Image recognition and the chat model shared DEEPSEEK_API_KEY: the
image-recognition bundle defaulted apiKeyEnv to the model key, so saving one
overwrote the other. Point the bundle at IMAGE_RECOGNITION_API_KEY and guard
both the provider and the settings card against a stale model ref, so vision
never reads or writes the chat key. Also add a clear-key button, default the
model to qwen3-vl-flash on the DashScope compatible-mode endpoint, and send
file images as base64 with a normalized base URL.
Co-Authored-By: Claude <noreply@anthropic.com>
Add the image-recognition bundle to the web profile template so the
capability is on by default for new web profiles.
Co-Authored-By: Claude <noreply@anthropic.com>
Document the four image-recognition packages and the vision group, register
the vision domain in the package index, add the capability decision as an
Agent Note, declare the invariants peer dep, and drop the unused agents
injection from the consumer.
Co-Authored-By: Claude <noreply@anthropic.com>
Mounts the capability seam, the configurable HTTP provider, and the
model-facing recognition consumer. Not in any default profile's bundles
list — a user opts in per profile.
Co-Authored-By: Claude <noreply@anthropic.com>
Pine