@honcho-ai/claude-honcho 0.3.3 → 0.4.0

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 (36) hide show
  1. package/.claude-plugin/plugin.json +1 -1
  2. package/README.md +111 -335
  3. package/dist/hooks/pre-tool-honcho.js +551 -605
  4. package/dist/hooks/pre-tool-honcho.js.map +11 -9
  5. package/dist/hooks/save-user-message.js +1741 -1057
  6. package/dist/hooks/save-user-message.js.map +24 -19
  7. package/dist/hooks/session-end.js +559 -617
  8. package/dist/hooks/session-end.js.map +11 -9
  9. package/dist/hooks/session-start.js +1938 -1304
  10. package/dist/hooks/session-start.js.map +31 -22
  11. package/dist/hooks/stop.js +1785 -1157
  12. package/dist/hooks/stop.js.map +25 -19
  13. package/dist/hooks/user-prompt.js +696 -16571
  14. package/dist/hooks/user-prompt.js.map +13 -90
  15. package/dist/mcp-server.js +1689 -1676
  16. package/dist/mcp-server.js.map +23 -20
  17. package/dist/skills/backfill-runner.js +1824 -911
  18. package/dist/skills/backfill-runner.js.map +27 -20
  19. package/dist/skills/{setup-runner.js → pane-runner.js} +1910 -1020
  20. package/dist/{hooks/pre-compact.js.map → skills/pane-runner.js.map} +28 -24
  21. package/dist/skills/status-runner.js +1568 -753
  22. package/dist/skills/status-runner.js.map +23 -19
  23. package/hooks/hooks.json +10 -42
  24. package/hooks/register.tsx +574 -0
  25. package/package.json +1 -1
  26. package/skills/insights/SKILL.md +3 -7
  27. package/dist/hooks/post-tool-use.js +0 -16905
  28. package/dist/hooks/post-tool-use.js.map +0 -97
  29. package/dist/hooks/pre-compact.js +0 -17087
  30. package/dist/skills/setup-runner.js.map +0 -95
  31. package/scripts/honcho-statusline.sh +0 -101
  32. package/skills/briefing/SKILL.md +0 -20
  33. package/skills/config/SKILL.md +0 -288
  34. package/skills/import/SKILL.md +0 -73
  35. package/skills/setup/SKILL.md +0 -60
  36. package/skills/status/SKILL.md +0 -30
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@honcho-ai/claude-honcho",
3
- "version": "0.3.3",
3
+ "version": "0.4.0",
4
4
  "type": "module",
5
5
  "description": "Persistent memory for Claude Code sessions using Honcho by Plastic Labs",
6
6
  "author": "Plastic Labs <hello@plasticlabs.ai>",
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  description: Distill accumulated Honcho memory into concrete Claude Code config updates — CLAUDE.md edits, output-style rules, and skill ideas
3
- allowed-tools: chat, honcho_remember, get_context, Read, Glob, AskUserQuestion, Write, Edit
3
+ allowed-tools: chat, Read, Glob, AskUserQuestion, Write, Edit
4
4
  user-invocable: true
5
5
  ---
6
6
 
@@ -54,10 +54,8 @@ Skip anything on this list, which is already written into their config: <the lis
54
54
  })
55
55
  ```
56
56
 
57
- If that call errors or hits the 120s ceiling, fall back to `honcho_remember` with
58
- `reasoning_level: "high"`. That tool is opt-in and only registered when the `rememberTool`
59
- config flag is on, so it may not be available — if it is missing, treat this path as thin and
60
- go straight to `get_context`. With a focus argument, send one query for that focus; with no
57
+ If that call errors or hits the 120s ceiling, send the same questions as separate `chat`
58
+ calls at `reasoning_level: "high"`. With a focus argument, send one query for that focus; with no
61
59
  argument, send all five axes (they run in parallel):
62
60
 
63
61
  1. How does this user want an agent to behave — autonomy, gating, what needs approval first?
@@ -66,8 +64,6 @@ argument, send all five axes (they run in parallel):
66
64
  4. What corrections or frustrations have they voiced — things to stop doing?
67
65
  5. What tooling, environment, and project defaults should be assumed without asking?
68
66
 
69
- Use `get_context` only if both paths come back thin — it is raw material, not analysis.
70
-
71
67
  ## Step 3: Filter
72
68
 
73
69
  Keep an observation only if all of these hold: