apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-07-11 16:12:13 +02:00
Code Issues Projects Releases Packages Wiki Activity

docs: document model provider headers

Browse source
This commit is contained in:
Open Agent Harness 2026-05-28 19:44:55 +00:00
parent 554a3d1f6a
commit 2a631b8bb9
3 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/source/resources/configuration_reference.rst
View file

@ -7,6 +7,9 @@ The following is a complete reference of the ``plano_config.yml`` that controls
the Plano gateway. This where you enable capabilities like routing to upstream LLm providers, defining prompt_targets the Plano gateway. This where you enable capabilities like routing to upstream LLm providers, defining prompt_targets
where prompts get routed to, apply guardrails, and enable critical agent observability features. where prompts get routed to, apply guardrails, and enable critical agent observability features.
``model_providers`` entries support an optional ``headers`` map for extra string HTTP headers sent to the
upstream provider. The deprecated ``llm_providers`` key accepts the same provider fields for legacy configs.
.. literalinclude:: includes/plano_config_full_reference.yaml .. literalinclude:: includes/plano_config_full_reference.yaml
:language: yaml :language: yaml
:linenos: :linenos:

5
docs/source/resources/includes/plano_config_full_reference.yaml
View file

@ -42,10 +42,15 @@ model_providers:
passthrough_auth: true passthrough_auth: true
# Custom/self-hosted endpoint with explicit http_host override # Custom/self-hosted endpoint with explicit http_host override
# headers: optional key-value map of extra HTTP headers sent to the upstream
# provider. Legacy llm_providers entries support the same provider fields.
- model: openai/llama-3.3-70b - model: openai/llama-3.3-70b
base_url: https://api.custom-provider.com base_url: https://api.custom-provider.com
http_host: api.custom-provider.com http_host: api.custom-provider.com
access_key: $CUSTOM_API_KEY access_key: $CUSTOM_API_KEY
headers:
User-Agent: "Plano/1.0"
X-Organization-Id: "org-example"
# Model aliases - use friendly names instead of full provider model names # Model aliases - use friendly names instead of full provider model names
model_aliases: model_aliases:

6
docs/source/resources/includes/plano_config_full_reference_rendered.yaml
View file

@ -82,6 +82,9 @@ listeners:
base_url: https://api.custom-provider.com base_url: https://api.custom-provider.com
cluster_name: openai_api.custom-provider.com cluster_name: openai_api.custom-provider.com
endpoint: api.custom-provider.com endpoint: api.custom-provider.com
headers:
User-Agent: Plano/1.0
X-Organization-Id: org-example
http_host: api.custom-provider.com http_host: api.custom-provider.com
model: llama-3.3-70b model: llama-3.3-70b
name: openai/llama-3.3-70b name: openai/llama-3.3-70b
@ -138,6 +141,9 @@ model_providers:
base_url: https://api.custom-provider.com base_url: https://api.custom-provider.com
cluster_name: openai_api.custom-provider.com cluster_name: openai_api.custom-provider.com
endpoint: api.custom-provider.com endpoint: api.custom-provider.com
headers:
User-Agent: Plano/1.0
X-Organization-Id: org-example
http_host: api.custom-provider.com http_host: api.custom-provider.com
model: llama-3.3-70b model: llama-3.3-70b
name: openai/llama-3.3-70b name: openai/llama-3.3-70b