chore(server): guard that /v1/models reports null model capabilities

[elyasmnvidian]

What

GET /v1/models leaves each model's context_window and tool_calling as null, and this PR keeps it that way on purpose, with a test that locks it in.

Why

The id in /v1/models is a symbolic route name (like random or smart), not the upstream model behind it — so there's nothing to read a real context window or tool-calling flag from. Inferring one from the route name (or from a target) would be a guess, and a wrong one. The operator picks the models they route to and already knows their limits, so Switchyard doesn't need to advertise them.

This replaces the earlier version of this PR, which inferred the context window from the model id and broke once the id became a route name (flagged in review).

Change

• A comment on model_entry_json explaining why the two fields are null.
• A test that serves a route named random over a big-context target and asserts both fields are null — written so any future attempt to infer a value (from the route name or the target) fails the test.
• streaming and the supported inbound formats stay populated; those are facts about this server, not the upstream model.

If someone later needs these reported, the operator can declare them in the server config and we report exactly what they set — no guessing.

[coderabbitai]

Walkthrough

The server maps context exhaustion errors to HTTP 400 responses with an OpenAI-compatible error code. Model listings now expose tool-calling support and inferred context-window values, with integration tests covering both changes.

Changes

Server behavior

Layer / File(s)	Summary
Context overflow error mapping crates/switchyard-server/src/lib.rs, crates/switchyard-server/tests/server.rs	Context window and pool exhaustion errors return HTTP 400 with context_length_exceeded; an overflow profile and integration test validate the response.
Model capability metadata crates/switchyard-server/src/lib.rs, crates/switchyard-server/tests/server.rs	Model listings report tool_calling: true and infer context_window from display-name substrings with a 128_000 fallback; endpoint assertions cover the values.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Poem

I’m a rabbit with tests in my burrow,
Errors now hop client-side in a hurry.
Models show tools and windows bright,
Context clues make their numbers right.
400 says, “Your prompt’s too furry!”

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly describes one major part of the change: reporting tool_calling and context_window in /v1/models.

---

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

🧹 Nitpick comments (1)

crates/switchyard-server/tests/server.rs (1)

217-242: 🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick win

Cover ContextPoolExhausted separately.

This test exercises only ContextWindowExceeded, while the production mapping also handles ContextPoolExhausted. Add a profile/test for the second variant so regressions in that branch cannot pass unnoticed.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@crates/switchyard-server/tests/server.rs` around lines 217 - 242, Add a
separate test alongside context_window_overflow_maps_to_client_error using a
profile that triggers ContextPoolExhausted. Send the same chat completion
request through build_switchyard_router, then assert the response is BAD_REQUEST
with error.code set to the expected client-facing code for pool exhaustion,
covering the distinct production mapping branch.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@crates/switchyard-server/tests/server.rs`:
- Around line 217-242: Add a separate test alongside
context_window_overflow_maps_to_client_error using a profile that triggers
ContextPoolExhausted. Send the same chat completion request through
build_switchyard_router, then assert the response is BAD_REQUEST with error.code
set to the expected client-facing code for pool exhaustion, covering the
distinct production mapping branch.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 4f5c9536-37c6-407c-a66f-fcadc9be076c

📥 Commits

Reviewing files that changed from the base of the PR and between 2fa6b87 and 01a361b.

📒 Files selected for processing (2)

• crates/switchyard-server/src/lib.rs
• crates/switchyard-server/tests/server.rs

[grahamking]

Won't this be a symbolic / router name like smart or random? We don't advertise the upstream models any more.