apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-29 15:49:40 +02:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'main' into adil/use_standard_tracing

Browse source
This commit is contained in:
Adil Hafeez 2026-02-02 12:13:10 -08:00
commit 891f3a7413
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
102 changed files with 6426 additions and 1026 deletions
Download patch file Download diff file Expand all files Collapse all files

6
config/README.md
View file

@ -18,7 +18,7 @@ $ cargo test
```
## Local development
- Build docker image for arch gateway. Note this needs to be built once.
- Build docker image for Plano. Note this needs to be built once.
```
$ sh build_filter_image.sh
```
@ -27,9 +27,9 @@ $ cargo test
```
$ cargo build --target wasm32-wasip1 --release
```
- Start envoy with arch_config.yaml and test,
- Start envoy with config.yaml and test,
```
$ docker compose -f docker-compose.dev.yaml up archgw
$ docker compose -f docker-compose.dev.yaml up plano
```
- dev version of docker-compose file uses following files that are mounted inside the container. That means no docker rebuild is needed if any of these files change. Just restart the container and chagne will be picked up,
- envoy.template.yaml

2
config/arch_config_schema.yaml
View file

@ -66,6 +66,8 @@ properties:
type: string
enum:
- plano_orchestrator_v1
max_retries:
type: integer
type:
type: string
enum:

17
config/envoy.template.yaml
View file

@ -278,6 +278,7 @@ static_resources:
{% if listener.agents %}
# agent listeners
- name: {{ listener.name | replace(" ", "_") }}
address:
socket_address:
@ -333,7 +334,7 @@ static_resources:
auto_host_rewrite: true
prefix_rewrite: "/agents/"
cluster: bright_staff
timeout: {{ llm_gateway_listener.timeout }}
timeout: {{ listener.timeout | default('30s') }}
http_filters:
- name: envoy.filters.http.compressor
typed_config:
@ -412,7 +413,7 @@ static_resources:
"@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
path: "/var/log/access_llm.log"
format: |
[%START_TIME%] "%REQ(:METHOD)% %REQ(X-ENVOY-ORIGINAL-PATH?:PATH)% %PROTOCOL%" %RESPONSE_CODE% %RESPONSE_FLAGS% %BYTES_RECEIVED% %BYTES_SENT% %DURATION% %RESP(X-ENVOY-UPSTREAM-SERVICE-TIME)% "%REQ(X-FORWARDED-FOR)%" "%REQ(USER-AGENT)%" "%REQ(X-REQUEST-ID)%" "%REQ(:AUTHORITY)%" "%UPSTREAM_HOST%" "%UPSTREAM_CLUSTER%"
[%START_TIME%] "%REQ(:METHOD)% %REQ(X-ENVOY-ORIGINAL-PATH?:PATH)% %PROTOCOL%" %RESPONSE_CODE% %RESPONSE_FLAGS% %BYTES_RECEIVED% %BYTES_SENT% %DURATION% %RESP(X-ENVOY-UPSTREAM-SERVICE-TIME)% "%REQ(X-FORWARDED-FOR)%" "%REQ(USER-AGENT)%" "%REQ(X-REQUEST-ID)%" "%REQ(:AUTHORITY)%" "%UPSTREAM_HOST%" "%UPSTREAM_CLUSTER%" attempts=%UPSTREAM_REQUEST_ATTEMPT_COUNT%
route_config:
name: local_routes
virtual_hosts:
@ -533,7 +534,7 @@ static_resources:
"@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
path: "/var/log/access_llm.log"
format: |
[%START_TIME%] "%REQ(:METHOD)% %REQ(X-ENVOY-ORIGINAL-PATH?:PATH)% %PROTOCOL%" %RESPONSE_CODE% %RESPONSE_FLAGS% %BYTES_RECEIVED% %BYTES_SENT% %DURATION% %RESP(X-ENVOY-UPSTREAM-SERVICE-TIME)% "%REQ(X-FORWARDED-FOR)%" "%REQ(USER-AGENT)%" "%REQ(X-REQUEST-ID)%" "%REQ(:AUTHORITY)%" "%UPSTREAM_HOST%" "%UPSTREAM_CLUSTER%"
[%START_TIME%] "%REQ(:METHOD)% %REQ(X-ENVOY-ORIGINAL-PATH?:PATH)% %PROTOCOL%" %RESPONSE_CODE% %RESPONSE_FLAGS% %BYTES_RECEIVED% %BYTES_SENT% %DURATION% %RESP(X-ENVOY-UPSTREAM-SERVICE-TIME)% "%REQ(X-FORWARDED-FOR)%" "%REQ(USER-AGENT)%" "%REQ(X-REQUEST-ID)%" "%REQ(:AUTHORITY)%" "%UPSTREAM_HOST%" "%UPSTREAM_CLUSTER%" attempts=%UPSTREAM_REQUEST_ATTEMPT_COUNT%
route_config:
name: local_routes
virtual_hosts:
@ -558,6 +559,16 @@ static_resources:
auto_host_rewrite: true
cluster: {{ llm_cluster_name }}
timeout: 300s
{% if llm_gateway_listener.max_retries %}
retry_policy:
retry_on: "5xx,connect-failure,refused-stream,reset,retriable-status-codes"
num_retries: {{ llm_gateway_listener.max_retries }}
per_try_timeout: 30s
retriable_status_codes: [429, 500, 502, 503, 504]
retry_back_off:
base_interval: 0.5s
max_interval: 5s
{% endif %}
{% endfor %}
- match:
prefix: "/"

2
config/validate_plano_config.sh
View file

@ -5,7 +5,7 @@ failed_files=()
for file in $(find . -name config.yaml -o -name arch_config_full_reference.yaml); do
echo "Validating ${file}..."
touch $(pwd)/${file}_rendered
if ! docker run --rm -v "$(pwd)/${file}:/app/arch_config.yaml:ro" -v "$(pwd)/${file}_rendered:/app/arch_config_rendered.yaml:rw" --entrypoint /bin/sh katanemo/plano:0.4.3 -c "python -m planoai.config_generator" 2>&1 > /dev/null ; then
if ! docker run --rm -v "$(pwd)/${file}:/app/arch_config.yaml:ro" -v "$(pwd)/${file}_rendered:/app/arch_config_rendered.yaml:rw" --entrypoint /bin/sh katanemo/plano:0.4.4 -c "python -m planoai.config_generator" 2>&1 > /dev/null ; then
echo "Validation failed for $file"
failed_files+=("$file")
fi