feat: sync generated types with schemas v0.22.0

[inference-gateway-maintainer]

Deterministic type sync from inference-gateway/schemas at v0.22.0.

Regenerated with task oas-sync SCHEMAS_REF=refs/tags/v0.22.0 by the org schemas-sync reusable workflow. Re-runs update this PR in place; it closes automatically if the repo is back in sync.

If the new types need follow-up implementation (client surface, examples, docs), comment @claude or @infer on this PR with instructions.

[edenreich]

@infer types were modified? anything we need to change in the code? examples? use /ponytail:ponytail

[inference-gateway-maintainer]

Model: ollama_cloud/deepseek-v4-flash:preview · View Job

Todos

• Review the full diff to understand what types changed
• Check if client code or examples need updates for the new types
• Export new Modality and ModelModalities types from init.py
• Run checks and commit

Pull Request

#106

✅ Infer Result: Success

Here's the ponytail review of the schemas v0.22.0 sync:

What changed in the types

The Model.modalities field changed from a flat list of strings:

modalities: Sequence[Literal["text", "image", "audio", "video"]] | None = None

to a structured object with input/output:

modalities: ModelModalities | None = None
# ModelModalities has: input: Sequence[Modality], output: Sequence[Modality]

Two new types: Modality (RootModel wrapping the Literal) and ModelModalities.

What needed to change

Only __init__.py - the new Modality and ModelModalities types weren't exported. Users accessing model.modalities.input couldn't reference the types. Fixed in commit a516fd8.

What did NOT need to change

• Client code (client.py): No direct modalities manipulation. list_models() returns ListModelsResponse which contains Model objects - the client just passes through the API response.
• Examples (examples/list/main.py): Just prints the response. The output will naturally show the new {input: [...], output: [...]} structure.
• Tests: No tests reference modalities at all.
• openapi.yaml: Already updated by the sync PR itself.

Skipped: nothing else. The types are generated code, the client is a pass-through, the examples are print-and-forget. Two lines of exports was the full diff.

Model: ollama_cloud/deepseek-v4-flash:preview · Exit Code: 0 · Duration: 1m 26s

Tokens: 878,687 in · 4,221 out · 882,908 total (20 requests)

Tool calls: 24 total · 88% success rate

Traces

Session: 1785962311-2d96c670

session (standard, success)                                        1m18s
├── chat ollama_cloud/deepseek-v4-flash:preview                     6.3s
│   ╰── POST /v1/chat/completions [inference-gateway]               6.3s
│       ╰── HTTP POST [inference-gateway]                           6.3s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     6.3s
│               ╰── HTTP POST [inference-gateway]                   6.3s
├── execute_tool TodoWrite call_wmgk3ukg                            75µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.4s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.4s
│       ╰── HTTP POST [inference-gateway]                           1.3s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.3s
│               ╰── HTTP POST [inference-gateway]                   1.3s
├── execute_tool Bash call_3yk3aag6                                  7ms
├── execute_tool Read call_8jv20ah5                                321µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     3.3s
│   ╰── POST /v1/chat/completions [inference-gateway]               3.3s
│       ╰── HTTP POST [inference-gateway]                           3.3s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     3.3s
│               ╰── HTTP POST [inference-gateway]                   3.3s
├── execute_tool Grep call_tulw7187                                  9ms
├── execute_tool Read call_r5a8efy8                                262µs
├── execute_tool Read call_9c3lvmlz                                682µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     3.7s
│   ╰── POST /v1/chat/completions [inference-gateway]               3.7s
│       ╰── HTTP POST [inference-gateway]                           3.7s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     3.7s
│               ╰── HTTP POST [inference-gateway]                   3.7s
├── execute_tool Read call_gwzujr9r                                150µs
├── execute_tool Read call_2jsivs5r                                146µs
├── execute_tool Grep call_3bvihlaa                                  2ms
├── chat ollama_cloud/deepseek-v4-flash:preview                     5.0s
│   ╰── POST /v1/chat/completions [inference-gateway]               5.0s
│       ╰── HTTP POST [inference-gateway]                           5.0s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     5.0s
│               ╰── HTTP POST [inference-gateway]                   5.0s
├── execute_tool TodoWrite call_41fcghow                            71µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     5.5s
│   ╰── POST /v1/chat/completions [inference-gateway]               5.5s
│       ╰── HTTP POST [inference-gateway]                           5.5s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     5.5s
│               ╰── HTTP POST [inference-gateway]                   5.5s
├── execute_tool MultiEdit call_hbbfa4vs                           375µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.5s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.5s
│       ╰── HTTP POST [inference-gateway]                           1.5s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.5s
│               ╰── HTTP POST [inference-gateway]                   1.5s
├── execute_tool Read call_koa40mfu                                274µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.5s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.5s
│       ╰── HTTP POST [inference-gateway]                           1.5s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.5s
│               ╰── HTTP POST [inference-gateway]                   1.5s
├── execute_tool Bash call_htgny8l7                                 72ms [error: tool_error]
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.8s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.8s
│       ╰── HTTP POST [inference-gateway]                           1.8s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.8s
│               ╰── HTTP POST [inference-gateway]                   1.8s
├── execute_tool Bash call_rcu7cbti                                16.5s
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.4s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.4s
│       ╰── HTTP POST [inference-gateway]                           1.3s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.3s
│               ╰── HTTP POST [inference-gateway]                   1.3s
├── execute_tool Bash call_oshigc79                                 1.2s [error: tool_error]
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.7s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.7s
│       ╰── HTTP POST [inference-gateway]                           1.7s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.7s
│               ╰── HTTP POST [inference-gateway]                   1.7s
├── execute_tool Bash call_5s8y9vjh                                444ms
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.5s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.5s
│       ╰── HTTP POST [inference-gateway]                           1.5s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.5s
│               ╰── HTTP POST [inference-gateway]                   1.5s
├── execute_tool Bash call_bf5ayho7                                 5.1s [error: tool_error]
├── chat ollama_cloud/deepseek-v4-flash:preview                     2.0s
│   ╰── POST /v1/chat/completions [inference-gateway]               2.0s
│       ╰── HTTP POST [inference-gateway]                           2.0s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     2.0s
│               ╰── HTTP POST [inference-gateway]                   2.0s
├── chat ollama_cloud/deepseek-v4-flash:preview                     2.4s
│   ╰── POST /v1/chat/completions [inference-gateway]               2.3s
│       ╰── HTTP POST [inference-gateway]                           2.3s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     2.3s
│               ╰── HTTP POST [inference-gateway]                   2.3s
├── execute_tool Bash call_6xry2ydz                                  4ms
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.7s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.7s
│       ╰── HTTP POST [inference-gateway]                           1.7s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.7s
│               ╰── HTTP POST [inference-gateway]                   1.7s
├── execute_tool TodoWrite call_ma118xiu                            68µs
├── chat ollama_cloud/deepseek-v4-flash:preview                     3.8s
│   ╰── POST /v1/chat/completions [inference-gateway]               3.8s
│       ╰── HTTP POST [inference-gateway]                           3.8s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     3.8s
│               ╰── HTTP POST [inference-gateway]                   3.8s
├── execute_tool Bash call_wabtxzhy                                  5ms
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.8s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.8s
│       ╰── HTTP POST [inference-gateway]                           1.8s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.8s
│               ╰── HTTP POST [inference-gateway]                   1.8s
├── execute_tool Bash call_nw3m10fp                                436ms
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.3s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.2s
│       ╰── HTTP POST [inference-gateway]                           1.2s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.2s
│               ╰── HTTP POST [inference-gateway]                   1.2s
├── execute_tool Bash call_a5tisjhd                                 1.4s
├── chat ollama_cloud/deepseek-v4-flash:preview                     1.7s
│   ╰── POST /v1/chat/completions [inference-gateway]               1.7s
│       ╰── HTTP POST [inference-gateway]                           1.7s
│           ╰── POST /proxy/:provider/*path [inference-gateway]     1.7s
│               ╰── HTTP POST [inference-gateway]                   1.7s
├── execute_tool TodoWrite call_ml54fum2                            69µs
╰── chat ollama_cloud/deepseek-v4-flash:preview                     3.2s
    ╰── POST /v1/chat/completions [inference-gateway]               3.2s
        ╰── HTTP POST [inference-gateway]                           3.2s
            ╰── POST /proxy/:provider/*path [inference-gateway]     3.2s
                ╰── HTTP POST [inference-gateway]                   3.2s

Stats

Tool Calls

╭───────────┬───────┬───────┬────────╮
│ Tool      │ Calls │ Fail% │ Avg    │
├───────────┼───────┼───────┼────────┤
│ Bash      │ 10    │ 30%   │ 2519ms │
│ Read      │ 6     │ 0%    │ 0ms    │
│ TodoWrite │ 4     │ 0%    │ 0ms    │
│ Grep      │ 2     │ 0%    │ 6ms    │
│ MultiEdit │ 1     │ 0%    │ 0ms    │
╰───────────┴───────┴───────┴────────╯

Token Usage

╭────────────────────────────────────────┬────────┬────────┬────────────┬────────┬──────╮
│ Model                                  │ Prompt │ Cached │ Completion │ Total  │ Cost │
├────────────────────────────────────────┼────────┼────────┼────────────┼────────┼──────┤
│ ollama_cloud/deepseek-v4-flash:preview │ 878687 │ 0      │ 4221       │ 882908 │ -    │
╰────────────────────────────────────────┴────────┴────────┴────────────┴────────┴──────╯

Sessions

╭───────────┬──────────┬──────────╮
│ Execution │ Mode     │ Sessions │
├───────────┼──────────┼──────────┤
│ headless  │ standard │ 1        │
╰───────────┴──────────┴──────────╯

⚠️ 3 log(s)

• Bash call_htgny8l7:

  exit status 201: task: [lint] echo "Running linting checks..."
  Running linting checks...
  task: [lint] black --check inference_gateway/ tests/ examples/
  "black": executable file not found in $PATH
  ::error title=Task 'lint' failed::exit status 127
  task: Failed to run task "lint": exit status 127
  

• Bash call_oshigc79:

  exit status 201: task: [lint] echo "Running linting checks..."
  Running linting checks...
  task: [lint] black --check inference_gateway/ tests/ examples/
  All done! ✨ 🍰 ✨
  19 files would be left unchanged.
  task: [lint] isort --check-only inference_gateway/ tests/ examples/
  ERROR: /home/runner/work/python-sdk/python-sdk/inference_gateway/__init__.py Imports are incorrectly sorted and/or formatted.
  ::error title=Task 'lint' failed::exit status 1
  task: Failed to run task "lint": exit status 1
  

• Bash call_bf5ayho7:

  exit status 201: task: [lint] echo "Running linting checks..."
  Running linting checks...
  task: [lint] black --check inference_gateway/ tests/ examples/
  All done! ✨ 🍰 ✨
  19 files would be left unchanged.
  task: [lint] isort --check-only inference_gateway/ tests/ examples/
  task: [lint] mypy inference_gateway/ examples/
  inference_gateway/client.py:513: error: Incompatible types in assignment (expression has type "int", target has type "bool | str | list[ResponseInputItem] | list[dict[str, Any]]")  [assignment]
  inference_gateway/client.py:580: error: Incompatible types in assignment (expression has type "int", target has type "bool | str | list[ResponseInputItem] | list[dict[str, Any]]")  [assignment]
  Found 2 errors in 1 file (checked 16 source files)
  ::error title=Task 'lint' failed::exit status 1
  task: Failed to run task "lint": exit status 1
  

Triggered by edenreich · Infer Action · OSS

[inference-gateway-releaser]

🎉 This PR is included in version 0.16.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀