Speech spend is missing from usage.jsonl and the call log
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
调研方向
Start with internal/session/tools_image.go:152-160 and internal/session/loop.go:5449, then trace how paid calls are written to v3/usage.jsonl and logs/calls.jsonl. Reproduce the speech request in an isolated profile and add an end-to-end check that confirms the speech model, cost, usage row, and codeaf logs entry.
由索引模型根据 Issue 内容生成。
描述
Seen on: dev 837b2b0.
Behaviour
A speak call raised the session total (meta.json spentUsd) by about $0.003 but wrote no row to v3/usage.jsonl or logs/calls.jsonl. So codeaf logs and day totals built from the ledger miss speech spend. Every paid call should have a usage row.
Replication
- Build dev 837b2b0 (
git checkout 837b2b0 && make build, binarybin/codeaf), or install the dev build withcurl -fsSL https://agentfield.ai/get/devaf | bash. - Use an isolated profile:
export HOME=$(mktemp -d), exportOPENROUTER_API_KEY, and keep the default model (~deepseek/deepseek-v4-flash-latest, crew on auto). - On a busy machine set
task.max_loadto0(/settings, Tasks) so the busy-machine gate does not hold tasks. cd $(mktemp -d) && codeaf, then:Say "hello from codeaf" out loud and save it as hello.mp3.- Compare the session's
meta.jsonspentUsdbefore and after withtail -n 3 $HOME/.codeaf/v3/usage.jsonlandcodeaf logs --tail.
Evidence
- meta.json
spentUsdrose by about $0.003; no new row in usage.jsonl or calls.jsonl. internal/session/tools_image.go:152-160andinternal/session/loop.go:5449: the chat belt adds media cost to the session only.
Guessed cause
A guess from reading the code, not a confirmed diagnosis. The chat belt adds media cost to the session total, not through the usage ledger.
Acceptance
- e2e: after the speech request above, usage.jsonl has one row with the speech model and its cost, and
codeaf logsshows the call.
Found while writing the public docs; manual text differences are in #1545.
🤖 Generated with Claude Code
- 主要语言
- Go
- 星标
- 115
- 派生
- 14
- 平均合并
- 9 小时 44 分钟
- 30 天内合并 PR
- 766
环境准备
我们还没有检查这个项目的环境配置文件。先看它的 README，通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
Agent-Field/CodeAF 的其他 Issue
-
area:chat bug sev:papercut
难度 2/5 1-3 小时 新手友好度 86/100
Agent-Field/CodeAF#1592 ·
维护者通常 1 天内回复
-
area:headless bug sev:critical
难度 2/5 1-3 小时 新手友好度 88/100
Agent-Field/CodeAF#1566 · 已指派 1 人 ·
维护者通常 1 天内回复
-
area:chat feature
难度 2/5 1-3 小时 新手友好度 88/100
Agent-Field/CodeAF#1510 ·
维护者通常 1 天内回复
-
area:tests bug
难度 2/5 1-3 小时 新手友好度 82/100
Agent-Field/CodeAF#1489 ·
维护者通常 1 天内回复
-
area:chat bug good first issue sev:papercut
难度 2/5 1-3 小时 新手友好度 78/100
Agent-Field/CodeAF#1470 ·
维护者通常 1 天内回复
查看 Agent-Field/CodeAF 的全部 Issue
相似的 Issue
-
automation models
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 72/100
txn2/mcp-data-platform#1984 ·
维护者通常 1 天内回复
-
agentic-workflows
难度 2/5 1-3 小时 新手友好度 68/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 88/100
维护者通常 1 天内回复
-
kind/docs prio/P2
难度 1/5 1 小时以内 新手友好度 95/100
agent-substrate/substrate#1986 ·
维护者通常 1 天内回复