Per-agent provider selection for custom agents
Nadie ha tomado este issue todavía.
- Lenguaje dominante
- Shell
- Estrellas
- 11.2k
- Forks
- 1.9k
- Merge medio
- 14 h 16 min
- PR fusionados (30 d)
- 6
Descripción
I know about BYOK (COPILOT_PROVIDER_BASE_URL plus COPILOT_MODEL), /model, and the model field in custom-agent frontmatter. We use all three. None of them lets two agents in one session talk to two different endpoints, because COPILOT_PROVIDER_BASE_URL is process-wide and nothing scopes it to an agent. That is the difference between this and #3624 and copilot-sdk#1545, both closed within hours pointing at the BYOK docs.
The ask
A provider field in custom-agent frontmatter. Or the per-agent env/env_file scoping that #2879 proposes for secrets, which would do the same job. The main agent keeps the session provider. The subagent gets its own base URL.
What the runtime already does
I put a recording HTTP server at COPILOT_PROVIDER_BASE_URL on 1.0.83-3 and dispatched a custom agent through the task tool. Three requests came out of one session:
1 model=local-worker-model tools=24 main agent
2 model=ROUTE-ME-LOCAL tools=1 subagent; model from its .agent.md frontmatter,
its own instructions in the system prompt
3 model=local-worker-model tools=24 main agent
The model override on the task tool arrives the same way. The per-agent model id already reaches the provider, and v1.0.62 ("Keep custom agents on their configured model when using BYOK providers") and v1.0.65 for subagents made that deliberate. What it cannot carry is an endpoint to send that id to.
Use case
A cloud main agent plans and reviews. It hands renames, comment edits, log lines and single-file changes to a subagent running a 27B model on the developer's Mac (MLX, 48 GB). Those tokens cost nothing. I am not claiming the local model matches the cloud one. On our own eight-task benchmark two local models came out indistinguishable from each other, and the only claim I will stand behind is free tokens for mechanical work. Judgement stays in the cloud.
What we tried
A routing proxy at COPILOT_PROVIDER_BASE_URL, keyed on the model id. Known local ids go to the MLX server and the proxy forwards the rest to GitHub. Two problems killed it. It puts the main agent's traffic through GitHub endpoints that are not documented for that use. And the docs say "A declared model or effort that can't be honored falls back to the session's value instead of failing the dispatch", so any proxy error on a local id sends that task to the session model instead. You find out from the bill rather than from an error.
Related
- #2879 asks for per-agent
env:/env_file:to isolate secrets. Same mechanism, different reason for wanting it. - #2728 asks for per-agent LSP config, so per-agent configuration beyond
modelis a shape this project already accepts. - #3709, #3282, #1354, #2554 and #2758 want the model version of this. A commenter on #3709 already asked for subagents to use the other models a provider offers.
- copilot-sdk#1544 named routing subagent tasks to a local endpoint. Its author closed it 14 minutes later while still investigating, and nobody from GitHub replied.
Guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Línea de trabajo
Comienza con la ruta de dispatch de task tool y el manejo de custom-agent frontmatter; después, sigue cómo COPILOT_PROVIDER_BASE_URL para toda la sesión y el modelo por agente llegan al provider. Define cómo un subagent selecciona su propio endpoint mientras el agente principal mantiene el provider de la sesión, y verifica que una sesión que contenga ambos agentes dirija las solicitudes correctamente sin confusión por los fallbacks.
Escrito por el modelo de indexación a partir del texto del issue.
Evaluación
- Área
- ai, cli
- Tipo de issue
- Nueva funcionalidad
- Dificultad
- 5/5
- Tiempo estimado
- Más de una semana
- Estado de actividad
- Activo
- Claridad
- Bastante claro
- Aptitud para principiantes
- 45/100