You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Stale-session guard for coordination, README entry for the field-bug batch
ClaudeR 0.12.1 / clauder-mcp 0.14.1. Field report: an agent still
pointed at a dead R session got success from send_message while the
event landed in a coordination log no live agent reads. Root cause:
get_r_addin_url keeps the stale session name when zero sessions are
alive, so _coord_dir resolved to the dead session directory.
New _coord_target resolver runs before every coordination call
(send_message, check_messages, wait_for_message, coordination_roster).
With no live R session it fails loudly and writes nothing. When the
connection re-binds to a different live session it prepends a NOTE
saying earlier sends may sit in the old log unseen. wait_for_message
also re-checks liveness every poll so a mid-wait death aborts instead
of hanging silently.
Protocol gains a delivery-guarantees paragraph. README gains the
combined Recent Updates entry for the 0.12.x field-bug batch. Three
new pytest cases cover dead session, re-bind note, and quiet stable
binding (33 total).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: README.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -50,6 +50,8 @@ claudeAddin()
50
50
<details>
51
51
<summary><b>Recent Updates</b> (click to expand)</summary>
52
52
53
+
- **Shared-connection identity, coordination visibility, and a stale-session guard (R 0.12.1 / clauder-mcp 0.14.1).** Three fixes from a live three-persona field session. (1) Personas sharing one MCP connection were renaming each other, because `set_agent_name` changes the identity of the whole connection. New `as_agent` parameter on `send_message`, `check_messages`, and `wait_for_message` acts as a named persona for one call, with a separate read cursor per name, and the agent intro now states where the current identity came from. (2) Coordination messages bypass R by design, so the console and the Agents panel showed nothing while agents talked. The addin now echoes each new coordination event to the console, appends it to the session log, and shows a live coordination roster with last-seen ages. (3) A bridge still pointed at a dead R session used to report "success" while writing to a coordination log no live agent reads. Coordination calls now fail loudly when no live session exists, and announce it when the connection re-binds to a different live session. Also from pilot 2: `check_cross_references` understands S-prefixed supplement numbering, and the audit protocol documents `unname()` for htest fields and author-plus-year citation matching.
54
+
53
55
-**Agent identity and cross-restart history (R 0.11.0 / clauder-mcp 0.13.0).** Built from field reports of a multi-day, three-agent session. New `set_agent_name` tool: an agent sets its working name (for example "Claude-Stasis") once, and execution history, message attribution, presence, and its read cursor all carry that name. This fixes the case where several agents or personas share one MCP connection and collapse into a single random id. `get_session_history` gains `include_past`: it parses prior session log files on disk, so the audit of who ran what now survives R restarts. The coordination protocol now makes identity the first step of check-in.
54
56
55
57
-**Researcher workflow release (R 0.10.0 / clauder-mcp 0.12.0).** Three workflows that paid tools charge for, built on machinery ClaudeR already had. (1) Systematic review screening: two independent AI screeners from different model families judge every abstract against your criteria, and the new `screening_report` tool computes agreement, Cohen's kappa, PRISMA flow counts, and the conflict set, so the human reads only the disagreements. (2) Grant Panel Mode: `grant_panel_prompt(rubric = "nih")` convenes a mock study section, one reviewer per criterion, anchored weaknesses, and a ranked list of revisions that would move the score. (3) Response to Reviewers: `reviewer_response_prompt()` parses a decision letter into a point-by-point registry, reruns analyses so answers carry real computed numbers, gates until every point is answered, and exports the response letter with `export_response_letter()` plus Word comments in the manuscript.
0 commit comments