Expose Bailian capabilities to dsh through its service seams as one
package with six subpath plugin entries and a `dsh.bundle` patch:
- TokenPlan as an LLM provider
- bailian_vision_describe / bailian_image_generate tools over `bl`
- knowledge-base retrieval as a WebSearchProvider (`bailian-kb`)
- cross-session memory: tools, pre-step recall, turn-close persist
- managed-agent as a SubagentProvider
TokenPlan configures the base bundle's existing pi-ai row rather than
mounting a second `dsh-llm-pi-ai` instance. A second instance cannot
work: pi-ai re-declares its entire built-in provider catalog to
`registerConfigurableProviders`, and that directory is global, so boot
fails with a duplicate on `amazon-bedrock`.
Routes and vision support were probed against the live gateway.
qwen3.8-max, qwen3.7-plus, qwen3.6-flash and glm-5.2 read images;
qwen3.7-max rejects them with HTTP 400; the DeepSeek routes accept image
content without erroring yet stay blind. The DeepSeek entries therefore
do not declare image input — claiming it would turn a clean refusal into
a silently wrong answer — and `bailian_vision_describe` serves them by
returning text instead.
Also fix `bl memory` against the v2 API, each verified live:
- `profile get` used /profiles, which returns HTTP 500. The documented
and working endpoint is /user_profile.
- `add` read `response.memory_ids`, which the service never returns. It
returns `memory_nodes`, so text output always printed "IDs: none".
- `MemoryNode.created_at`/`updated_at` are unix seconds, not strings, and
`UserProfileResponse.profile` did not match the wire shape.
- Add the missing request parameters: --meta-data, --project-id,
--project-ids, --min-score, --enable-rerank, --plan-version,
--enable-judge, --enable-rewrite, --timestamp.
- Add `memory profile list|detail|update|delete`, covering the four v2
profile-schema operations the CLI was missing.
`plan_version: lite` is ignored by the service and still bills pro;
`enable_rerank: false` is what actually selects lite, which is ~50x
cheaper per search. The CLI flag and the memory plugin both send the
parameter that works.
Disable pnpm's autoInstallPeers: the @deepseek-ai/dsh-* rc line peers on
three packages that were never published to npm, which 404s the whole
workspace install. Verified the existing packages still build.
Co-Authored-By: Claude <noreply@anthropic.com>
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.
- Removed the `bailian-cli-commands` dependency from `pnpm-lock.yaml` and `package.json` as it was no longer needed.
- Expanded the E2E tests in `auth.e2e.test.ts` to cover additional scenarios for the `auth login` command, ensuring proper error handling for conflicting flags and missing parameters.
- Improved test assertions for better clarity and coverage of authentication flows.
- Added e2e package as a workspace dependency in pnpm-lock.yaml.
- Updated globalSetup path in vite.config.ts to point to the new e2e package location.
- Enhanced documentation for CLI E2E testing, including architecture layers and triggering conditions.
- Refactored test paths and commands in the documentation to align with the new structure.
- Removed outdated dataset and auth E2E tests to streamline the test suite.
- Updated command references and validation checks in the documentation to reflect recent changes.
- use tsx for bl/kscli dev and test runners
- point local library exports to src while keeping publishConfig on dist
- switch vendored telemetry modules to .cjs for source-run compatibility
- update stress/e2e helpers and agent docs for the new source execution path
Decompose the monolithic `cli` package into three layers so multiple
products can be assembled from a shared base:
- bailian-cli-runtime: framework infra (createCli, registry, args,
output, pipeline, utils) — product-agnostic
- bailian-cli-commands: command library, grouped (base/knowledge/text/
media/memory/misc) so each product picks the sets it needs
- packages/cli (bl): full command set; packages/rag (rag): base +
knowledge only
Product identity (binName / clientName / npmPackage) is injected at the
createCli boundary and required there, with no per-consumer defaults.
Node's built-in fetch (undici) ignores proxy environment variables, so
bl always connected directly and failed with ECONNRESET behind a VPN or
corporate proxy. Install an EnvHttpProxyAgent as the global dispatcher at
startup, but only when a proxy variable is actually set — behavior is
unchanged otherwise. Lowercase variables take precedence over uppercase
(curl convention) and NO_PROXY is honored.
Values are trimmed and passed explicitly to work around undici reading
env vars with ??, where an empty lowercase variable (https_proxy="")
masks a configured uppercase one. Invalid proxy URLs fail with a clear
usage error instead of a stack trace, and the ECONNRESET hint now
suggests exporting HTTPS_PROXY.
Tests are fully offline and need no credentials: unit tests cover env
parsing, and the e2e test runs a minimal probe (setupProxyFromEnv + a
bare fetch) against a .invalid host through a local CONNECT proxy to
verify traffic routes through the proxy, NO_PROXY is honored, no
dispatcher is installed when unset, and invalid values error clearly.
lisheng.lisheng