common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix(cli): /model picker honors provider-specific context caps (#16030)

Browse Source 
`_apply_model_switch_result` (the interactive `/model` picker's
confirmation path) printed `ModelInfo.context_window` straight from
models.dev, which reports the vendor-wide value (1.05M for gpt-5.5 on
openai). ChatGPT Codex OAuth caps the same slug at 272K, so the picker
showed 1M while the runtime (compressor, gateway `/model`, typed
`/model <name>`) correctly used 272K — the classic 'sometimes 1M,
sometimes 272K' mismatch on a single model.

Both display paths now go through `resolve_display_context_length()`,
matching the fix that `_handle_model_switch` received earlier.

Also bump the stale last-resort fallback in DEFAULT_CONTEXT_LENGTHS
(`gpt-5.5: 400000 -> 1050000`) to match the real OpenAI API value; the
272K Codex cap is already enforced via the Codex-OAuth branch, so the
fallback now reflects what every non-Codex probe-miss should see.

Tests: adds `test_apply_model_switch_result_context.py` with three
scenarios (Codex cap wins, OpenRouter shows 1.05M, resolver-empty falls
back to ModelInfo). Updates the existing non-Codex fallback test to
assert 1.05M (the correct value).

## Validation
| path                          | before    | after     |
|-------------------------------|-----------|-----------|
| picker -> gpt-5.5 on Codex    | 1,050,000 | 272,000   |
| picker -> gpt-5.5 on OpenAI   | 1,050,000 | 1,050,000 |
| picker -> gpt-5.5 on OpenRouter | 1,050,000 | 1,050,000 |
| typed /model gpt-5.5 on Codex | 272,000   | 272,000   |
This commit is contained in:
Teknium
2026-04-26 05:43:31 -07:00
committed by GitHub
parent 2ccdadcca6
commit 438db0c7b0
4 changed files with 177 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/agent/test_model_metadata.py
View File

@@ -340,7 +340,9 @@ class TestCodexOAuthContextLength:
from agent.model_metadata import get_model_context_length
# OpenRouter — should hit its own catalog path first; when mocked
# empty, falls through to hardcoded DEFAULT_CONTEXT_LENGTHS (400k).
# empty, falls through to hardcoded DEFAULT_CONTEXT_LENGTHS (1.05M,
# matching the real direct-API value — Codex OAuth's 272k cap is
# provider-specific and must not leak here).
with patch("agent.model_metadata.fetch_model_metadata", return_value={}), \
patch("agent.model_metadata.fetch_endpoint_model_metadata", return_value={}), \
patch("agent.model_metadata.get_cached_context_length", return_value=None), \
@@ -351,7 +353,7 @@ class TestCodexOAuthContextLength:
api_key="",
provider="openrouter",
)
assert ctx == 400_000, (
assert ctx == 1_050_000, (
f"Non-Codex gpt-5.5 resolved to {ctx}; Codex 272k override "
"leaked outside openai-codex provider"
)