Merge branch 'main' into adil/agent_format

2026-06-17 15:25:17 +02:00 · 2025-09-30 19:07:49 -07:00 · 2025-09-30 19:07:49 -07:00 · d588e3da98
commit d588e3da98
parent 94d57804d7 f4d65e2469
34 changed files with 292 additions and 2525 deletions
--- a/arch/envoy.template.yaml
+++ b/arch/envoy.template.yaml
@ -64,6 +64,8 @@ static_resources:
                  typed_config:
                    "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
                    path: "/var/log/access_ingress.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%"
                route_config:
                  name: local_routes
                  virtual_hosts:
@ -117,6 +119,8 @@ static_resources:
                  typed_config:
                    "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
                    path: "/var/log/access_ingress_prompt.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%"
                route_config:
                  name: local_routes
                  virtual_hosts:
@ -425,6 +429,8 @@ static_resources:
                  typed_config:
                    "@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%"
                route_config:
                  name: local_routes
                  virtual_hosts:
@ -515,6 +521,8 @@ static_resources:
                  typed_config:
                    "@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%"
                route_config:
                  name: local_routes
                  virtual_hosts:
@ -705,6 +713,56 @@ static_resources:
              tls_minimum_protocol_version: TLSv1_2
              tls_maximum_protocol_version: TLSv1_3

+    - name: moonshotai
+      connect_timeout: 0.5s
+      type: LOGICAL_DNS
+      dns_lookup_family: V4_ONLY
+      lb_policy: ROUND_ROBIN
+      load_assignment:
+        cluster_name: moonshotai
+        endpoints:
+          - lb_endpoints:
+              - endpoint:
+                  address:
+                    socket_address:
+                      address: api.moonshot.ai
+                      port_value: 443
+                  hostname: "api.moonshot.ai"
+      transport_socket:
+        name: envoy.transport_sockets.tls
+        typed_config:
+          "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
+          sni: api.moonshot.ai
+          common_tls_context:
+            tls_params:
+              tls_minimum_protocol_version: TLSv1_2
+              tls_maximum_protocol_version: TLSv1_3
+
+    - name: zhipu
+      connect_timeout: 0.5s
+      type: LOGICAL_DNS
+      dns_lookup_family: V4_ONLY
+      lb_policy: ROUND_ROBIN
+      load_assignment:
+        cluster_name: zhipu
+        endpoints:
+          - lb_endpoints:
+              - endpoint:
+                  address:
+                    socket_address:
+                      address: open.bigmodel.cn
+                      port_value: 443
+                  hostname: "open.bigmodel.cn"
+      transport_socket:
+        name: envoy.transport_sockets.tls
+        typed_config:
+          "@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
+          sni: open.bigmodel.cn
+          common_tls_context:
+            tls_params:
+              tls_minimum_protocol_version: TLSv1_2
+              tls_maximum_protocol_version: TLSv1_3
+
    - name: together_ai
      connect_timeout: 0.5s
      type: LOGICAL_DNS
--- a/arch/supervisord.conf
+++ b/arch/supervisord.conf
@ -2,21 +2,21 @@
 nodaemon=true

 [program:brightstaff]
-command=sh -c "RUST_LOG=debug /app/brightstaff 2>&1 | tee /var/log/brightstaff.log"
+command=sh -c "RUST_LOG=info /app/brightstaff 2>&1 | tee /var/log/brightstaff.log | while IFS= read -r line; do echo '[brightstaff]' \"$line\"; done"
 stdout_logfile=/dev/stdout
 redirect_stderr=true
 stdout_logfile_maxbytes=0
 stderr_logfile_maxbytes=0

 [program:envoy]
-command=/bin/sh -c "python -m cli.config_generator && envsubst < /etc/envoy/envoy.yaml > /etc/envoy.env_sub.yaml && envoy -c /etc/envoy.env_sub.yaml --component-log-level wasm:info --log-format '[%%Y-%%m-%%d %%T.%%e][%%l] %%v' 2>&1 | tee /var/log/envoy.log"
+command=/bin/sh -c "python -m cli.config_generator && envsubst < /etc/envoy/envoy.yaml > /etc/envoy.env_sub.yaml && envoy -c /etc/envoy.env_sub.yaml --component-log-level wasm:info --log-format '[%%Y-%%m-%%d %%T.%%e][%%l] %%v' 2>&1 | tee /var/log/envoy.log | while IFS= read -r line; do echo '[envoy_logs] ' \"$line\"; done"
 stdout_logfile=/dev/stdout
 redirect_stderr=true
 stdout_logfile_maxbytes=0
 stderr_logfile_maxbytes=0

 [program:tail_access_logs]
-command=/bin/sh -c "tail -F /var/log/access_*.log"
+command=/bin/sh -c "tail -F /var/log/access_*.log | while IFS= read -r line; do echo '[access_logs]' \"$line\"; done"
 stdout_logfile=/dev/stdout
 redirect_stderr=true
 stdout_logfile_maxbytes=0
--- a/arch/tools/README.md
+++ b/arch/tools/README.md
@ -19,7 +19,7 @@ source venv/bin/activate

 ### Step 3: Run the build script
 ```bash
-pip install archgw==0.3.14
+pip install archgw==0.3.15
 ```

 ## Uninstall Instructions: archgw CLI
--- a/arch/tools/cli/config_generator.py
+++ b/arch/tools/cli/config_generator.py
@ -20,6 +20,8 @@ SUPPORTED_PROVIDERS = [
    "azure_openai",
    "xai",
    "ollama",
+    "moonshotai",
+    "zhipu",
 ]


--- a/arch/tools/cli/consts.py
+++ b/arch/tools/cli/consts.py
@ -10,4 +10,4 @@ SERVICE_NAME_MODEL_SERVER = "model_server"
 SERVICE_ALL = "all"
 MODEL_SERVER_LOG_FILE = "~/archgw_logs/modelserver.log"
 ARCHGW_DOCKER_NAME = "archgw"
-ARCHGW_DOCKER_IMAGE = os.getenv("ARCHGW_DOCKER_IMAGE", "katanemo/archgw:0.3.14")
+ARCHGW_DOCKER_IMAGE = os.getenv("ARCHGW_DOCKER_IMAGE", "katanemo/archgw:0.3.15")
--- a/arch/tools/poetry.lock
+++ b/arch/tools/poetry.lock
@ -2,7 +2,7 @@

 [[package]]
 name = "archgw_modelserver"
-version = "0.3.14"
+version = "0.3.15"
 description = "A model server for serving models"
 optional = false
 python-versions = "*"
@ -635,4 +635,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "18a3144509286d68efc9711706943ace163d0d35cd3e700511b77d8c2ac1b303"
+content-hash = "70deeecce65e4760e1a50c3d232004842cbd6397ef45163d315269ac7de8e9fc"
--- a/arch/tools/pyproject.toml
+++ b/arch/tools/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "archgw"
-version = "0.3.14"
+version = "0.3.15"
 description = "Python-based CLI tool to manage Arch Gateway."
 authors = ["Katanemo Labs, Inc."]
 packages = [
@ -10,7 +10,7 @@ readme = "README.md"

 [tool.poetry.dependencies]
 python = "^3.10"
-archgw_modelserver = "^0.3.14"
+archgw_modelserver = "^0.3.15"
 click = "^8.1.7"
 jinja2 = "^3.1.4"
 jsonschema = "^4.23.0"