release: 2.2.0 (#238)

* docs: swap examples used in readme (#231)

* chore(internal): slight transform perf improvement (#233)

* chore(internal): expand CI branch coverage (#235)

* chore(internal): reduce CI branch coverage

* fix(perf): skip traversing types for NotGiven values

* fix(perf): optimize some hot paths

* chore(internal): update pyright settings

* chore(client): minor internal fixes

* chore(internal): bump pyright version

* chore(internal): base client updates

* chore(internal): update models test

* docs(api): updates to API spec

* feat(api): add translation endpoint

* codegen metadata

* chore(ci): add timeout thresholds for CI jobs

* chore(internal): import reformatting

* chore(internal): fix list file params

* chore(internal): refactor retries to not use recursion

* docs(api): updates to API spec

* fix(pydantic v1): more robust ModelField.annotation check

* feat(api): add ai detect tool endpoint

* chore(internal): minor formatting changes

* chore(ci): run on more branches and use depot runners

* chore(ci): only use depot for staging repos

* chore: broadly detect json family of content-type headers

* docs(api): updates to API spec

* docs(api): updates to API spec

* feat(chat): add parse method (#237)

Co-authored-by: Robert Craigie <robert@craigie.dev>

* docs(api): updates to API spec

* test: Add translation_data to chat completions data. (#239)

* docs: README updates

* docs: Update models in README.

* release: 2.2.0

---------

Co-authored-by: stainless-app[bot] <142633134+stainless-app[bot]@users.noreply.github.com>
Co-authored-by: Robert Craigie <robert@craigie.dev>
Co-authored-by: Sarah Deaton <sarah.deaton@writer.com>

Author: 3 people

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.2.0-rc1"
+  ".": "2.2.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 32
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/writerai%2Fwriter-a0e83ebfd81856b538d16c7a41ccdc11687ee558e1435a40f3bb7e0d6e1ab7c8.yml
-openapi_spec_hash: 8ac62303a9158c13f344975cb0786bc6
-config_hash: b1d3b26784527ee46af49c1bb9e93193
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/writerai%2Fwriter-07dea48ea85e600712dcdfd99a688f6a9cb8dd1f56d0a06e0ab54fc8a98a89b1.yml
+openapi_spec_hash: 0d30ab04c227bf53f3109dc4d861e5dc
+config_hash: c0c9f57ab19252f82cf765939edc61de

CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## 2.2.0 (2025-04-30)
+
+Full Changelog: [v2.2.0-rc1...v2.2.0](https://github.com/writer/writer-python/compare/v2.2.0-rc1...v2.2.0)
+
+### Documentation
+
+* **api:** updates to API spec ([0236e86](https://github.com/writer/writer-python/commit/0236e8698e48b393dbb711f91e76fef66007d724))
+* README updates ([c85f8b5](https://github.com/writer/writer-python/commit/c85f8b591d27e4f0b2ff1ff01532aa31c4b62f7b))
+* Update models in README. ([da7e11a](https://github.com/writer/writer-python/commit/da7e11a9c62d971253efc83550557be37864fabb))
+
 ## 2.2.0-rc1 (2025-04-25)
 
 Full Changelog: [v2.1.0...v2.2.0-rc1](https://github.com/writer/writer-python/compare/v2.1.0...v2.2.0-rc1)

README.md

@@ -18,7 +18,7 @@ To install the package from PyPI, use `pip`:
 
 ```sh
 # install from PyPI
-pip install --pre writer-sdk
+pip install writer-sdk
 ```
 
 ## Prequisites
@@ -75,7 +75,7 @@ chat_completion = client.chat.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
 )
 print(chat_completion.choices[0].message.content)
 ```
@@ -97,7 +97,7 @@ async def main() -> None:
                 "role": "user",
             }
         ],
-        model="palmyra-x-004",
+        model="palmyra-x5",
     )
     print(chat_completion.choices[0].message.content)
 
@@ -125,7 +125,7 @@ stream = client.chat.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
     stream=True,
 )
 
@@ -153,7 +153,7 @@ stream = await client.chat.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
     stream=True,
 )
 
@@ -174,7 +174,7 @@ The SDK also includes helpers to process streams and handle incoming events.
 
 ```python
 with client.chat.stream(
-    model="palmyra-x-004",
+    model="palmyra-x5",
     messages=[{"role": "user", "content": prompt}],
 ) as stream:
     for event in stream:
@@ -308,7 +308,7 @@ try:
                 "role": "user",
             }
         ],
-        model="palmyra-x-004",
+        model="palmyra-x5",
     )
 except writerai.APIConnectionError as e:
     print("The server could not be reached")
@@ -359,7 +359,7 @@ client.with_options(max_retries=5).chat.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
 )
 ```
 
@@ -391,7 +391,7 @@ client.with_options(timeout=5.0).chat.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
 )
 ```
 
@@ -440,7 +440,7 @@ response = client.chat.with_raw_response.chat(
         "content": "Write a haiku about programming",
         "role": "user",
     }],
-    model="palmyra-x-004",
+    model="palmyra-x5",
 )
 print(response.headers.get('X-My-Header'))
 
@@ -464,7 +464,7 @@ with client.chat.with_streaming_response.chat(
             "role": "user",
         }
     ],
-    model="palmyra-x-004",
+    model="palmyra-x5",
 ) as response:
     print(response.headers.get("X-My-Header"))
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "writer-sdk"
-version = "2.2.0-rc1"
+version = "2.2.0"
 description = "The official Python library for the writer API"
 dynamic = ["readme"]
 license = "Apache-2.0"

src/writerai/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "writerai"
-__version__ = "2.2.0-rc1"  # x-release-please-version
+__version__ = "2.2.0"  # x-release-please-version

src/writerai/resources/chat.py

@@ -93,8 +93,8 @@ def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           logprobs: Specifies whether to return log probabilities of the output tokens.
 
@@ -106,8 +106,8 @@ def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -133,11 +133,11 @@ def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with
@@ -189,8 +189,8 @@ def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           stream: Indicates whether the response should be streamed incrementally as it is
               generated or only returned once fully complete. Streaming can be useful for
@@ -206,8 +206,8 @@ def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -229,11 +229,11 @@ def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with
@@ -285,8 +285,8 @@ def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           stream: Indicates whether the response should be streamed incrementally as it is
               generated or only returned once fully complete. Streaming can be useful for
@@ -302,8 +302,8 @@ def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -325,11 +325,11 @@ def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with
@@ -634,8 +634,8 @@ async def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           logprobs: Specifies whether to return log probabilities of the output tokens.
 
@@ -647,8 +647,8 @@ async def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -674,11 +674,11 @@ async def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with
@@ -730,8 +730,8 @@ async def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           stream: Indicates whether the response should be streamed incrementally as it is
               generated or only returned once fully complete. Streaming can be useful for
@@ -747,8 +747,8 @@ async def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -770,11 +770,11 @@ async def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with
@@ -826,8 +826,8 @@ async def chat(
               the model to respond to. The array must contain at least one message.
 
           model: The [ID of the model](https://dev.writer.com/home/models) to use for creating
-              the chat completion. Supports `palmyra-x-004`, `palmyra-fin`, `palmyra-med`,
-              `palmyra-creative`, and `palmyra-x-003-instruct`.
+              the chat completion. Supports `palmyra-x5`, `palmyra-x4`, `palmyra-fin`,
+              `palmyra-med`, `palmyra-creative`, and `palmyra-x-003-instruct`.
 
           stream: Indicates whether the response should be streamed incrementally as it is
               generated or only returned once fully complete. Streaming can be useful for
@@ -843,8 +843,8 @@ async def chat(
               single request. This parameter allows for generating multiple responses,
               offering a variety of potential replies from which to choose.
 
-          response_format: The response format to use for the chat completion, available with
-              `palmyra-x-004`.
+          response_format: The response format to use for the chat completion, available with `palmyra-x4`
+              and `palmyra-x5`.
 
               `text` is the default response format. [JSON Schema](https://json-schema.org/)
               is supported for structured responses. If you specify `json_schema`, you must
@@ -866,11 +866,11 @@ async def chat(
 
           tools: An array containing tool definitions for tools that the model can use to
               generate responses. The tool definitions use JSON schema. You can define your
-              own functions or use one of the built-in `graph`, `llm`, or `vision` tools. Note
-              that you can only use one built-in tool type in the array (only one of `graph`,
-              `llm`, or `vision`). You can pass multiple custom
-              tools](https://dev.writer.com/api-guides/tool-calling) of type `function` in the
-              same request.
+              own functions or use one of the built-in `graph`, `llm`, `translation`, or
+              `vision` tools. Note that you can only use one built-in tool type in the array
+              (only one of `graph`, `llm`, `translation`, or `vision`). You can pass multiple
+              [custom tools](https://dev.writer.com/api-guides/tool-calling) of type
+              `function` in the same request.
 
           top_p: Sets the threshold for "nucleus sampling," a technique to focus the model's
               token generation on the most likely subset of tokens. Only tokens with