mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-12 03:48:56 +00:00
ce2582e9d0
* feat(terraform): vendor terraform-provider-litellm as source of truth with endpoint drift CI * fix(terraform): address review feedback on vendored provider Replace deprecated io/ioutil with io. Remove the unused org/team CRUD client methods so the endpoint audit only tracks live call sites (54 -> 46). Redact request/response logs by parsing the JSON and recursively masking sensitive fields, which fixes the nested-object leak in the old credential_values regex, with a regex fallback for non-JSON payloads; covered by new unit tests. Docs: stop showing api_key inside vector store litellm_params and document that Sensitive attributes still persist in plaintext state, recommending litellm_credential_name and an encrypted state backend. * fix(terraform): stop persisting server-returned litellm_params into vector store state The vector store Read wrote litellm_params straight back from the API response into state. The proxy redacts secrets in those responses, so the readback overwrote user config with redaction sentinels and caused perpetual diffs, and against a server that returns raw values it would persist secrets into a non-Sensitive attribute. Read now preserves the config value like the credential and model resources do, litellm_params is marked Sensitive, and a regression test pins that a server-returned api_key never lands in state * fix(terraform): send role on team member update and stop persisting server env into MCP state The team member update payload omitted role, and the proxy leaves role unchanged when the field is absent, so a role downgrade reported as applied by Terraform never took effect on the proxy. The update now always sends the configured role (the attribute is Required). The MCP server resource wrote env straight back from API responses into a non-Sensitive attribute, pulling admin-visible secrets into state and, for sanitized responses, blanking user config. Read now preserves the config value, env is marked Sensitive, and the docs warn against passing secrets via args. Regression tests cover both fixes and fail against the previous behavior.
130 lines
3.3 KiB
Markdown
130 lines
3.3 KiB
Markdown
# litellm_team Resource
|
|
|
|
Manages a team configuration in LiteLLM. Teams allow you to group users and manage their access to models and usage limits.
|
|
|
|
## Example Usage
|
|
|
|
### Basic Team Configuration
|
|
|
|
```hcl
|
|
resource "litellm_team" "engineering" {
|
|
team_alias = "engineering-team"
|
|
models = ["gpt-4-proxy", "claude-2"]
|
|
max_budget = 1000.0
|
|
}
|
|
```
|
|
|
|
### Team with Comprehensive Configuration
|
|
|
|
```hcl
|
|
resource "litellm_team" "advanced_team" {
|
|
team_alias = "ai-research-team"
|
|
organization_id = "org_123456"
|
|
models = ["gpt-4-proxy", "claude-2", "gpt-3.5-turbo"]
|
|
|
|
# Budget and rate limiting
|
|
max_budget = 1000.0
|
|
budget_duration = "1mo"
|
|
tpm_limit = 500000
|
|
rpm_limit = 5000
|
|
blocked = false
|
|
|
|
# Team member permissions
|
|
team_member_permissions = [
|
|
"create_key",
|
|
"delete_key",
|
|
"view_spend",
|
|
"edit_team"
|
|
]
|
|
|
|
# Metadata for organization
|
|
metadata = {
|
|
department = "Engineering"
|
|
project = "AI Research"
|
|
cost_center = "R&D-001"
|
|
}
|
|
}
|
|
```
|
|
|
|
### Team with Model Dependencies
|
|
|
|
```hcl
|
|
# First create models
|
|
resource "litellm_model" "gpt4" {
|
|
model_name = "gpt-4-proxy"
|
|
custom_llm_provider = "openai"
|
|
base_model = "gpt-4"
|
|
model_api_key = var.openai_api_key
|
|
}
|
|
|
|
resource "litellm_model" "claude" {
|
|
model_name = "claude-proxy"
|
|
custom_llm_provider = "anthropic"
|
|
base_model = "claude-3-sonnet-20240229"
|
|
model_api_key = var.anthropic_api_key
|
|
}
|
|
|
|
# Then create team with access to these models
|
|
resource "litellm_team" "model_dependent_team" {
|
|
team_alias = "model-users"
|
|
models = [
|
|
litellm_model.gpt4.model_name,
|
|
litellm_model.claude.model_name
|
|
]
|
|
|
|
max_budget = 500.0
|
|
budget_duration = "1mo"
|
|
|
|
team_member_permissions = [
|
|
"view_spend"
|
|
]
|
|
}
|
|
```
|
|
|
|
## Argument Reference
|
|
|
|
The following arguments are supported:
|
|
|
|
* `team_alias` - (Required) A human-readable identifier for the team.
|
|
|
|
* `organization_id` - (Optional) The ID of the organization this team belongs to.
|
|
|
|
* `models` - (Optional) List of model names that this team can access.
|
|
|
|
* `metadata` - (Optional) A map of metadata key-value pairs associated with the team.
|
|
|
|
* `blocked` - (Optional) Whether the team is blocked from making requests. Default is `false`.
|
|
|
|
* `tpm_limit` - (Optional) Team-wide tokens per minute limit.
|
|
|
|
* `rpm_limit` - (Optional) Team-wide requests per minute limit.
|
|
|
|
* `max_budget` - (Optional) Maximum budget allocated to the team.
|
|
|
|
* `budget_duration` - (Optional) Duration for the budget cycle. Valid values are:
|
|
* `daily`
|
|
* `weekly`
|
|
* `monthly`
|
|
* `yearly`
|
|
|
|
* `team_member_permissions` - (Optional) List of permissions granted to team members. This controls what actions team members can perform within the team context.
|
|
|
|
## Attribute Reference
|
|
|
|
In addition to the arguments above, the following attributes are exported:
|
|
|
|
* `id` - The unique identifier for the team.
|
|
|
|
## Import
|
|
|
|
Teams can be imported using the team ID:
|
|
|
|
```shell
|
|
terraform import litellm_team.engineering <team-id>
|
|
```
|
|
|
|
Note: The team ID is generated when the team is created and is different from the `team_alias`.
|
|
|
|
## Note on Team Members
|
|
|
|
Team members are managed through the separate `litellm_team_member` resource. This allows for more granular control over team membership and permissions. See the `litellm_team_member` resource documentation for details on managing team members.
|