Pass 5: add supplement/appendix integration check (8th)

ClaudeR 0.12.4. Adds an eighth content-reasoning check to Pass 5:
supplement and appendix integration (is every supplement cited from
the body, and does any body claim depend on an uncited supplement).
This is general editorial-review practice, not tied to any fixture.

Validated on the synthetic benchmark (Opus, blind, three runs): 22, 22,
20 (mean 21.3 of 24), zero false positives, recovering the uncited-
supplement defect every run. Up from the 7-check Pass 5 mean of 20.7
and well above the native-tools baseline of 17.6 and the old tool-led
protocol of 16.8.

Two defects (a post-treatment moderator and an exclusion criterion
that the data cannot support) remain unfound by design: general checks
for them were considered but rejected as too close to the answer key.

R CMD check: Status OK. checks.R: all pass. Bridge unchanged.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Author: IMNMV

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: ClaudeR
 Title: R Integration for Claude AI
-Version: 0.12.3
+Version: 0.12.4
 Authors@R: person("Nykko", "Vitali", email = "nykvt@icloud.com", role = c("aut", "cre"))
 Description: Connects RStudio with Claude AI to enable interactive coding sessions.
 License: MIT + file LICENSE

README.md

@@ -50,7 +50,7 @@ claudeAddin()
 <details>
 <summary><b>Recent Updates</b> (click to expand)</summary>
 
-- **Reviewer Zero now reasons, not just reconciles (R 0.12.3).** Added a mandatory Pass 5 (content reasoning) to the base auditing protocol. The deterministic tools (reconcile_values, verify_references, check_cross_references, probe_scripts) find numeric, reference, cross-reference, and code defects, but they do not reason about meaning, and a manuscript can clear every one of them and still be wrong. Pass 5 is a gated, equal-weight pass with seven checks the tools cannot do: instrument and source attribution, whether each reported test is computable from the data that exists, whether each cited figure or table actually contains the claimed evidence, magnitude wording, convergence across studies, causal and generality framing, and data existence for descriptive claims. In a controlled benchmark on a synthetic manuscript with a known defect set, this raised detection from below a native-tools baseline to clearly above it, recovering exactly the reasoning defects the old tool-led protocol was missing.
+- **Reviewer Zero now reasons, not just reconciles (R 0.12.4).** Added a mandatory Pass 5 (content reasoning) to the base auditing protocol. The deterministic tools (reconcile_values, verify_references, check_cross_references, probe_scripts) find numeric, reference, cross-reference, and code defects, but they do not reason about meaning, and a manuscript can clear every one of them and still be wrong. Pass 5 is a gated, equal-weight pass with eight checks the tools cannot do: instrument and source attribution, whether each reported test is computable from the data that exists, whether each cited figure or table actually contains the claimed evidence, magnitude wording, convergence across studies, causal and generality framing, data existence for descriptive claims, and supplement and appendix integration (every supplement cited, and no body claim resting on an uncited one). In a controlled benchmark on a synthetic manuscript with a known defect set, this raised detection from below a native-tools baseline (16.8 of 24) to clearly above it (21.3 of 24), recovering exactly the reasoning defects the old tool-led protocol was missing, with no rise in false positives.
 
 - **Shared-connection identity, coordination visibility, and a stale-session guard (R 0.12.2 / clauder-mcp 0.14.2).** 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. The bridge now enforces the pattern: a second `set_agent_name` with a different name is refused unless forced, every send confirmation echoes the name it was sent as, and the agent intro 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 in full (no truncation), 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.
 

inst/prompts/reviewer_zero.md

@@ -414,7 +414,7 @@ reasoning_registry <- data.frame(
   check = c("instrument_attribution", "test_computability",
             "figure_claim_match", "magnitude_wording",
             "convergence_consistency", "causal_generality_framing",
-            "data_existence"),
+            "data_existence", "supplement_integration"),
   status = "unrun",           # unrun -> clear | defect
   finding = "",               # verbatim claim + what is wrong
   stringsAsFactors = FALSE)
@@ -457,6 +457,11 @@ Pass 3 discrepancy.
    reliability claim (demographics, Cronbach's alpha, "measures collected"),
    does the supporting data exist anywhere in the project? A claim resting on
    data absent from the corpus must be flagged as unverifiable.
+8. **Supplement and appendix integration.** Is every supplementary file, table,
+   or appendix cited somewhere in the manuscript body? Conversely, does any body
+   claim depend on evidence that appears only in an uncited supplement or
+   appendix? A load-bearing argument whose support lives in a supplement the
+   text never points to is a defect, not a formatting lapse.
 
 ### Reasoning-pass gate