feat(llm): LLMResult.tool_calls from OpenAI-shaped responses

Parse choices[0].message.tool_calls into the ask Result; empty list when
absent. Offline gold covers tool_calls_from.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
cflmyandCursor committed 2026-09-24 20:07:59 +08:00
1 parent 46d78c6e15
commit 2d412e3bba
7 files changed
+83 -16

No files matched your search

+3
View File
@@ -70,6 +70,7 @@ import llm:ext/ai/llm.mq.md
| `tokens` | Alias of `usage.total_tokens` (agent metrics) |
| `name` | Optional handle tag (`fast` / `reasoning`) |
| `llm_calls` | `1` per ask |
| `tool_calls` | List of OpenAI-shaped tool call objects (empty when none) |
### Compat
@@ -102,4 +103,6 @@ Fallbacks: `MARQDO_LLM_API_KEY`, `MARQDO_LLM_BASE_URL`, `MARQDO_LLM_MODEL`. Ctor
- `tests/ext/llm-ask-offline.mq.md` (create + collect)
- `tests/ext/llm-stream-offline.mq.md`
- `tests/ext/llm-named-offline.mq.md` (fast/reasoning + prompt_load)
- `tests/ext/llm-tool-calls-offline.mq.md` (`tool_calls_from` / Result field)
- `tests/ext/llm-meta-offline.mq.md` · `llm-entry-prompt-offline.mq.md`
- Live: `llm-complete.mq.md` · `llm-stream-live.mq.md`
+2 -2
View File
@@ -33,7 +33,7 @@
| Named models(`llm.fast` / `llm.reasoning`) | **done** |
| Prompt document:`prompt` / `prompt_load` + `type: prompt` 正文 | **done**(无参 `ask`/`stream` → `sys.module_source` + `prompt_body`) |
| 拆 `ext/ai/llm/openai.mq.md` + `ollama` 后端 | **done** |
| tool_calls 完整 Result | 暂缓 |
| tool_calls 完整 Result | **done**(`openai.tool_calls_from` + `LLMResult.tool_calls`;`llm-tool-calls-offline`) |
| Transport → 可选 ABI 插件 | 暂缓 |
| Artifact Metadata Binding(`${env.*}` / `secret` · `sys.meta`) | **done**(Phase 1 Metadata-only + Phase 2 scope lift;[binding.md](../design/binding.md)) |
@@ -73,5 +73,5 @@
## 6. 验收金样
- Agent:`tests/ext/agent-v2-learn.mq.md` · `agent-p4-route.mq.md` · `agent-zero-llm.mq.md` · `agent-plan-preserve.mq.md` · `scripts/agent-harness.sh`
- LLM:`tests/ext/llm-ask-offline.mq.md` · `llm-stream-offline.mq.md` · `llm-ctor-offline.mq.md` · `llm-named-offline.mq.md` · `llm-meta-offline.mq.md` · `llm-entry-prompt-offline.mq.md`
- LLM:`tests/ext/llm-ask-offline.mq.md` · `llm-stream-offline.mq.md` · `llm-ctor-offline.mq.md` · `llm-named-offline.mq.md` · `llm-meta-offline.mq.md` · `llm-entry-prompt-offline.mq.md` · `llm-tool-calls-offline.mq.md`
- Binding:`tests/structure/meta-binding.mq.md` · `meta-lift.mq.md`
+9 -4
View File
@@ -265,7 +265,7 @@ Prefer declaring `model` / `api_key` / `base_url` in frontmatter Binding, then u
+ `prompt`=None
+ `path`=None
Semantic ask → **LLMResult** (`text`, `model`, `finish`, `backend`, `usage`, `name`). Prefer `[text](result)` for the answer string. Omit `prompt=` / `path=` to use the entry document (`sys.module_source` + `prompt_body`).
Semantic ask → **LLMResult** (`text`, `model`, `finish`, `backend`, `usage`, `name`, `tool_calls`). Prefer `[text](result)` for the answer string. Omit `prompt=` / `path=` to use the entry document (`sys.module_source` + `prompt_body`).
1. `path`
**p = > prompt_load path=`path`**
@@ -283,12 +283,17 @@ Semantic ask → **LLMResult** (`text`, `model`, `finish`, `backend`, `usage`, `
**text = > json.get value=`pack` key="text"**
**usage = > json.get value=`pack` key="usage"**
**finish = > json.get value=`pack` key="finish"**
**tc = > json.get value=`pack` key="tool_calls"**
1. not `tc`
**tc = > json.parse text=[]**
2. *
**_ = 1**
`result` =
| text | model | finish | backend | usage | name | llm_calls | tokens |
|------|-------|--------|---------|-------|------|-----------|--------|
| `text` | [model](self) | `finish` | [backend](self) | `usage` | [name](self) | 1 | [total_tokens](usage) |
| text | model | finish | backend | usage | name | llm_calls | tokens | tool_calls |
|------|-------|--------|---------|-------|------|-----------|--------|------------|
| `text` | [model](self) | `finish` | [backend](self) | `usage` | [name](self) | 1 | [total_tokens](usage) | `tc` |
*result*
+32 -2
View File
@@ -44,6 +44,29 @@ Extract `{prompt_tokens,completion_tokens,total_tokens}` from an OpenAI-shaped r
*usage*
## tool_calls_from
+ `data`
Extract OpenAI-shaped `choices[0].message.tool_calls` as a list (or empty list).
**choices = > json.get value=`data` key="choices"**
1. not `choices`
**empty = > json.parse text=[]**
*empty*
2. *
**c0 = [1](choices)**
**msg = > json.get value=`c0` key="message"**
1. not `msg`
**empty = > json.parse text=[]**
*empty*
2. *
**tc = > json.get value=`msg` key="tool_calls"**
1. `tc`
*tc*
2. *
**empty = > json.parse text=[]**
*empty*
## chat_completions
+ `base_url`
+ `api_key`
@@ -54,7 +77,7 @@ Extract `{prompt_tokens,completion_tokens,total_tokens}` from an OpenAI-shaped r
+ `suffix`=/chat/completions
+ `bearer`="Bearer "
POST `/chat/completions` (or stream SSE). Non-stream → `{text,usage,finish}`; stream → `{events,finish}`.
POST `/chat/completions` (or stream SSE). Non-stream → `{text,usage,finish,tool_calls}`; stream → `{events,finish}`.
**url = base_url + suffix**
**auth = bearer + api_key**
@@ -89,17 +112,24 @@ POST `/chat/completions` (or stream SSE). Non-stream → `{text,usage,finish}`;
**resp = > net.http_post url=`url` body=`body` headers=`headers`**
1. [status](resp) == 200
**data = > json.parse text=[body](resp)**
**text = [content]([message]([1]([choices](data))))**
**msg = [message]([1]([choices](data)))**
**text = > json.get value=`msg` key="content"**
1. not `text`
**text = ""**
2. *
**_ = 1**
**usage = > usage_from data=`data`**
**fr = > json.get value=[1]([choices](data)) key="finish_reason"**
1. not `fr`
**fr = "stop"**
2. *
**_ = 1**
**tc = > tool_calls_from data=`data`**
**pack = > json.parse text={"finish":"stop"}**
**pack = > json.set map=`pack` key="text" value=`text`**
**pack = > json.set map=`pack` key="usage" value=`usage`**
**pack = > json.set map=`pack` key="finish" value=`fr`**
**pack = > json.set map=`pack` key="tool_calls" value=`tc`**
*pack*
2. *
> print text=ext/ai/llm/openai: HTTP error
+8 -3
View File
@@ -234,12 +234,17 @@ import openai:ext/ai/llm/openai.mq.md
**text = > json.get value=`pack` key="text"**
**usage = > json.get value=`pack` key="usage"**
**finish = > json.get value=`pack` key="finish"**
**tc = > json.get value=`pack` key="tool_calls"**
1. not `tc`
**tc = > json.parse text=[]**
2. *
**_ = 1**
`result` =
| text | model | finish | backend | usage | name | llm_calls | tokens |
|------|-------|--------|---------|-------|------|-----------|--------|
| `text` | [model](自) | `finish` | [backend](自) | `usage` | [name](自) | 1 | [total_tokens](usage) |
| text | model | finish | backend | usage | name | llm_calls | tokens | tool_calls |
|------|-------|--------|---------|-------|------|-----------|--------|------------|
| `text` | [model](自) | `finish` | [backend](自) | `usage` | [name](自) | 1 | [total_tokens](usage) | `tc` |
*result*
+24
View File
@@ -0,0 +1,24 @@
---
title: llm tool_calls offline
description: Parse OpenAI-shaped tool_calls into a list; no network.
import openai:ext/ai/llm/openai.mq.md
import json:lib/json.mq.md
---
# main
**raw = "{\"choices\":[{\"finish_reason\":\"tool_calls\",\"message\":{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_1\",\"type\":\"function\",\"function\":{\"name\":\"lookup\",\"arguments\":\"{\\\"q\\\":\\\"marqdo\\\"}\"}}]}}]}"**
**data = > json.parse text=`raw`**
**tc = > openai.tool_calls_from data=`data`**
**n = > len value=`tc`**
> print text=`n`
**first = [1](tc)**
> print text=[id](`first`)
> print text=[type](`first`)
**fn = [function](first)**
> print text=[name](`fn`)
**empty_data = > json.parse text={"choices":[{"message":{"role":"assistant","content":"hi"}}]}**
**empty = > openai.tool_calls_from data=`empty_data`**
**en = > len value=`empty`**
> print text=`en`
+5 -5
View File
@@ -4041,21 +4041,21 @@ fn ext_llm_meta_offline() {
}
#[test]
fn ext_llm_entry_prompt_offline() {
fn ext_llm_tool_calls_offline() {
let root = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"));
let output = Command::new(env!("CARGO_BIN_EXE_marqdo"))
.args(["run", "tests/ext/llm-entry-prompt-offline.mq.md"])
.args(["run", "tests/ext/llm-tool-calls-offline.mq.md"])
.env("MARQDO_EXT", root.join("ext"))
.current_dir(&root)
.output()
.expect("run llm-entry-prompt-offline");
.expect("run llm-tool-calls-offline");
let code = output.status.code().unwrap_or(1);
let stdout = String::from_utf8_lossy(&output.stdout);
let stderr = String::from_utf8_lossy(&output.stderr);
assert_eq!(code, 0, "llm-entry-prompt-offline stderr={stderr}");
assert_eq!(code, 0, "llm-tool-calls-offline stderr={stderr}");
assert_eq!(
stdout.trim_end(),
"Say hello to Marqdo.\n\n# main\n\n**raw = > sys.module_source**\n**p = > llm.prompt_body src=`raw`**\n> print text=`p`",
"1\ncall_1\nfunction\nlookup\n0",
"stdout={stdout}"
);
}