opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: label chatd metrics by model, add stream-state diagnostics (#24475)

Browse Source 
Adds production-observability metrics to coderd/x/chatd/ for
model-level correlation and a chatStreams memory-leak investigation.

- Label per-request chatd metrics (steps_total, message_count,
  prompt_size_bytes, tool_result_size_bytes, ttft_seconds,
  compaction_total) with `model` and enrich the per-turn logger
  with provider/model.
- Add `coderd_chatd_stream_retries_total{provider, model, kind}`
  counter incremented in chatloop before OnRetry.
- Register a prometheus.Collector exposing `streams_active`,
  `stream_buffer_size_max`, `stream_buffer_events`,
  `stream_subscribers` from p.chatStreams.
- Add `coderd_chatd_stream_buffer_dropped_total` counter,
  incremented per publishToStream drop independently of the
  existing log-rate-limited bufferDropCount.
- Snapshot logger/model before the title-generation goroutine to
  avoid a data race with the logger/model rebind below it.

> 🤖
This commit is contained in:
Cian Johnston
2026-04-17 16:16:30 +01:00
committed by GitHub
parent 91f9de27a1
commit 4b585465b8
7 changed files with 690 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/admin/integrations/prometheus.md
+12 -6
View File
@@ -199,12 +199,18 @@ deployment. They will always be available from the agent.
| `coderd_authz_prepare_authorize_duration_seconds` | histogram | Duration of the 'PrepareAuthorize' call in seconds. | |
| `coderd_build_info` | gauge | Describes the current build/version of the Coder server. Value is always 1. | `revision` `version` |
| `coderd_chatd_chats` | gauge | Number of chats being processed, by state. | `state` |
| `coderd_chatd_compaction_total` | counter | Total compaction outcomes (only recorded when compaction was triggered or failed). | `provider` `result` |
| `coderd_chatd_message_count` | histogram | Number of messages in the prompt per LLM request. | `provider` |
| `coderd_chatd_prompt_size_bytes` | histogram | Estimated byte size of the prompt per LLM request. | `provider` |
| `coderd_chatd_steps_total` | counter | Total agentic loop steps across all chats. | `provider` |
| `coderd_chatd_tool_result_size_bytes` | histogram | Size in bytes of each tool execution result. | `provider` `tool_name` |
| `coderd_chatd_ttft_seconds` | histogram | Time-to-first-token: wall time from LLM request to first streamed chunk. | `provider` |
| `coderd_chatd_compaction_total` | counter | Total compaction outcomes (only recorded when compaction was triggered or failed). | `model` `provider` `result` |
| `coderd_chatd_message_count` | histogram | Number of messages in the prompt per LLM request. | `model` `provider` |
| `coderd_chatd_prompt_size_bytes` | histogram | Estimated byte size of the prompt per LLM request. | `model` `provider` |
| `coderd_chatd_steps_total` | counter | Total agentic loop steps across all chats. | `model` `provider` |
| `coderd_chatd_stream_buffer_dropped_total` | counter | Number of chat stream buffer events dropped due to the per-chat buffer cap. | |
| `coderd_chatd_stream_buffer_events` | gauge | Sum of current buffer lengths across all chat streams. | |
| `coderd_chatd_stream_buffer_size_max` | gauge | Maximum current buffer length across all chat streams. | |
| `coderd_chatd_stream_retries_total` | counter | Total LLM stream retries. | `kind` `model` `provider` |
| `coderd_chatd_stream_subscribers` | gauge | Current number of chat stream subscribers across all chat streams. | |
| `coderd_chatd_streams_active` | gauge | Current number of chat stream state entries (in-flight plus retained). | |
| `coderd_chatd_tool_result_size_bytes` | histogram | Size in bytes of each tool execution result. | `model` `provider` `tool_name` |
| `coderd_chatd_ttft_seconds` | histogram | Time-to-first-token: wall time from LLM request to first streamed chunk. | `model` `provider` |
| `coderd_db_query_counts_total` | counter | Total number of queries labelled by HTTP route, method, and query name. | `method` `query` `route` |
| `coderd_db_query_latencies_seconds` | histogram | Latency distribution of queries in seconds. | `query` |
| `coderd_db_tx_duration_seconds` | histogram | Duration of transactions in seconds. | `success` `tx_id` |