Files
claude-agent-acp/docs/model-configuration.md
Sergey Shkredov e8eb9d340f feat: narrow models to what the providers/set gateway lists (#1340)
### Summary

Addresses [IJAI-1783](https://youtrack.jetbrains.com/issue/IJAI-1783).

An organization can restrict the models its JetBrains gateway serves,
but a session routed through `providers/set` offered the whole Claude
Code catalogue, so the picker showed models the gateway then refused.
`providers/set` now lists the gateway's models before it responds, and
the model picker offers only the SDK models the gateway lists.

- `anthropic`: `GET {baseUrl}/v1/models?limit=1000`, paginated by
`has_more`/`last_id`, with the provider headers and `anthropic-version`.
- `bedrock`: `GET {baseUrl}/foundation-models` (`ListFoundationModels`,
`modelSummaries[].modelId`), the listing the JetBrains gateway answers
on its Bedrock route. Only `anthropic.` ids count. The cross-region
prefix `global` when listed, else that of the first listed id, becomes
the session's `ANTHROPIC_BEDROCK_REGION_PREFIX`, so the CLI calls the
models under the prefix the gateway serves; ids of other prefixes, and
SDK rows resolved to another prefix, are dropped.
- Rows match by `resolvedModel` (or `value`) without dates, `-vN:M`
suffixes, `[1m]` hints and provider prefixes; the narrowing runs after
the `availableModels` allowlist. When the gateway does not list the
model a session runs (the dropped default, or a resumed or recreated
session's last model), the session switches to the first listed one with
`setModel`, so the CLI does not keep running an unlisted model.
- The listing runs in the provider-update queue, so `providers/set` and
`providers/disable` apply in the order they arrive; logout also clears a
`providers/set` that is still listing.
- A 4xx answer means the gateway has no listing: `providers/set`
succeeds and nothing is narrowed. Any other failed listing (network
error, 5xx, unexpected body, 10 s timeout) fails `providers/set` with
`internal_error`, and the previous provider stays in effect. An invalid
header or a base URL with credentials fails without repeating the value.
A listing that matches no SDK model leaves the session with no model to
offer: there is no model config option.
- `vertex`, gateways set through `authenticate`, and native routing are
not listed. Setting the same gateway again reuses its listing;
`providers/disable` and logout drop it.
- `docs/model-configuration.md` describes the narrowing.

### Not covered

Background haiku requests, subagents, and a `/model` typed into the
prompt choose their own model and are not checked against the listing.

### Verification

```bash
npm run check
npm run build
npm run test:run -- --no-file-parallelism   # 2964 passed, 5 failed, 30 skipped; all 5 in session-index.test.ts, flaky on main too
```

Tests stub `fetch` (`src/tests/setup-no-network.ts` answers an empty
listing by default) and cover the listing requests and pagination, the
Bedrock region prefix and its env, region-aware matching, the dropped
default, the failing `providers/set`, and the empty picker. The
JetBrains Bedrock gateway's `/foundation-models` answers
`global.anthropic.claude-{haiku,opus,sonnet}-5-5` (seen through Junie,
which lists the same route); this adapter has not yet been run end to
end against it.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 17:03:27 +02:00

68 lines
4.8 KiB
Markdown

# Model Configuration
When using claude-agent-acp with alternative providers (e.g. AWS Bedrock), model IDs differ from the direct Anthropic API. The `CLAUDE_MODEL_CONFIG` environment variable lets you configure model overrides and availability at the deployment level.
## `CLAUDE_MODEL_CONFIG`
A JSON string with two optional fields:
| Field | Type | Description |
| ----------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------- |
| `modelOverrides` | `Record<string, string>` | Maps Anthropic model IDs to provider-specific model IDs (e.g. Bedrock model IDs or ARNs) |
| `availableModels` | `string[]` | Restricts which models are offered to users. Accepts aliases (`"opus"`), prefixes (`"opus-4-5"`), or full IDs |
### Examples
**Bedrock model overrides:**
```bash
CLAUDE_MODEL_CONFIG='{"modelOverrides":{"claude-opus-4-6":"us.anthropic.claude-opus-4-6-v1","claude-sonnet-4-5":"us.anthropic.claude-sonnet-4-5-v1"}}'
```
**Restrict available models:**
```bash
CLAUDE_MODEL_CONFIG='{"availableModels":["opus","sonnet"]}'
```
**Both together:**
```bash
CLAUDE_MODEL_CONFIG='{"modelOverrides":{"claude-opus-4-6":"us.anthropic.claude-opus-4-6-v1","claude-sonnet-4-5":"us.anthropic.claude-sonnet-4-5-v1"},"availableModels":["opus","sonnet"]}'
```
**Full Bedrock example:**
```bash
CLAUDE_CODE_USE_BEDROCK=1 \
AWS_REGION=us-west-2 \
CLAUDE_MODEL_CONFIG='{"modelOverrides":{"claude-opus-4-6":"us.anthropic.claude-opus-4-6-v1"}}' \
node dist/index.js
```
## Precedence
An ACP caller can provide `settings` via `_meta.claudeCode.options.settings` in `session/new` or `session/load`, as an object or a path to a settings file. The adapter merges `CLAUDE_MODEL_CONFIG` into those settings, so a caller that only adds hooks keeps the model settings. When both set the same key, the caller wins; the merge is shallow, so a caller's `modelOverrides` replaces the env var's map.
| Source | Priority |
| -------------------------------------------- | ---------------------------------------------- |
| `_meta.claudeCode.options.settings` (caller) | Highest — wins for each key it sets |
| `CLAUDE_MODEL_CONFIG` (env var) | Used for the keys that the caller does not set |
## Format details
- The value must be valid JSON. Invalid JSON will cause session creation to fail with a parse error.
- Only `modelOverrides` and `availableModels` keys are read; other keys in the JSON are ignored.
- Both fields map directly to the Claude Agent SDK's `Settings` type.
## Models of a `providers/set` gateway
When an ACP client routes the agent through a gateway with `providers/set`, the adapter lists the gateway's models before `providers/set` returns, with the provider headers:
- `anthropic`: `GET {baseUrl}/v1/models`, paginated by `has_more`/`last_id`.
- `bedrock`: `GET {baseUrl}/foundation-models` (Bedrock `ListFoundationModels`, `modelSummaries[].modelId`). Only `anthropic.` ids count. The cross-region prefix `global` when listed, else that of the first listed id with one (`eu` for `eu.anthropic.claude-sonnet-5`), becomes the session's `ANTHROPIC_BEDROCK_REGION_PREFIX`, and ids with other prefixes, or without one, are dropped.
The model picker then offers only the SDK models whose resolved model the gateway lists, matched without dates, version suffixes (`-v1:0`), `-fast`, `@` suffixes, context hints (`[1m]`) and provider prefixes, after the `availableModels` allowlist above. On Bedrock, a model the CLI resolved to another region prefix is dropped as well. When the gateway does not list the model a session runs, that is the default model or a resumed session's last model, the session switches to the first remaining picker row.
A 4xx answer means the gateway has no listing: `providers/set` succeeds and nothing is narrowed. A failed listing (network error, a status other than 2xx or 4xx, unexpected body, the 10 s timeout, an invalid header, or a base URL with credentials) fails `providers/set` with a JSON-RPC internal error, and the previous provider stays in effect. A listing that matches no SDK model leaves the session with no model to offer: there is no model config option. Gateways set through `authenticate`, `vertex` providers, and native routing are not listed. Setting the same gateway again (the same protocol, base URL and headers) reuses its listing, unless it answered 4xx; `providers/set` and `providers/disable` apply in the order they arrive, and logout clears the routing after `claude auth logout`, including a `providers/set` still listing; `providers/disable` and logout drop it.