feat(telemetry): integrate OpenTelemetry observability stack with health metrics

- Add OpenTelemetry SDK, OTLP exporter, Prometheus integration
- Implement connection tracking with active/total/disconnection metrics
- Add health endpoint with uptime and connection counts
- Integrate tracing spans for socket events and engine messages
- Add metrics collection for event handling duration
- Update health endpoint to include live runtime state
- Add graceful telemetry shutdown in main function
- Implement engine session active metrics tracking
- Add namespace-specific attributes to connection metrics
- Introduce message edit history retrieval endpoint
- Add scheduled message CRUD operations and dispatcher
- Update Socket.IO event registration with observability
- Refactor component update to remove dead code allowance
- Add comprehensive environment variables documentation
- Implement detailed development guidelines in AGENTS.md
This commit is contained in:
zhenyi
2026-06-11 13:53:29 +08:00
parent 40241e5db3
commit 0dbac480ae
22 changed files with 3116 additions and 64 deletions
Generated
+265
View File
@@ -1449,13 +1449,16 @@ version = "0.1.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0"
dependencies = [
"base64",
"bytes",
"futures-channel",
"futures-util",
"http 1.4.2",
"http-body",
"hyper",
"ipnet",
"libc",
"percent-encoding",
"pin-project-lite",
"socket2 0.6.4",
"tokio",
@@ -1612,6 +1615,12 @@ dependencies = [
"fred",
"futures-util",
"jsonwebtoken",
"opentelemetry",
"opentelemetry-appender-tracing",
"opentelemetry-otlp",
"opentelemetry-prometheus",
"opentelemetry_sdk",
"prometheus",
"prost",
"prost-types",
"rand 0.9.4",
@@ -1626,6 +1635,7 @@ dependencies = [
"tonic-prost",
"tonic-prost-build",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
"uuid",
"walkdir",
@@ -1650,6 +1660,12 @@ dependencies = [
"serde_core",
]
[[package]]
name = "ipnet"
version = "2.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d98f6fed1fde3f8c21bc40a1abb88dd75e67924f9cffc3ef95607bad8017f8e2"
[[package]]
name = "itertools"
version = "0.14.0"
@@ -1966,6 +1982,108 @@ version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
[[package]]
name = "opentelemetry"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b0142c63252a9e054e68a4c61a5778f7b14f576274d593f8ce883d191a099682"
dependencies = [
"futures-core",
"futures-sink",
"js-sys",
"pin-project-lite",
"thiserror 2.0.18",
"tracing",
]
[[package]]
name = "opentelemetry-appender-tracing"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c0080f0dc1d7c786f467cd85a4e395fcab11ee852004f39a29a18ab7c25d837"
dependencies = [
"opentelemetry",
"tracing",
"tracing-core",
"tracing-subscriber",
]
[[package]]
name = "opentelemetry-http"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5683015d09e2df236ef005b17f6f196f0d5f6313c4fa43a7b6a53b52776e4331"
dependencies = [
"async-trait",
"bytes",
"http 1.4.2",
"opentelemetry",
"reqwest",
]
[[package]]
name = "opentelemetry-otlp"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9966929966d17620d7c316c643ba62631826e10021409357772d5eea84f62c35"
dependencies = [
"http 1.4.2",
"opentelemetry",
"opentelemetry-http",
"opentelemetry-proto",
"opentelemetry_sdk",
"prost",
"reqwest",
"thiserror 2.0.18",
"tokio",
"tonic",
"tonic-types",
]
[[package]]
name = "opentelemetry-prometheus"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c0359983e7f79cf33c9abd89e5d7ddf67c46c419d0148598022d70e70c01aba"
dependencies = [
"once_cell",
"opentelemetry",
"opentelemetry_sdk",
"prometheus",
"tracing",
]
[[package]]
name = "opentelemetry-proto"
version = "0.32.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56d658ba1faf63f7b9c492cfbe6e0ec365440a16132d3270c1065f7b33f1b638"
dependencies = [
"opentelemetry",
"opentelemetry_sdk",
"prost",
"tonic",
"tonic-prost",
]
[[package]]
name = "opentelemetry_sdk"
version = "0.32.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b59f80e1ac4d5ff7a2db8fb6c80badb7f0f3f858211fba08dd9aaec750894f9"
dependencies = [
"futures-channel",
"futures-executor",
"futures-util",
"opentelemetry",
"percent-encoding",
"portable-atomic",
"rand 0.9.4",
"thiserror 2.0.18",
"tokio",
"tokio-stream",
]
[[package]]
name = "parking"
version = "2.2.1"
@@ -2122,6 +2240,21 @@ dependencies = [
"unicode-ident",
]
[[package]]
name = "prometheus"
version = "0.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3ca5326d8d0b950a9acd87e6a3f94745394f62e4dae1b1ee22b2bc0c394af43a"
dependencies = [
"cfg-if",
"fnv",
"lazy_static",
"memchr",
"parking_lot",
"protobuf",
"thiserror 2.0.18",
]
[[package]]
name = "prost"
version = "0.14.4"
@@ -2175,6 +2308,26 @@ dependencies = [
"prost",
]
[[package]]
name = "protobuf"
version = "3.7.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d65a1d4ddae7d8b5de68153b48f6aa3bba8cb002b243dbdbc55a5afbc98f99f4"
dependencies = [
"once_cell",
"protobuf-support",
"thiserror 1.0.69",
]
[[package]]
name = "protobuf-support"
version = "3.7.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3e36c2f31e0a47f9280fb347ef5e461ffcd2c52dd520d8e216b52f93b0b0d7d6"
dependencies = [
"thiserror 1.0.69",
]
[[package]]
name = "pulldown-cmark"
version = "0.13.4"
@@ -2418,6 +2571,37 @@ version = "0.8.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d6f6ff9a378485b298a5286656da665ba74413d36db0979633275d2e708145d4"
[[package]]
name = "reqwest"
version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
dependencies = [
"base64",
"bytes",
"futures-channel",
"futures-core",
"futures-util",
"http 1.4.2",
"http-body",
"http-body-util",
"hyper",
"hyper-util",
"js-sys",
"log",
"percent-encoding",
"pin-project-lite",
"sync_wrapper",
"tokio",
"tower",
"tower-http",
"tower-service",
"url",
"wasm-bindgen",
"wasm-bindgen-futures",
"web-sys",
]
[[package]]
name = "ring"
version = "0.17.14"
@@ -3073,6 +3257,9 @@ name = "sync_wrapper"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263"
dependencies = [
"futures-core",
]
[[package]]
name = "synstructure"
@@ -3370,6 +3557,17 @@ dependencies = [
"tonic-build",
]
[[package]]
name = "tonic-types"
version = "0.14.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73ab1b02061f83d519bba3caa167f88f261ef05720ab8ebc954ade70de3348e8"
dependencies = [
"prost",
"prost-types",
"tonic",
]
[[package]]
name = "tower"
version = "0.5.3"
@@ -3389,6 +3587,24 @@ dependencies = [
"tracing",
]
[[package]]
name = "tower-http"
version = "0.6.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4cfcf7e2740e6fc6d4d688b4ef00650406bb94adf4731e43c096c3a19fe40840"
dependencies = [
"bitflags",
"bytes",
"futures-util",
"http 1.4.2",
"http-body",
"pin-project-lite",
"tower",
"tower-layer",
"tower-service",
"url",
]
[[package]]
name = "tower-layer"
version = "0.3.3"
@@ -3445,6 +3661,32 @@ dependencies = [
"tracing-core",
]
[[package]]
name = "tracing-opentelemetry"
version = "0.33.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "adbc64cba7137545b8044cb1fe9814f7aacf3c6b5f9b45be8bb5db538befdb26"
dependencies = [
"js-sys",
"opentelemetry",
"smallvec",
"tracing",
"tracing-core",
"tracing-log",
"tracing-subscriber",
"web-time",
]
[[package]]
name = "tracing-serde"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "704b1aeb7be0d0a84fc9828cae51dab5970fee5088f83d1dd7ee6f6246fc6ff1"
dependencies = [
"serde",
"tracing-core",
]
[[package]]
name = "tracing-subscriber"
version = "0.3.23"
@@ -3455,12 +3697,15 @@ dependencies = [
"nu-ansi-term",
"once_cell",
"regex-automata",
"serde",
"serde_json",
"sharded-slab",
"smallvec",
"thread_local",
"tracing",
"tracing-core",
"tracing-log",
"tracing-serde",
]
[[package]]
@@ -3646,6 +3891,16 @@ dependencies = [
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-futures"
version = "0.4.73"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "54568702fabf5d4849ce2b90fadfa64168a097eaf4b351ce9df8b687a0086aaf"
dependencies = [
"js-sys",
"wasm-bindgen",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.123"
@@ -3712,6 +3967,16 @@ dependencies = [
"semver",
]
[[package]]
name = "web-sys"
version = "0.3.100"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6e0871acf327f283dc6da28a1696cdc64fb355ba9f935d052021fa77f35cce69"
dependencies = [
"js-sys",
"wasm-bindgen",
]
[[package]]
name = "web-time"
version = "1.1.0"