This commit is contained in:
seb
2026-09-22 20:11:46 +02:00
parent 746c4749ab
commit 7880f9ba9d
3 changed files with 78 additions and 2 deletions

1
.gitignore vendored
View File

@@ -1,3 +1,4 @@
node_modules/
examples/.env
examples/invoice.pdf
examples/prompts.log

75
AGENTS.md Normal file
View File

@@ -0,0 +1,75 @@
# AGENTS.md
Orientation notes for AI coding assistants working in this repo. Read this first.
## What this is
`llmorbiter` — a small (v0.1.0, 0BSD) **LLM tool-calling orchestrator with provider
abstraction**. Pure ES modules (`"type": "module"`). Only runtime dependency is `dotenv`.
No build step, no test runner, no README (this file is the orientation doc).
## Layout
```
src/
index.js # public entry — re-exports everything
LLMOrbiter.js # core orchestrator (~364 lines)
Tool.js # defineTool() + ToolError + DirectReturnError
providers/
OpenRouterProvider.js # streaming OpenRouter SSE provider
examples/
weather.js # minimal tool-calling demo
tool-error-retry.js # tool-error + LLM self-correction demo (has PASS/FAIL asserts)
pdf-pages.js # PDF -> per-page LLM processing (500 lines, largest)
tools/weather.js # sample static-data weather tool
```
## Public API (`src/index.js`)
Exports: `LLMOrbiter`, `OpenRouterProvider`, `defineTool`, `ToolError`, `DirectReturnError`.
- `defineTool({ name, description, parameters, strict=true, invoke })` -> `{ spec, invoke, name }`.
`spec` is the OpenAI-compatible function schema sent to the LLM; `invoke(args, { signal })`
is the local implementation.
- `ToolError(message)` — throw from a tool to signal a recoverable error back to the LLM.
- `DirectReturnError(data)` — throw from a tool to stop the loop immediately; `run()` resolves
with `{ directReturn: true, data, ... }`.
### `new LLMOrbiter(provider, opts)`
`opts` are lifecycle callbacks: `onLLMCall`, `onUsage`, `onToolCall`, `onToolError`,
`onToolResult`, `onStatus`, `onContent`, `onReasoning`.
### `orbiter.run(opts)`
`{ prompt, messages, model, tools, maxIterations=10, tool_choice, extraBody, signal }`.
Loop: send messages + tool specs -> if `tool_calls` come back, invoke locals and feed results
back -> repeat until no more tool calls or `maxIterations`. Returns
`{ content, toolResults, usage, rawUsage, iterations, messages, ... }`; the returned `messages`
can seed the next `run()` for conversation continuity (a leading `{role:'system'}` entry is the
system prompt). `orbiter.abort(reason)` cancels the active run; aborts surface as
`DOMException('...', 'AbortError')`.
### `OpenRouterProvider`
`new OpenRouterProvider({ apiKey, apiUrl, siteUrl, siteName })`. Method:
`chatCompletions({ model, messages, tools, tool_choice, signal, extraBody, onStatus, onContent, onReasoning })`
— streams SSE, assembles `{ content, tool_calls, finish_reason, usage, reasoning_details, reasoning }`.
`apiUrl` defaults to `https://openrouter.ai/api/v1/chat/completions`.
## Gotchas / notes
- Examples need `OPENROUTER_API_KEY` (in `examples/.env` or via `--key`). Default model in the
examples: `deepseek/deepseek-v4-flash-0731`.
- `.gitignore` ignores `node_modules/`, `examples/.env`, `examples/invoice.pdf`.
- `pdf-pages.js` shells out to `pdftotext -layout`, splits pages on `\f`, and appends prompts
to `examples/prompts.log`.
- `OpenRouterProvider._readStream` currently writes reasoning straight to `process.stdout`
(debug-style side effect) rather than only via `onReasoning` — worth knowing if refactoring.
## Style conventions observed
- 4-space indent, single quotes, semicolons, `'use strict';` header.
- Comments use em dashes (`—`) and `───` section dividers in examples.

View File

@@ -21,7 +21,7 @@
* Create a tool from a definition.
* Returns { spec, invoke } where spec is the wire-format object sent to the LLM.
*/
export function defineTool({ name, description, parameters, strict = true, invoke }) {
export function defineTool({ name, description, parameters, strict = false, invoke }) {
if (!name) throw new Error('Tool must have a name');
if (typeof invoke !== 'function') throw new Error(`Tool "${name}" must have an invoke function`);