ai-spend-agent 0.5.9 → 0.6.1

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.
Files changed (3) hide show
  1. package/README.md +15 -0
  2. package/dist/index.js +1275 -107
  3. package/package.json +3 -3
package/README.md CHANGED
@@ -3,14 +3,29 @@
3
3
  The full [aibill](https://github.com/futurastudio/ai-spend-agent) CLI.
4
4
 
5
5
  ```bash
6
+ npx aibill init
6
7
  npx ai-spend-agent
7
8
  # short alias
8
9
  npx aibill
9
10
  ```
10
11
 
12
+ Run `npx aibill init` from a project to detect machine-wide local Claude Code
13
+ and Codex history, print the first evidence-labeled personal receipt, and seed a private
14
+ aggregate cache under `~/.aibill/cache/`. Init never replaces missing personal
15
+ evidence with the bundled sample and never overwrites existing connected
16
+ source or audit state.
17
+
11
18
  It reads local Claude Code and Codex metadata, labels API-equivalent estimates,
12
19
  and can optionally add official OpenAI or Anthropic provider-reported cost
13
20
  through an environment-variable reference. No product telemetry is sent.
21
+ aibill never sits in the inference path and never stores, prints, or proxies provider credentials.
22
+
23
+ Connector validation (`live_verified`, `fixture_verified`, `untested`, or
24
+ `failed`) and each number's financial evidence (`verified`, `estimated`,
25
+ `detected_unverified`, or `missing`) are separate status axes. Run `npx aibill
26
+ doctor --sources` to see both with freshness and the last sanitized error.
27
+ The source registry also records read-boundary approval separately; an approved
28
+ local folder is permission to scan, not verified financial evidence.
14
29
 
15
30
  See the repository
16
31
  [README](https://github.com/futurastudio/ai-spend-agent#readme) for commands,