teamtrail 0.38.0-next.52 → 0.52.1
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.
- package/README.md +11 -16
- package/dist/app/assets/index-B8Bp4gma.js +167 -0
- package/dist/app/assets/index-CCvfI-Yv.css +1 -0
- package/dist/app/index.html +2 -2
- package/dist/cli.js +1811 -1171
- package/package.json +2 -2
- package/dist/app/assets/index-DIc_V3ys.css +0 -1
- package/dist/app/assets/index-Dskipftt.js +0 -175
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
# teamtrail
|
|
4
4
|
|
|
5
|
-
**
|
|
5
|
+
**Verified work from AI coding agents.** Agents do the work, you make the calls, and nothing counts as done until it's verified. Teamtrail breaks big work into decision tickets for Claude Code, Codex or any MCP agent, sends you only the calls that are yours, and runs your tests before anything is done. One command opens it for the agents working in your repo.
|
|
6
6
|
|
|
7
7
|
**[teamtrail.app](https://teamtrail.app)** · [Docs](https://teamtrail.app/docs/) · [GitHub](https://github.com/teamtrailhq/teamtrail)
|
|
8
8
|
|
|
@@ -107,21 +107,16 @@ A remote agent's files aren't on your machine, so it gets no worktree, and on tr
|
|
|
107
107
|
|
|
108
108
|
### Tools
|
|
109
109
|
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
| `close_ticket` | Resolve (or rule out) a ticket: resolution comment, close, DecisionRecord, unblocked tickets |
|
|
121
|
-
| `record_decision` | Keep any other decision as a DecisionRecord |
|
|
122
|
-
| `proof_report` | A ticket's Verified by Teamtrail report for its pull request: the checks Teamtrail ran, criteria verified or only claimed, the review and the decisions it relies on (also `teamtrail proof <ticket>` in a terminal) |
|
|
123
|
-
| `ask_human` / `wait_for_answer` | Ask the human through the Lookout inbox and wait for the answer |
|
|
124
|
-
| `list_inbox` / `answer_question` | Questions from every agent; answer one with the human's words from the chat (it guides the agent; only answers given in the Lookout or Slack back a decision that needs the human) |
|
|
110
|
+
`teamtrail mcp` offers about thirty tools, in these groups:
|
|
111
|
+
|
|
112
|
+
- **Trails:** `status`, `start_trail`, `resume_trail`, `update_trail`, and the discovery brief (`submit_brief`, `get_brief`).
|
|
113
|
+
- **Tickets:** `next_ticket`, `claim_ticket`, `release_ticket`, `add_ticket` and acceptance criteria (`set_criteria`).
|
|
114
|
+
- **Working and completing:** `report_progress`, `report_completion`, `verification_status`, `submit_review`, `close_ticket`, `record_decision`, and the Verified by Teamtrail report (`proof_report`, also `teamtrail proof <ticket>` in a terminal).
|
|
115
|
+
- **The human:** `ask_human`, `wait_for_answer`, `list_inbox`, `answer_question` (a chat answer guides the agent; only answers given in the Lookout or Slack back a decision that needs you), and decision memory (`find_precedent`).
|
|
116
|
+
- **Knowledge, assumptions and reroutes:** `propose_knowledge`, `search_knowledge`, `flag_knowledge`, `list_assumptions`, `challenge_assumption`, `propose_reroute`, `reroute_status`.
|
|
117
|
+
- **Guides and other projects:** `list_guides`, `projects_status`.
|
|
118
|
+
|
|
119
|
+
Every tool, its inputs and what remote agents can't call: [MCP tools reference](https://teamtrail.app/docs/mcp-tools/).
|
|
125
120
|
|
|
126
121
|
Sessions, questions and usage reach the Lookout through `.teamtrail/.agents/`, so the agent and the Lookout can start in any order.
|
|
127
122
|
|