mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-10-06 02:48:25 +00:00
lithos-llm now owns which named secrets each provider reads and how they
shape into its auth scheme, including a derived `<PROVIDER>_API_KEY` for
operator-defined providers. Fabro's job shrinks to supplying the store:
`VaultCredentialSource` hands lithos a lookup that reads the process
environment, then the vault, under the same conventional names.
What Fabro still adds on top: the Codex OAuth credential in the vault,
refreshed and persisted when it expires; `{{ secrets.NAME }}` tokens in a
provider's `default_headers`, resolved against the vault and re-sent as
credential headers; and OpenAI organization and project headers from the
environment.
Deleted with the `metadata.fabro.credentials` list: `CredentialRef`,
`CredentialResolver`, `EnvCredentialSource` (now
`VaultCredentialSource::environment_only`), and the `env_var_names` /
`expected_vault_secret_name` helpers, replaced by `secret_names` and
`expected_secret_name` over the lithos table. `openai-codex` joins the
first-party provider id constants.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2.3 KiB
2.3 KiB
LLM Client Resolution
This document defines how Fabro resolves LLM credentials and constructs fabro-llm clients.
Core Rules
fabro_auth::CredentialSourceis the credential authority.- Long-lived runtime contexts store
Arc<dyn CredentialSource>andArc<Catalog>, notClient. - Call
fabro_llm::client::Client::from_source(&source, catalog).await?at the point of use. - Standalone setup and tests that use default settings build a default
Arc<Catalog>locally, then pass it explicitly. GenerateParams::new(model, client)always receives an explicitArc<Client>.- When a caller needs diagnostics in runtime request-serving paths, call
source.resolve(catalog)directly and consume bothcredentialsandauth_issues. VaultCredentialSourceis the normal source for vault-backed runtime contexts;VaultCredentialSource::environment_only()serves env-only or no-vault contexts.
Why
- Rebuilding a client from the source at point of use preserves OAuth refresh behavior on long-running processes.
- Holding the source on contexts avoids process-global installs and cross-context leakage.
- Threading the catalog into credential resolution keeps custom providers, aliases, header-only providers, and API model IDs consistent across auth, client registration, and request translation.
- Requiring an explicit client on
GenerateParamsmakes the old silent fallback bug unrepresentable.
Application
- Workflow state lives on
RunServices.llm_sourceandRunServices.catalog. - Server state lives on
AppState.llm_sourceandAppState.catalog(). - Hooks and other long-lived executors receive a source plus catalog and derive clients when they actually generate.
- One-shot CLI commands may resolve a source locally, build a default settings catalog if they do not load runtime catalog settings, then derive a client once for that operation.
Enforcement
- Do not add new
Client::from_env-style shortcuts in production paths. - Do not cache a long-lived
Clientwhere OAuth refresh or storage-dir rebinding matters. - Do not construct LLM clients or resolve credentials without an explicit
Arc<Catalog>or&Catalog. - Mirror server-secrets-strategy.md: production credential resolution should be explicit about where secrets come from and how they flow into subprocesses.