chore: sync openapi.yaml with schemas v1.4.1 (deprecated metadata key)

[inference-gateway-maintainer]

Deterministic sync from inference-gateway/schemas at v1.4.1, regenerated with task oas-sync SCHEMAS_REF=refs/tags/v1.4.1. Re-runs update this PR in place; it closes automatically if the repo is back in sync.

This PR is spec-only: no generated or hand-written code changes.

Net change against our v1.2.2 baseline

• The select_metadata parameter on the list models endpoint gains a deprecated value (upstream schemas PR #290 in v1.4.0, references gateway #793), and its description now explains that deprecated lists models the community tables mark as deprecated, which are hidden by default, and adds no field.
• schemas v1.3.0 introduced the WebWright provider and v1.4.1 reverted it, so the net diff here contains no provider changes.

Impact on the SDK

• None. inference_gateway/models.py has no diff in this PR because deprecated adds no response field.
• InferenceGatewayClient.list_models takes include as a plain list of strings, so callers can already pass "deprecated" today. A future PR could refresh the docstring's supported-values list, that is all.

[edenreich]

@infer please update the PR description and title to reflect on the change.

[inference-gateway-maintainer]

Model: ollama_cloud/glm-5.3-flash · Action: v0.57.0 · CLI: v0.231.1 · View Job

Todos

(agent has not posted a plan yet)

Pull Request

#156

✅ Infer Result: Success

Done - PR #156's title and description now reflect the actual change.

What I updated:

• New title: chore: sync openapi.yaml with schemas v1.4.1 (deprecated metadata key) - I changed feat: to chore: because the net diff touches only the vendored OpenAPI spec with zero code impact (docs:-style sync of the spec, matching the repo precedent in ff488ae).
• New description (gh pr edit 156):
  • Sates it is spec-only: no generated or hand-written code changes.
  • Explains the net change vs the v1.2.2 baseline: schemas v1.4.0 added deprecated to the select_metadata enum on the list-models endpoint (upstream PR #290, references gateway #793), and v1.4.1 reverted the WebWright provider that v1.3.0 had added, so provider changes net out to zero - which is why only the 3-line select_metadata diff remains.
  • Clarifies SDK impact: models.py has no diff (the new key adds no response field), and list_models already accepts include as a plain string list so callers can pass "deprecated" today; a follow-up could refresh the docstring's supported-values list.

One caveat: the schemas-sync workflow writes these fields itself, so if it re-runs on a future schemas update, it may retitle the PR back to its default format.

Skipped: no code, doc, or commit changes (nothing to run checks on; working tree is clean), and I did not open follow-up issues since the PR body already names the only conceivable follow-up (docstring refresh), which is the user's call.

Model: ollama_cloud/glm-5.3-flash · Action: v0.57.0 · CLI: v0.231.1 · Exit Code: 0 · Duration: 2m 9s

Tokens: 248,251 in · 11,106 out · 259,357 total (9 requests)

Tool calls: 13 total · 100% success rate

Traces

Session: 1792501885-7b106492

session (headless, success)                                                                         2m2s
├── chat ollama_cloud/glm-5.3-flash                                                                 7.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       7.3s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     7.3s
│           ╰── POST [inference-gateway, server]                                                    7.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 7.3s
├── execute_tool Bash call_aoift3hs                                                                  5ms
├── execute_tool Bash call_yltz6yez                                                                  3ms
├── chat ollama_cloud/glm-5.3-flash                                                                17.3s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      17.3s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    17.3s
│           ╰── POST [inference-gateway, server]                                                   17.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                17.3s
├── execute_tool Grep call_47c477d1                                                                  3ms
├── execute_tool Bash call_8zrjc48m                                                                427ms
├── chat ollama_cloud/glm-5.3-flash                                                                 7.9s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       7.9s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     7.9s
│           ╰── POST [inference-gateway, server]                                                    7.9s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 7.9s
├── execute_tool Bash call_e7s18mmh                                                                428ms
├── execute_tool Grep call_cwzuwea9                                                                  3ms
├── chat ollama_cloud/glm-5.3-flash                                                                24.7s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      24.7s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    24.7s
│           ╰── POST [inference-gateway, server]                                                   24.7s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                24.7s
├── execute_tool Grep call_tui29e9b                                                                  1ms
├── execute_tool Grep call_tpq4z0ai                                                                974µs
├── chat ollama_cloud/glm-5.3-flash                                                                 9.8s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       9.8s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     9.8s
│           ╰── POST [inference-gateway, server]                                                    9.8s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 9.8s
├── execute_tool Read call_1rr5pncc                                                                297µs
├── execute_tool Bash call_ff5bamxw                                                                394ms
├── chat ollama_cloud/glm-5.3-flash                                                                41.0s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      41.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    41.0s
│           ╰── POST [inference-gateway, server]                                                   41.0s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                41.0s
├── execute_tool Write call_tb5gag9c                                                                 1ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.4s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.4s
│           ╰── POST [inference-gateway, server]                                                    2.4s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.4s
├── execute_tool Bash call_2t73gvsn                                                                 2.1s
├── chat ollama_cloud/glm-5.3-flash                                                                 2.0s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.0s
│           ╰── POST [inference-gateway, server]                                                    2.0s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.0s
├── execute_tool Bash call_wvrv5vuj                                                                  4ms
╰── chat ollama_cloud/glm-5.3-flash                                                                 3.1s
    ╰── POST /v1/chat/completions [inference-gateway, server]                                       3.1s
        ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     3.1s
            ╰── POST [inference-gateway, server]                                                    3.1s
                ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 3.1s

Stats

Tool Calls

╭───────┬───────┬───────┬───────╮
│ Tool  │ Calls │ Fail% │ Avg   │
├───────┼───────┼───────┼───────┤
│ Bash  │ 7     │ 0%    │ 484ms │
│ Grep  │ 4     │ 0%    │ 3ms   │
│ Read  │ 1     │ 0%    │ 307µs │
│ Write │ 1     │ 0%    │ 1ms   │
╰───────┴───────┴───────┴───────╯

Token Usage

╭────────────────────────────┬────────┬────────┬────────────┬────────┬──────╮
│ Model                      │ Prompt │ Cached │ Completion │ Total  │ Cost │
├────────────────────────────┼────────┼────────┼────────────┼────────┼──────┤
│ ollama_cloud/glm-5.3-flash │ 248251 │ 152320 │ 11106      │ 259357 │ -    │
╰────────────────────────────┴────────┴────────┴────────────┴────────┴──────╯

Sessions

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

Triggered by edenreich · Infer Action · OSS