Replaced 138 typography characters (curly quotes, apostrophes, em/en
dashes, non-breaking hyphens) with ASCII equivalents per
docs/CLAUDE.md heading and content hygiene rules so grep, copy-paste,
and Mintlify search hit clean tokens.
- docs/reference/AGENTS.default.md: 29 chars, plus removed the
duplicate '# AGENTS.md - OpenClaw Personal Assistant (default)' H1
(Mintlify renders title from frontmatter; the in-body H1 with
parens and a bare hyphen produced a brittle anchor).
- docs/help/testing-live.md: 29 chars
- docs/tools/image-generation.md: 28 chars
- docs/channels/index.md: 27 chars
- docs/tools/video-generation.md: 25 chars
The image-generation page was 395 lines with a 3-step quick-start
written as plain numbered prose, a sprawling 'OpenAI gpt-image-2'
section that mixed routing/legacy/OpenAI options with five inline
slash-command examples, and provider tables that mixed alphabetic
and recency order.
Restructure for scan-first reading without losing technical content:
- Wrap Quick start in a Steps component (auth -> default model ->
ask the agent), pulling the Codex OAuth note inline with the model
step where it belongs and surfacing the LAN/SSRF caveat as a
Warning callout.
- Alphabetize the Supported providers table (ComfyUI, fal, Google,
LiteLLM, MiniMax, OpenAI, OpenRouter, Vydra, xAI) and the Provider
capabilities table (same order across both). Convert the Yes/No
capability table to checkmarks plus exact counts for readability.
- Replace the long inline OpenAI / OpenRouter / MiniMax / xAI prose
with a 'Provider deep dives' AccordionGroup so each backend's
routing, legacy URL handling, and provider-specific knobs collapse
by default.
- Move the four provider-selection-order notes into a small
AccordionGroup ('Per-call overrides are exact', 'Auto-detection is
auth-aware', 'Timeouts', 'Inspect at runtime').
- Collapse the five flat slash-command examples into a single Tabs
component (4K landscape / transparent PNG / two-square /
edit-one-ref / edit-multi-ref) with the matching CLI variant inline
on the transparent-PNG tab.
- Sentence-case the Related list (Tools overview, Configuration
reference) and drop the redundant generic introductory wording.
- Add sidebarTitle so the nav reads 'Image generation' explicitly.
Wording, schema fields, defaults, model refs, env vars, and the
detailed OpenAI/OpenRouter/Codex routing rules are unchanged.
* feat(litellm): add image generation provider
Registers litellm as an image-generation provider so model refs like
litellm/gpt-image-2 route through the LiteLLM proxy, and
agents.defaults.imageGenerationModel.fallbacks entries of the form
litellm/... resolve without "No image-generation provider registered
for litellm" errors.
Implementation uses the OpenAI-compatible /images/generations and
/images/edits endpoints that LiteLLM proxies for. BaseUrl resolves from
models.providers.litellm.baseUrl (default http://localhost:4000). Private
network is auto-allowed when baseUrl is a loopback/RFC1918 address, which
covers the common self-hosted LiteLLM proxy case without needing
OPENCLAW_PROVIDER_ALLOW_PRIVATE_NETWORK. Public baseUrls keep normal SSRF
defaults.
Default model is gpt-image-2 (matching upstream 4.21+ OpenAI default).
Advertises the same 2K/4K sizes OpenAI now exposes, plus legacy
256/512/1024 for dall-e-3. Supports both generate and edit.
Local patch. LiteLLM has no upstream image-generation support yet; revisit
if upstream adds one.
* ci: rerun after upstream main hot-fix
* fix(litellm): harden image generation provider
---------
Co-authored-by: Chris Zhang <chris@ChrisdeMac-mini.local>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
