@raindrop-ai/claude-code 0.0.19 → 0.0.21
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/plugin.json +1 -1
- package/README.md +26 -0
- package/dist/cli.js +1180 -120
- package/dist/index.cjs +1139 -97
- package/dist/index.d.cts +124 -1
- package/dist/index.d.ts +124 -1
- package/dist/index.js +1138 -97
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -45,6 +45,28 @@ Tag events with product names or custom metadata via `.claude/settings.json`:
|
|
|
45
45
|
}
|
|
46
46
|
```
|
|
47
47
|
|
|
48
|
+
## Tool catalog capture (`ai.prompt.tools`)
|
|
49
|
+
|
|
50
|
+
Claude Code hooks and transcripts never expose the request Claude Code sends to the model, so this
|
|
51
|
+
integration cannot observe the tool catalog and records nothing by default (the attribute stays
|
|
52
|
+
absent, meaning "unknown"). Supply the catalog yourself with `tools` — an array of tool
|
|
53
|
+
declarations in any shape `@raindrop-ai/core` recognizes (`{ name, description?, parameters }`,
|
|
54
|
+
`{ type: "function", name, inputSchema }`, OpenAI/Anthropic wrappers, ...):
|
|
55
|
+
|
|
56
|
+
```json
|
|
57
|
+
{
|
|
58
|
+
"tools": [
|
|
59
|
+
{ "name": "read_file", "description": "Read a file", "parameters": { "type": "object", "properties": { "path": { "type": "string" } }, "required": ["path"] } }
|
|
60
|
+
]
|
|
61
|
+
}
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
Set it in `~/.config/raindrop/config.json` (`tools`) or as JSON in the `RAINDROP_TOOLS` environment
|
|
65
|
+
variable (the variable wins). The override is recorded verbatim as `ai.prompt.tools` on every LLM
|
|
66
|
+
span reconstructed from the transcript (`gen_ai.response.model` spans), never on tool-call,
|
|
67
|
+
subagent, or permission spans, and `tools: []` records an explicitly empty catalog. Nothing is
|
|
68
|
+
inferred from hook payloads: implicit capture is not possible here.
|
|
69
|
+
|
|
48
70
|
## Custom Self-Diagnostics Signals
|
|
49
71
|
|
|
50
72
|
Replace the built-in signal categories with your own via `~/.config/raindrop/config.json`:
|
|
@@ -96,3 +118,7 @@ raindrop-claude-code debug-off # disables logging
|
|
|
96
118
|
## Docs
|
|
97
119
|
|
|
98
120
|
Full documentation: [docs.raindrop.ai/sdk/claude-code](https://docs.raindrop.ai/sdk/claude-code)
|
|
121
|
+
|
|
122
|
+
## Application Git identity
|
|
123
|
+
|
|
124
|
+
Claude Code does not infer the agent-under-test revision from the edited workspace or ambient deploy/CI metadata in the hook process. By default the new canonical application revision is unknown. Configure it under `app_git` in `~/.config/raindrop/config.json`, using `commit_sha`, `commit_dirty`, and ordinary `branch`, set `RAINDROP_COMMIT_SHA` / `RAINDROP_COMMIT_DIRTY` / `RAINDROP_BRANCH`, or set an explicit `source_directory` (or `RAINDROP_GIT_SOURCE_DIRECTORY`) that identifies the agent-under-test checkout. Set `app_git` to `false` to opt out. Automatic canonical branch discovery is off unless `detect_branch` is true, and the legacy `git.branch` workspace metadata remains unchanged.
|