fix(aux): skip kimi-coding in vision auto-detect (closes #17076) (#17451)

* docs(anthropic): correct OAuth scope to Max plan + extra usage credits only

The previous docs pass (#17399) overstated what Anthropic OAuth works
with. In practice Hermes can only route against a Claude Max plan that
has purchased extra usage credits — the base Max allowance is not
consumed, and Claude Pro is not supported at all. Without Max + extra
credits, users must fall back to an ANTHROPIC_API_KEY (pay-per-token).

Updates the four pages touched in #17399:
- integrations/providers.md
- user-guide/features/credential-pools.md
- reference/environment-variables.md
- getting-started/quickstart.md

* fix(aux): skip kimi-coding in vision auto-detect (closes #17076)

Kimi Coding Plan's /coding endpoint (Anthropic Messages wire) has no
image_in capability — Kimi's own docs confirm and suggest switching to
a vision-capable model. Vision lives on the separate Kimi Platform
(api.moonshot.ai, OpenAI-wire, pay-as-you-go). When the user has
kimi-coding as main provider and auxiliary.vision.provider=auto,
resolve_vision_provider_client was handing back an AnthropicAuxiliaryClient
wrapped around /coding which 404'd on every vision request.

Add a _PROVIDERS_WITHOUT_VISION frozenset ({kimi-coding, kimi-coding-cn})
and gate the main-provider vision branch on membership. On a skip the
auto-detect falls through to OpenRouter → Nous like any other
main-provider-unavailable case.

Explicit per-task overrides (auxiliary.vision.provider=kimi-coding) are
unaffected — the skip only applies when the caller is in auto mode.

Tests: 4 new targeted tests in TestVisionAutoSkipsKimiCoding covering
the skip path, CN variant, explicit-override passthrough, and a guard
against accidental skip-list widening.

agent/auxiliary_client.py

@@ -229,6 +229,21 @@ _PROVIDER_VISION_MODELS: Dict[str, str] = {
     "zai": "glm-5v-turbo",
 }
 
+# Providers whose endpoint does not accept image input, even though the
+# provider's broader ecosystem has vision models available elsewhere.  When
+# `auxiliary.vision.provider: auto` sees one of these as the main provider,
+# it must skip straight to the aggregator chain instead of returning a client
+# that will 404 on every vision request.
+#
+# kimi-coding / kimi-coding-cn: the Kimi Coding Plan routes through
+# api.kimi.com/coding (Anthropic Messages wire) which Kimi's own docs
+# describe as having no image_in capability. Vision lives on the separate
+# Kimi Platform (api.moonshot.ai, OpenAI-wire, pay-as-you-go).  See #17076.
+_PROVIDERS_WITHOUT_VISION: frozenset = frozenset({
+    "kimi-coding",
+    "kimi-coding-cn",
+})
+
 # OpenRouter app attribution headers
 _OR_HEADERS = {
     "HTTP-Referer": "https://hermes-agent.nousresearch.com",
@@ -2534,6 +2549,19 @@ def resolve_vision_provider_client(
                         main_provider, default_model or resolved_model or main_model,
                     )
                     return _finalize(main_provider, sync_client, default_model)
+            elif main_provider in _PROVIDERS_WITHOUT_VISION:
+                # Kimi Coding Plan's /coding endpoint (Anthropic Messages wire)
+                # does not accept image input — Kimi's own docs say "Current
+                # model does not support image input, switch to a model with
+                # image_in capability" and vision lives on the separate Kimi
+                # Platform (api.moonshot.ai). Skip the main provider and fall
+                # through to the aggregator chain instead of returning a
+                # client that will 404 on every vision request (#17076).
+                logger.debug(
+                    "Vision auto-detect: skipping main provider %s (no "
+                    "vision support) — falling through to aggregator chain",
+                    main_provider,
+                )
             else:
                 rpc_client, rpc_model = resolve_provider_client(
                     main_provider, vision_model,