Skip to content

docs(telemetry): document summary.tokens.llm.prompt_cached and completion_reasoning (#2305) #2318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
r266-tech wants to merge 2 commits into
base: main
Choose a base branch
from
Open

docs(telemetry): document summary.tokens.llm.prompt_cached and completion_reasoning (#2305) #2318

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d72aff3
docs(telemetry): document summary.tokens.llm.prompt_cached and comple…
r266-tech May 29, 2026
7a5a6e3
docs(telemetry): document summary.tokens.llm.prompt_cached and comple…
r266-tech May 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion docs/en/guides/07-operation-telemetry.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,9 @@ Typical response shape:
"llm": {
"input": 12,
"output": 6,
"total": 18
"total": 18,
"prompt_cached": 8,
"completion_reasoning": 4
}
},
"vector": {
Expand Down Expand Up @@ -163,6 +165,8 @@ Only fields that are actually produced by an operation are returned. Missing gro
| `summary.tokens.llm.input` | Total LLM input tokens |
| `summary.tokens.llm.output` | Total LLM output tokens |
| `summary.tokens.llm.total` | Total LLM tokens |
| `summary.tokens.llm.prompt_cached` | Cached prompt tokens reported by the provider |
| `summary.tokens.llm.completion_reasoning` | Reasoning tokens in the completion reported by the provider |
| `summary.tokens.embedding.total` | Total embedding-model tokens |

### `summary.vector`
Expand Down
6 changes: 5 additions & 1 deletion docs/zh/guides/07-operation-telemetry.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,9 @@ Telemetry 是按需返回的。只有你显式请求时，OpenViking 才会在
"llm": {
"input": 12,
"output": 6,
"total": 18
"total": 18,
"prompt_cached": 8,
"completion_reasoning": 4
}
},
"vector": {
Expand Down Expand Up @@ -163,6 +165,8 @@ summary 顶层这 3 个基础字段总会存在：
| `summary.tokens.llm.input` | LLM 输入 token 总量 |
| `summary.tokens.llm.output` | LLM 输出 token 总量 |
| `summary.tokens.llm.total` | LLM token 总量 |
| `summary.tokens.llm.prompt_cached` | 服务方返回的命中缓存的 prompt token 数 |
| `summary.tokens.llm.completion_reasoning` | 服务方返回的 completion 中的推理 token 数 |
| `summary.tokens.embedding.total` | embedding 模型 token 总量 |

### `summary.vector`
Expand Down