Stop inferring size/prompt_extend from sync vs async; use per-family sizeProfile. wanx*-imageedit uses function+base_image_url; bare qwen-image uses the fixed resolution table.
- claude-code: honor CLAUDE_CONFIG_DIR; drop stale ANTHROPIC_API_KEY
- qwen-code: write $version:3; security.auth carries selectedType only
- opencode: tolerate JSONC (comments/trailing commas) via stripJsonc
- openclaw: add --context-window flag (default 256000), full cost fields,
agents.defaults.models allowlist
- hermes: switch to official flat model.* block; api_mode only for
anthropic endpoints
- codex: official env_key + auth.json fallback; add --wire-api flag
(default chat, responses for supported models)
- convert local images to Base64 for Token Plan image and video commands
- preserve the existing OSS upload flow for standard API Key profiles
- use wan2.7-image as the default image model with the sync endpoint
- hide full Base64 image content in dry-run output
- add Token Plan compatibility tests and update related docs
- Add Skills / MCP / Agents / Assets inventory views with click-to-open
right-side detail drawers (reusable infoDrawer)
- Render SKILL.md as Markdown via a self-contained, XSS-safe inline renderer
(HTML-escape first, strip YAML frontmatter, no external deps)
- Add local vs remote origin badges to Skills and MCP items
- Add quick-launch for coding agents (allowlisted id->binary, execFile, no
shell); gate the button on Connected AND the CLI binary being on PATH
- Add per-category model catalog surfaced as click-to-fill suggestion chips
under each default_*_model field, sourced from real bl pipeline model names
- Add assets browser (categorized, time-sorted) with preview, open-locally
and delete, backed by path-traversal-guarded file serving
- Convert Profiles to a tile grid with an add-tile and design-consistent
new-profile modal; make view headers sticky and use drawers for editing
- Tests for inventory, agent-launch, assets and config-ui endpoints
- switch the default text model to qwen3.8-max-preview
- add dedicated T2V, I2V, and R2V model defaults
- persist and consume per-mode video model settings
- enable thinking when validating the qwen3.8 preview model
- add Token Plan subscription and login entry to CLI, README, INSTALL, and skill
- document built-in Base URL and automatic key validation
- remove the completed Token Plan integration design document
Add `bl config agent` to configure a coding agent (Claude Code, Qwen Code,
OpenCode, OpenClaw, Hermes, Codex) to use a DashScope/ModelStudio endpoint
with a single command. Writers non-destructively merge into each agent's
local config with a timestamped backup and atomic writes.
- Field structures aligned to farion1231/cc-switch; qwen-code aligned to
QwenLM/qwen-code source (modelProviders/security.auth keyed by protocol).
- provider id unified as `bailian-cli` (qwen-code brands via model entry
name + BAILIAN_CLI_API_KEY, since it keys by protocol).
- Codex config.toml merged via smol-toml to preserve unrelated settings.
- Add writer unit tests + config e2e cases; regenerate skill reference.
chenanran555