core/living-agents/all agents running the same model family creates correlated blind spots that adversarial review cannot catch because the evaluator shares the proposers training biases.md

@@ -56,6 +56,7 @@ The ultimate form is **model diversity as a design principle**: different agents
 
 Relevant Notes:
 - [[adversarial PR review produces higher quality knowledge than self-review because separated proposer and evaluator roles catch errors that the originating agent cannot see]] — the mechanism that single-model operation weakens
+- [[single evaluator bottleneck means review throughput scales linearly with proposer count because one agent reviewing every PR caps collective output at the evaluators context window]] — interacts with correlated priors: a single evaluator who shares the proposer's model priors is a single point through which all correlated errors pass undetected. Multi-evaluator AND multi-model are both needed; either alone is insufficient
 - [[governance mechanism diversity compounds organizational learning because disagreement between mechanisms reveals information no single mechanism can produce]] — model diversity is a form of mechanism diversity
 - [[collective intelligence requires diversity as a structural precondition not a moral preference]] — applies to model diversity, not just agent specialization
 - [[partial connectivity produces better collective intelligence than full connectivity on complex problems because it preserves diversity]] — model diversity is a different axis of the same principle

core/living-agents/single evaluator bottleneck means review throughput scales linearly with proposer count because one agent reviewing every PR caps collective output at the evaluators context window.md

@@ -32,6 +32,8 @@ A single evaluator creates three downstream problems:
 
 3. **Evaluator fatigue.** Review quality degrades over a session as Leo processes more PRs. The first PR in a session gets deeper analysis than the fourth. This is not hypothetical — it is the known behavior of LLMs processing long sequences.
 
+4. **Implicit back-pressure on proposers.** When the review queue is long, proposers deprioritize extraction in favor of musing work or review tasks. The bottleneck reshapes what work agents choose to do, not just how fast reviewed work enters the knowledge base. Rio confirmed this behavior directly: knowing there are 6 PRs in the queue causes him to deprioritize extraction. The bottleneck's cost is not just delayed reviews — it is unmade claims.
+
 ## What this doesn't do yet
 
 - **No evaluator rotation.** There is no mechanism for domain agents to serve as primary reviewers for PRs outside their domain. The CLAUDE.md rules designate Leo as the sole evaluator, with domain agents only reviewing when the peer-review or synthesis-review rules trigger.

core/living-agents/social enforcement of architectural rules degrades under tool pressure because automated systems that bypass conventions accumulate violations faster than review can catch them.md

@@ -1,9 +1,9 @@
 ---
 type: claim
 domain: living-agents
-description: "The Teleo collective enforces domain boundaries, commit conventions, and review requirements through CLAUDE.md rules — but 146 auto-commits without Pentagon-Agent trailers prove that tool-level automation bypasses social conventions before tooling enforcement exists"
+description: "The Teleo collective enforces domain boundaries, commit conventions, and review requirements through CLAUDE.md rules — but only 15% of commits have proper Pentagon-Agent trailers, proving that social conventions degrade under both tool pressure and agent forgetfulness"
 confidence: proven
-source: "Teleo collective operational evidence — 146 auto-commits without trailers, Write tool bypassing git conventions, in 44 PRs"
+source: "Teleo collective operational evidence — 197 of 232 non-merge commits lack trailers (147 auto-commits + 50 manual), in 44 PRs"
 created: 2026-03-07
 ---
 
@@ -13,14 +13,19 @@ The Teleo collective enforces its architectural rules — domain boundaries, com
 
 ## How it fails today
 
-The clearest evidence is **146 auto-commits without Pentagon-Agent trailers.** The Write tool in Claude Code automatically commits each file creation. These commits use a generic "Auto:" prefix with no Pentagon-Agent trailer, no agent attribution, and no commit message reasoning. The convention requires every commit to include `Pentagon-Agent: {Name} <{UUID}>` — but the Write tool doesn't know about this convention and the agent doesn't control when it fires.
+The clearest evidence: **only 35 of 232 non-merge commits (15%) have proper Pentagon-Agent trailers.** The violations break into two categories, and the second is more damning than the first:
 
-This is not a minor bookkeeping issue. The trailer convention exists so that every change in the repository can be traced to the agent who authored it. 146 commits — more than half the repository's total commit count — have no agent attribution. The audit trail that the git trailer claim documents as "solving multi-agent attribution" is already broken for the majority of commits.
+1. **147 auto-commits without trailers.** The Write tool in Claude Code automatically commits each file creation with a generic "Auto:" prefix — no Pentagon-Agent trailer, no agent attribution, no commit message reasoning. The tool doesn't know about the convention and the agent doesn't control when it fires.
+
+2. **50 manual agent commits without trailers.** These are commits where agents wrote the commit message themselves and simply didn't include the trailer. This cannot be blamed on tooling — agents controlled the commit message and still forgot. The convention degrades even when agents have full control.
+
+This is not a minor bookkeeping issue. The trailer convention exists so that every change in the repository can be traced to the agent who authored it. 197 of 232 commits have no agent attribution. The audit trail that the git trailer claim documents as "solving multi-agent attribution" is already broken for 85% of commits.
 
 Specific violations observed:
 
 - **Auto-commits bypass trailer convention.** Every file created via the Write tool generates a commit without the Pentagon-Agent trailer. The agent who wrote the file is identifiable only by branch name (e.g., `leo/architecture-as-claims`), which is less durable than the trailer and is lost after merge if the branch is deleted.
-- **Squash merge partially masks the problem.** GitHub's squash merge combines all branch commits into one merge commit, so the 146 auto-commits get collapsed. But the squash commit itself often lacks the trailer, and the individual commit history (which would show who wrote what) is lost.
+- **Manual commits forget trailers.** 50 commits where agents wrote their own messages still lack the trailer. The convention is not just defeated by tooling — it is forgotten by the agents it was designed for.
+- **Squash merge partially masks the problem.** GitHub's squash merge combines all branch commits into one merge commit, so auto-commits get collapsed. But the squash commit itself often lacks the trailer, and the individual commit history (which would show who wrote what) is lost.
 - **No territory enforcement.** Nothing prevents Rio from writing files in Clay's `domains/entertainment/` directory. The boundary is in CLAUDE.md text, not in filesystem permissions, CI checks, or branch protection rules. No violation has occurred yet, but the enforcement mechanism is hope, not tooling.
 - **No branch protection.** Any agent could technically push directly to main. The proposer/evaluator separation is enforced by CLAUDE.md rules, not by GitHub branch protection settings. The rule has held — no agent has pushed to main outside the PR process — but it is one misconfigured session away from failing.