fix(providers): require base_url for anthropic-compatible

Copilot review on #661: empty base_url let the SDK fall back to
https://api.anthropic.com, sending compat-shaped requests to the
commercial API. The lane is local-only by definition, and the /v1-strip
edge case already established fail-loudly-over-silent-prod-retarget;
apply the same principle to the empty case. create_client raises an
actionable ValueError; the admin Detect path surfaces it as a clean
error string via probe_model_endpoint's existing handler.
This commit is contained in:
Patrick Buckley
2026-06-11 20:27:12 -07:00
parent 12bd848c68
commit 7ef04e576a
3 changed files with 24 additions and 4 deletions
+5 -3
View File
@@ -775,9 +775,11 @@ wire translation as the real Anthropic lane, but every model resolves to
the `_ANTHROPIC_COMPAT_DEFAULT` capabilities (200K context, 64K output,
`token_param=max_tokens`, `thinking_mode=none`, no native
web_search/tool_search, no vision) — the static Claude table never
applies to local checkpoints. `base_url` is the server root WITHOUT
`/v1` (the Anthropic SDK appends `/v1/messages`); a trailing `/v1`
pasted out of openai-compatible habit is stripped automatically. Set a
applies to local checkpoints. `base_url` is required — the server root
WITHOUT `/v1` (the Anthropic SDK appends `/v1/messages`); a trailing
`/v1` pasted out of openai-compatible habit is stripped automatically,
and an empty value fails at client construction rather than falling
back to the commercial endpoint. Set a
placeholder `api_key` (e.g. `"dummy"`) for unauthenticated servers. Tool calling
needs the server started with `--enable-auto-tool-choice
--tool-call-parser <family>` plus the matching reasoning parser.