codex-as-api 0.6.2__tar.gz → 0.6.3__tar.gz

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codex-as-api
-Version: 0.6.2
+Version: 0.6.3
 Summary: Use ChatGPT/Codex OAuth as a local OpenAI-compatible API server.
 Project-URL: Homepage, https://github.com/Eunho-J/codex-as-api
 Project-URL: Repository, https://github.com/Eunho-J/codex-as-api
@@ -444,7 +444,7 @@ GPT-5.6 requests can instead use the public Responses-shaped object:
 - 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.
 - Remote compact keeps its existing private Codex `reasoning_effort` field but does not accept public `reasoning.mode` or `reasoning.context`.
 
-Anthropic `thinking` values map as `enabled → high`, `adaptive → medium`, and `disabled → none`. Claude Code's `output_config.effort` takes precedence over the adaptive default and supports `low`, `medium`, `high`, `xhigh`, and `max`. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro and non-null public cache policy/breakpoints or `safety_identifier` fail explicitly on the private Codex provider.
+Anthropic `thinking` values map as `enabled → high`, `adaptive → medium`, and `disabled → none`. Claude Code's `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level `thinking.disabled` takes precedence over ambient `output_config.effort`, so Claude Code WebSearch/WebFetch auxiliary calls use `none` instead of failing the compatibility check with HTTP 400. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro and non-null public cache policy/breakpoints or `safety_identifier` fail explicitly on the private Codex provider.
 
 The pinned official Codex HTTP request has no `stop` field. Omitted, `null`, and empty stop values are omitted from the private request; any non-empty OpenAI `stop` or Anthropic `stop_sequences` value returns HTTP 400 before the private transport starts.
 
@@ -647,9 +647,13 @@ The `/v1/messages` endpoint implements the Anthropic Messages gateway shape used
 Start the proxy first. `CODEX_AS_API_MODEL` is the fallback used when Claude Code sends a built-in Anthropic model name:
 
 ```bash
-CODEX_AS_API_MODEL=gpt-5.6-terra codex-as-api
+CODEX_AS_API_MODEL=gpt-5.6-terra \
+CODEX_AS_API_RESPONSES_LITE=off \
+codex-as-api
 ```
 
+`CODEX_AS_API_RESPONSES_LITE=off` is required for Claude Code hosted WebSearch on GPT-5.6. Official Codex Responses Lite uses a client-side standalone `web.run` tool, while this gateway receives Anthropic's hosted `web_search` declaration and has no standalone executor; classic Responses preserves that hosted tool. WebFetch does not use a hosted Responses tool, but still needs the disabled-thinking precedence fix when process-level effort is enabled.
+
 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:
 
 ```bash
@@ -720,7 +724,7 @@ The provider handles:
 ## Release & package publishing
 
 - Bump versions in `pyproject.toml`, `src/codex_as_api/__init__.py`, `src/codex_as_api/server.py`, `ts/package.json`, `ts/package-lock.json`, `rust/Cargo.toml`, and `rust/Cargo.lock`.
-- Publish a GitHub Release such as `v0.6.2` from the matching commit.
+- Publish a GitHub Release such as `v0.6.3` from the matching commit.
 - The manually-dispatched `Publish npm packages` workflow builds/tests the TypeScript package, runs `npm pack --dry-run`, publishes `codex-as-api` to npmjs when `NPM_TOKEN` is configured, and publishes `@eunho-j/codex-as-api` to GitHub Packages with `GITHUB_TOKEN`.
 
 Publishing to npmjs requires an authenticated npm session (`npm login` beforehand; `npm whoami` should succeed). From the repository root, the publish itself is one command:
@@ -763,6 +767,14 @@ npm test
 
 ## Release Notes
 
+### v0.6.3
+
+- Accept Claude Code auxiliary requests that combine ambient `output_config.effort` with call-level `thinking.disabled`.
+- Give explicit disabled thinking precedence and send Codex reasoning effort `none` instead of returning HTTP 400.
+- Document and test `CODEX_AS_API_RESPONSES_LITE=off` for Claude Code hosted WebSearch on GPT-5.6; WebFetch needs no Responses Lite override.
+- Preserve fail-loudly validation for invalid effort values and unsupported `output_config` fields.
+- Add Python, TypeScript, and Rust adapter regressions, streamed `/v1/messages` coverage, and a `/count_tokens` regression for the WebSearch/WebFetch request shape.
+
 ### v0.6.2
 
 - Fix `/v1/messages/count_tokens` overcounting that could trigger Claude Code autocompaction on every turn.

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/README.md

@@ -410,7 +410,7 @@ GPT-5.6 requests can instead use the public Responses-shaped object:
 - 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.
 - Remote compact keeps its existing private Codex `reasoning_effort` field but does not accept public `reasoning.mode` or `reasoning.context`.
 
-Anthropic `thinking` values map as `enabled → high`, `adaptive → medium`, and `disabled → none`. Claude Code's `output_config.effort` takes precedence over the adaptive default and supports `low`, `medium`, `high`, `xhigh`, and `max`. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro and non-null public cache policy/breakpoints or `safety_identifier` fail explicitly on the private Codex provider.
+Anthropic `thinking` values map as `enabled → high`, `adaptive → medium`, and `disabled → none`. Claude Code's `output_config.effort` takes precedence over adaptive or enabled thinking and supports `low`, `medium`, `high`, `xhigh`, and `max`. Call-level `thinking.disabled` takes precedence over ambient `output_config.effort`, so Claude Code WebSearch/WebFetch auxiliary calls use `none` instead of failing the compatibility check with HTTP 400. The supported reasoning context and verbosity extensions are also available on `/v1/messages`, image generation, and inspection requests; Pro and non-null public cache policy/breakpoints or `safety_identifier` fail explicitly on the private Codex provider.
 
 The pinned official Codex HTTP request has no `stop` field. Omitted, `null`, and empty stop values are omitted from the private request; any non-empty OpenAI `stop` or Anthropic `stop_sequences` value returns HTTP 400 before the private transport starts.
 
@@ -613,9 +613,13 @@ The `/v1/messages` endpoint implements the Anthropic Messages gateway shape used
 Start the proxy first. `CODEX_AS_API_MODEL` is the fallback used when Claude Code sends a built-in Anthropic model name:
 
 ```bash
-CODEX_AS_API_MODEL=gpt-5.6-terra codex-as-api
+CODEX_AS_API_MODEL=gpt-5.6-terra \
+CODEX_AS_API_RESPONSES_LITE=off \
+codex-as-api
 ```
 
+`CODEX_AS_API_RESPONSES_LITE=off` is required for Claude Code hosted WebSearch on GPT-5.6. Official Codex Responses Lite uses a client-side standalone `web.run` tool, while this gateway receives Anthropic's hosted `web_search` declaration and has no standalone executor; classic Responses preserves that hosted tool. WebFetch does not use a hosted Responses tool, but still needs the disabled-thinking precedence fix when process-level effort is enabled.
+
 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:
 
 ```bash
@@ -686,7 +690,7 @@ The provider handles:
 ## Release & package publishing
 
 - Bump versions in `pyproject.toml`, `src/codex_as_api/__init__.py`, `src/codex_as_api/server.py`, `ts/package.json`, `ts/package-lock.json`, `rust/Cargo.toml`, and `rust/Cargo.lock`.
-- Publish a GitHub Release such as `v0.6.2` from the matching commit.
+- Publish a GitHub Release such as `v0.6.3` from the matching commit.
 - The manually-dispatched `Publish npm packages` workflow builds/tests the TypeScript package, runs `npm pack --dry-run`, publishes `codex-as-api` to npmjs when `NPM_TOKEN` is configured, and publishes `@eunho-j/codex-as-api` to GitHub Packages with `GITHUB_TOKEN`.
 
 Publishing to npmjs requires an authenticated npm session (`npm login` beforehand; `npm whoami` should succeed). From the repository root, the publish itself is one command:
@@ -729,6 +733,14 @@ npm test
 
 ## Release Notes
 
+### v0.6.3
+
+- Accept Claude Code auxiliary requests that combine ambient `output_config.effort` with call-level `thinking.disabled`.
+- Give explicit disabled thinking precedence and send Codex reasoning effort `none` instead of returning HTTP 400.
+- Document and test `CODEX_AS_API_RESPONSES_LITE=off` for Claude Code hosted WebSearch on GPT-5.6; WebFetch needs no Responses Lite override.
+- Preserve fail-loudly validation for invalid effort values and unsupported `output_config` fields.
+- Add Python, TypeScript, and Rust adapter regressions, streamed `/v1/messages` coverage, and a `/count_tokens` regression for the WebSearch/WebFetch request shape.
+
 ### v0.6.2
 
 - Fix `/v1/messages/count_tokens` overcounting that could trigger Claude Code autocompaction on every turn.

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/RELEASES.md

@@ -1,5 +1,20 @@
 # Release Notes
 
+## v0.6.3
+
+### Claude Code WebSearch/WebFetch auxiliary calls
+
+- Fix HTTP 400 responses when a Claude Code session with ambient effort sends a WebSearch/WebFetch auxiliary request containing both `output_config.effort` and call-level `thinking: {"type":"disabled"}`.
+- Give explicit disabled thinking precedence over valid ambient effort and forward Codex reasoning effort `none` across Python, TypeScript, and Rust.
+- Require and document `CODEX_AS_API_RESPONSES_LITE=off` for Claude Code hosted WebSearch on GPT-5.6 because official Responses Lite relies on a standalone `web.run` executor; WebFetch does not require this override.
+- Continue rejecting empty, non-string, or unsupported effort values and unsupported `output_config` fields rather than silently discarding malformed requests.
+
+### Validation
+
+- Adapter tests cover every valid Claude Code effort value paired with disabled thinking while retaining invalid-value failures.
+- Streamed `/v1/messages` tests across all three runtimes and a local `/count_tokens` test reproduce the Claude Code 2.1.209 request shape and prove provider-backed requests reach the classic Codex wire with reasoning effort `none`.
+- A real GPT-5.6 Sol Codex OAuth WebSearch completed with HTTP 200 and structured `server_tool_use`, `web_search_tool_result`, and terminal SSE events.
+
 ## v0.6.2
 
 ### Claude Code count_tokens autocompact fix
@@ -9,7 +24,7 @@
 - Count tool calls, tool-result identifiers, reasoning content, and normalized tool schemas once while excluding model IDs, output limits, stream flags, metadata, and other non-model request controls.
 - Keep the existing image estimate separate so URL and inline base64 images are counted once without tokenizing the base64 payload as text.
 - Keep token counting local and OAuth-free. No `tiktoken` package dependency or first-run encoding download is introduced.
-- Record the upstream synchronization point as `tiktoken` 0.13.0 commit `08a5f3b2c987ada4fc5aa1f16c643c203fa8acaa`, checked on 2026-07-14, with the official rank-file SHA-256 verified in packaged builds.
+- Record the upstream synchronization point as `tiktoken` 0.13.0 commit `08a5f3b2c987ada4fc5aa1f16c643c203fa8acaa`, checked on 2026-07-14, with the official rank-file SHA-256 verified during release validation.
 
 ### Validation
 

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "codex-as-api"
-version = "0.6.2"
+version = "0.6.3"
 description = "Use ChatGPT/Codex OAuth as a local OpenAI-compatible API server."
 readme = "README.md"
 license = { text = "Apache-2.0" }

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/src/codex_as_api/__init__.py

@@ -1,3 +1,3 @@
 """codex-as-api: Use ChatGPT/Codex OAuth as a local OpenAI-compatible API server."""
 
-__version__ = "0.6.2"
+__version__ = "0.6.3"

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/src/codex_as_api/anthropic_adapter.py

@@ -341,13 +341,19 @@ def _convert_reasoning_effort(thinking: dict[str, Any] | None, output_config: ob
             raise ValueError("output_config.task_budget is not supported by the Codex OAuth backend")
         raw_effort = output_config.get("effort")
         if raw_effort is not None:
-            if raw_effort not in {"low", "medium", "high", "xhigh", "max"}:
+            if not isinstance(raw_effort, str) or raw_effort not in {
+                "low",
+                "medium",
+                "high",
+                "xhigh",
+                "max",
+            }:
                 raise ValueError("output_config.effort must be one of: low, medium, high, xhigh, max")
             output_effort = raw_effort
 
     thinking_effort = _convert_thinking(thinking)
-    if thinking_effort == "none" and output_effort is not None:
-        raise ValueError("output_config.effort cannot be represented together with thinking.disabled")
+    if thinking_effort == "none":
+        return "none"
     return output_effort or thinking_effort
 
 

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/src/codex_as_api/server.py

@@ -140,7 +140,7 @@ try:
     app = FastAPI(
         title="codex-as-api",
         description="Local OpenAI-compatible API server backed by ChatGPT/Codex OAuth.",
-        version="0.6.2",
+        version="0.6.3",
     )
 
     @app.exception_handler(ChatGPTOAuthError)

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/tests/test_anthropic_adapter.py

@@ -392,13 +392,34 @@ class TestAnthropicRequestToInternal:
         )
         assert converted == effort
 
-    def test_output_config_effort_conflicts_with_disabled_thinking(self):
-        with pytest.raises(ValueError, match="thinking.disabled"):
+    @pytest.mark.parametrize("effort", ["low", "medium", "high", "xhigh", "max"])
+    def test_disabled_thinking_overrides_output_config_effort(self, effort):
+        _, _, _, _, converted, _ = anthropic_request_to_internal(
+            model="test",
+            messages=[{"role": "user", "content": "hi"}],
+            thinking={"type": "disabled"},
+            output_config={"effort": effort},
+        )
+        assert converted == "none"
+
+    def test_disabled_thinking_preserves_output_config_format(self):
+        _, _, _, _, converted, text = anthropic_request_to_internal(
+            model="test",
+            messages=[{"role": "user", "content": "hi"}],
+            thinking={"type": "disabled"},
+            output_config={"effort": "high", "format": {"type": "json_object"}},
+        )
+        assert converted == "none"
+        assert text == {"format": {"type": "json_object"}}
+
+    @pytest.mark.parametrize("effort", ["", 1, [], {}, "ultra"])
+    def test_disabled_thinking_does_not_bypass_output_config_effort_validation(self, effort):
+        with pytest.raises(ValueError, match="output_config.effort"):
             anthropic_request_to_internal(
                 model="test",
                 messages=[{"role": "user", "content": "hi"}],
                 thinking={"type": "disabled"},
-                output_config={"effort": "high"},
+                output_config={"effort": effort},
             )
 
     def test_output_config_task_budget_fails_loudly(self):

{codex_as_api-0.6.2 → codex_as_api-0.6.3}/tests/test_server.py

@@ -1569,6 +1569,30 @@ def test_messages_count_tokens_counts_normalized_tools_without_provider_call(cli
     assert body["context_window"] >= body["auto_compact_token_limit"]
 
 
+def test_messages_count_tokens_accepts_disabled_thinking_with_ambient_effort(client, monkeypatch):
+    import codex_as_api.server as server_mod
+
+    def fail_provider_call():
+        raise AssertionError("count_tokens must not call the Codex backend")
+
+    monkeypatch.setattr(server_mod, "_get_provider", fail_provider_call)
+    response = client.post(
+        "/v1/messages/count_tokens",
+        json={
+            "model": "gpt-5.6-sol",
+            "max_tokens": 1024,
+            "stream": True,
+            "messages": [{"role": "user", "content": "search the web"}],
+            "tools": [{"type": "web_search_20250305", "name": "web_search"}],
+            "thinking": {"type": "disabled"},
+            "output_config": {"effort": "high"},
+        },
+    )
+
+    assert response.status_code == 200, response.text
+    assert response.json()["input_tokens"] > 0
+
+
 def test_messages_count_tokens_large_ascii_payload_is_not_double_counted(client):
     resp = client.post(
         "/v1/messages/count_tokens",
@@ -2088,6 +2112,40 @@ def test_anthropic_latest_claude_code_shape_routes_known_gpt_effort_and_fast_mod
     assert "speed" not in outbound
 
 
+def test_anthropic_disabled_thinking_overrides_ambient_effort_for_web_auxiliary_stream(
+    client,
+    recording_backend: RecordingBackend,
+    monkeypatch,
+):
+    monkeypatch.setenv(RESPONSES_LITE_ENV, "off")
+    response = client.post(
+        "/v1/messages",
+        json={
+            "model": "gpt-5.6-sol",
+            "max_tokens": 1024,
+            "stream": True,
+            "system": "system",
+            "messages": [{"role": "user", "content": "search the web"}],
+            "tools": [{"type": "web_search_20250305", "name": "web_search"}],
+            "thinking": {"type": "disabled"},
+            "output_config": {"effort": "high"},
+        },
+    )
+
+    assert response.status_code == 200, response.text
+    outbound = recording_backend.requests.get(timeout=1)["body"]
+    assert outbound["reasoning"]["effort"] == "none"
+    assert "context" not in outbound["reasoning"]
+    assert outbound["tools"] == [{"type": "web_search", "external_web_access": True}]
+    events = [
+        json.loads(line.removeprefix("data: "))
+        for line in response.text.splitlines()
+        if line.startswith("data: {")
+    ]
+    assert events[0]["type"] == "message_start"
+    assert events[-1]["type"] == "message_stop"
+
+
 def test_anthropic_output_config_format_reaches_codex_text_format(
     client,
     recording_backend: RecordingBackend,
@@ -2251,6 +2309,7 @@ def test_anthropic_unrepresentable_latest_controls_fail_before_upstream(
 @pytest.mark.parametrize(
     "unsupported",
     [
+        {"thinking": {"type": "disabled"}, "output_config": {"effort": []}},
         {"output_config": {"format": "json"}},
         {"output_config": {"format": {"type": "json_object", "extra": True}}},
         {
@@ -2267,7 +2326,7 @@ def test_anthropic_unrepresentable_latest_controls_fail_before_upstream(
         },
     ],
 )
-def test_anthropic_routes_reject_invalid_formats_and_unknown_image_sources(
+def test_anthropic_routes_reject_invalid_controls_and_unknown_image_sources(
     client,
     recording_backend: RecordingBackend,
     route,