Per-agent provider selection for custom agents
Personne n'a encore pris cette issue.
- Langage dominant
- Shell
- Étoiles
- 11.2k
- Forks
- 1.9k
- Merge moyen
- 14 h 16 min
- PR mergées (30 j)
- 6
Description
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.
Guide de contribution
Ouvrir le guide de contribution
Par où commencer
- Lisez l'issue en entier, puis le guide de contribution du projet.
- Signalez en commentaire que vous la prenez — cela évite que deux personnes fassent le même travail.
- Forkez le dépôt et travaillez sur une branche.
- Ouvrez une pull request qui référence le numéro de l'issue.
Piste de recherche
Commencez par le chemin de dispatch de task tool et la gestion de custom-agent frontmatter, puis suivez comment COPILOT_PROVIDER_BASE_URL au niveau de la session et le modèle par agent atteignent le provider. Définissez comment un subagent sélectionne son propre endpoint tandis que l’agent principal conserve le provider de la session, et vérifiez qu’une session contenant les deux agents achemine correctement les requêtes sans confusion liée aux fallbacks.
Rédigé par le modèle d'indexation à partir du texte de l'issue.
Évaluation
- Domaine
- ai, cli
- Type d'issue
- Fonctionnalité
- Difficulté
- 5/5
- Temps estimé
- Plus d'une semaine
- Activité
- Active
- Clarté
- Plutôt claire
- Accessibilité débutants
- 45/100