `/v1/chat/completions` and `/v1/images/generations`, `stream_options: {"include_usage": true | false | null}` on streaming endpoints (and `stream_options: null`), Anthropic `metadata` objects with arbitrary string or `null` entries, and `citations: []` or `{"enabled": false}` on Anthropic content blocks.
|
|
11
|
+
- Accept full Anthropic `MessageCreateParams` envelopes on `POST /v1/messages/count_tokens` and `POST /v1/messages/compact` (`temperature`, `top_p`, `top_k`, `stop_sequences`, all valid `tool_choice` variants, and optional `max_tokens` on `/v1/messages/compact`) so callers can pass their existing request payload directly.
|
|
12
|
+
|
|
3
13
|
## v0.10.2
|
|
4
14
|
|
|
5
15
|
### Realtime call & sideband deadlines and cross-runtime parity fixes
|