mirror of
https://github.com/multica-ai/multica.git
synced 2026-08-15 00:04:58 +02:00
882666d478
* docs(runtimes): document QwenPaw and fix its hidden MCP tab (MUL-5828) QwenPaw shipped in SupportedTypes but reached the docs only through the two READMEs. Add it everywhere the other 19 runtimes are enumerated: - providers / install-agent-runtime (en, zh, ja, ko) - SELF_HOSTING.md and CLI_AND_DAEMON.md, including MULTICA_QWENPAW_PATH / _MODEL / _ARGS and the launch contract - environment-variables (4 locales): _ARGS covers five tools now that MULTICA_QWENPAW_ARGS exists, not four - landing i18n (4 locales): the "15 supported tools" list was missing DevEco Code, Grok, Qoder CN, Qwen Code, and QwenPaw QwenPaw is the only runtime where ModelSelectionSupported returns false, so document that its model list is empty by design rather than a symptom of an offline runtime. Also add qwenpaw to MCP_SUPPORTED_PROVIDERS. qwenpaw.go forwards opts.McpConfig, but the omission hid the MCP tab in the agent inspector, which would have made the new "Multica-managed MCP: yes" row false. While in these tables, move the Reasonix row back into runtime-id order. Co-authored-by: multica-agent <github@multica.ai> * fix(runtimes): close the remaining QwenPaw drifts and stale runtime lists (MUL-5828) Frontend-side follow-ups to the QwenPaw docs pass: - RUNTIME_PROFILE_PROTOCOL_FAMILIES was missing qwenpaw, so the custom runtime profile picker could not select it even though migrations 253/254 and agent.SupportedTypes both allow it. - PROVIDER_DISPLAY_NAMES was missing it too. The daemon's runtimeDisplayNameOverrides maps qwenpaw to "QwenPaw"; without the mirror an aliased runtime rendered "Qwenpaw", which is exactly the drift the comment on that map warns about. - provider-logo had no qwenpaw case and fell through to the generic Monitor icon. Adds the standalone mark from the official wordmark (agentscope-ai/QwenPaw, Apache-2.0), drawn with currentColor so one path covers both themes. Also corrects two stale runtime lists in the root docs: - Drop the Gemini row and MULTICA_GEMINI_PATH / _MODEL from CLI_AND_DAEMON.md. Migration 126 dropped the gemini protocol family and no gemini probe exists, so the runtime has been gone for a while. - Add Antigravity, CodeBuddy, and DevEco Code to CLI_AND_DAEMON.md and SELF_HOSTING.md, plus their PATH / MODEL / ARGS variables. Co-authored-by: multica-agent <github@multica.ai> * fix(agent): make MULTICA_QWENPAW_ARGS work and stop advertising _MODEL (MUL-5828) Review caught two env vars the docs promised but the runtime did not honour. MULTICA_QWENPAW_ARGS was read by config.go and forwarded by daemon.go as ExecOptions.ExtraArgs, but the backend consumed CustomArgs only, so the value was plumbed all the way down and then dropped. Consume ExtraArgs before CustomArgs, matching the precedence CLI_AND_DAEMON.md documents and the five other backends that accept both. The new test fails on the old backend with "acp --per-agent". MULTICA_QWENPAW_MODEL cannot work by design: the backend never calls session/set_model because that rewrites QwenPaw's shared agent config, so ExecOptions.Model is ignored (pinned by TestQwenpawUsageModelIgnored). The probe read it into AgentEntry.Model, which only ever feeds that ignored field. Drop the read and stop documenting the variable, and note the exception on the four environment-variables pages, which otherwise claim every tool takes a _MODEL override. Co-authored-by: multica-agent <github@multica.ai> * docs(agent): stop enumerating ExtraArgs consumers in the field comment (MUL-5828) The list said "claude and codex backends only", which was already wrong for codebuddy, antigravity, and qwen. An enumeration here has to be updated from a different file every time a backend opts in, and going stale is exactly what let MULTICA_QWENPAW_ARGS ship plumbed but dropped. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Bohan-J <bohan@devv.ai> Co-authored-by: multica-agent <github@multica.ai>