Problem

/model switch always shows Context: 256,000 tokens for custom providers configured via providers: in config.yaml, regardless of the actual context_length value set on the provider entry.

Observed behavior:

/model vertex-opus46
  ✓ Model switched: claude-opus-4.6
    Provider: vertex-opus46
    Context: 256,000 tokens    ← wrong, should be 1,000,000

This affects all custom provider setups (vertex-proxy, LiteLLM, or any providers: entry) using the common config shape:

providers:
  vertex-opus46:
    base_url: http://127.0.0.1:8788/anthropic
    model: claude-opus-4.6
    context_length: 1000000
    api_mode: anthropic_messages

Root Cause

Two bugs in the resolution chain:

1. get_compatible_custom_providers() early-returns [] on dict-shaped custom_providers. When custom_providers: {} exists in config.yaml (an empty dict, not a list), the not isinstance(custom_providers, list) guard returns early, skipping the providers: dict loop below it. All user-configured providers become invisible to the context_length lookup.

2. get_custom_provider_context_length() only checks models.<model>.context_length. The common config shape has model and context_length as siblings at the provider level, with no nested models: dict. The lookup returns None and the whole chain falls through to DEFAULT_FALLBACK_CONTEXT = 256_000.

Fix

config.py:

• get_compatible_custom_providers(): gracefully handle dict-shaped custom_providers by normalizing it the same way as the providers: dict, instead of early-returning.
• get_custom_provider_context_length(): after the existing models.<model>.context_length lookup, fall back to the provider-level context_length when the entry's default model matches the requested model.

agent_runtime_helpers.py:

• Persist the resolved new_context_length back to agent._config_context_length after switch_model completes, so the display path in cli.py reads the correct value instead of None.

Testing

Manual: Tested with providers: config entries pointing at vertex-proxy (port 8788, Anthropic wire protocol).

Before fix:

/model vertex-opus46   → Context: 256,000 tokens
/model vertex-haiku    → Context: 256,000 tokens

After fix:

/model vertex-opus46   → Context: 1,000,000 tokens
/model vertex-haiku    → Context: 200,000 tokens

Automated: All existing tests pass:

• test_config.py — 87 passed
• test_config_validation.py — 21 passed (dict-shaped custom_providers detection still works)
• test_model_switch_custom_providers.py — 19 passed
• test_custom_provider_context_length — 12 passed, 2 skipped

Supersedes #36199.

Signed-off-by: Chris van Hoof vanhoof@ouwish.com