diff --git a/k8s/apps/agent-pod/configmap.yaml b/k8s/apps/agent-pod/configmap.yaml
index 174a1ae..4437f48 100644
--- a/k8s/apps/agent-pod/configmap.yaml
+++ b/k8s/apps/agent-pod/configmap.yaml
@@ -8,8 +8,8 @@ data:
       "theme": "light",
       "compaction": {
         "enabled": true,
-        "reserveTokens": 8192,
-        "keepRecentTokens": 12000
+        "reserveTokens": 16000,
+        "keepRecentTokens": 6000
       }
     }
 kind: ConfigMap
diff --git a/k8s/apps/agent-pod/coordinator-configmap.yaml b/k8s/apps/agent-pod/coordinator-configmap.yaml
index 9e550a6..3f873ce 100644
--- a/k8s/apps/agent-pod/coordinator-configmap.yaml
+++ b/k8s/apps/agent-pod/coordinator-configmap.yaml
@@ -39,7 +39,6 @@ data:
     // with fs.watch instead of polling.
     const fs = require("node:fs");
     const path = require("node:path");
-    const crypto = require("node:crypto");
     const { spawn } = require("node:child_process");
     
     const WORK_DIR = process.env.HUB_WORK_DIR || path.join(require("node:os").tmpdir(), "agent-harness-work");
@@ -523,6 +522,11 @@ data:
     // running concurrently (see runCoordinator).
     async function runRepoPipeline({ repoId, repo, baseBranch, tasks, branchName }, pipelineSession) {
       const cwd = path.join(WORK_DIR, repoId);
+      // repoId is a slug derived from the repo URL now (see slugFor), not a
+      // fresh UUID -- reusable across separate `runCoordinator` invocations
+      // against the same repo, so a stale clone from a prior run has to be
+      // wiped before this one starts, not merged into.
+      fs.rmSync(cwd, { recursive: true, force: true });
       fs.mkdirSync(cwd, { recursive: true });
       const pool = {};
     
@@ -678,20 +682,40 @@ data:
     // How many repos can be mid-flight at once. Each repo gets its own clone
     // and its own 4-agent pool (planner/investigator/implementer/judge), so
     // this is now the real concurrency knob -- tasks within one repo are
-    // already serialized against that repo's pool (see runPhase). Backends
-    // that queue rather than reject concurrent requests to one loaded model
-    // (e.g. Ollama) still process this many repos' worth of stages one at a
-    // time internally even if REPO_CONCURRENCY says otherwise; bump it once
-    // there's more than one model instance to actually parallelize against.
+    // already serialized against that repo's pool (see runPhase). The backend
+    // (homelab-ornith) actually runs 2 GPU replicas behind one Kubernetes
+    // Service, each with its own copy of the model loaded (see homelab's
+    // k8s/apps/llm-serving/ornith.yaml) -- so up to 2 concurrent LLM calls get
+    // real independent instances; a 3rd+ concurrent call queues inside
+    // whichever replica the Service's own load-balancing lands it on (each
+    // replica runs OLLAMA_NUM_PARALLEL=1). REPO_CONCURRENCY above 2 is still
+    // useful (more repos in flight overlaps git/file work, not just LLM calls)
+    // but past 2 simultaneous LLM calls, extra concurrency mostly means queueing
+    // rather than added throughput -- bump the backend's replica count to
+    // change that, not this constant.
     const REPO_CONCURRENCY = Number(process.env.REPO_CONCURRENCY) || 3;
     
+    // repoId is the repo's own name, not a random id -- it's what every role
+    // session's --name is built from (see runOnPool: `${repoId}-${role}`), so
+    // agent-manager's own session list groups naturally by repo ("portfolio-
+    // planner", "portfolio-judge", "poiman-planner", ...) instead of by opaque
+    // UUID. Takes the last path segment of the URL, strips a trailing `.git`,
+    // and sanitizes anything that isn't safe in a tmux session name / directory
+    // name / git branch name. Two different repos that happen to share a
+    // basename (e.g. two orgs' "portfolio") would collide -- not handled, since
+    // nothing about this harness's usage has needed more than one org per run.
+    function slugFor(repoUrl) {
+      const last = repoUrl.replace(/\/+$/, "").split("/").pop() || repoUrl;
+      return last.replace(/\.git$/, "").replace(/[^a-zA-Z0-9._-]/g, "-");
+    }
+    
     // Top-level entry point: runs every repo in `repos` to completion, up to
     // REPO_CONCURRENCY at a time. Returns a map of repoId -> final
     // pipelineSession, one per repo, independent of how the others fared.
     async function runCoordinator({ repos, base, tasks, branchName }) {
       const sessions = {};
       await runConcurrent(repos, REPO_CONCURRENCY, async (repoUrl) => {
-        const repoId = crypto.randomUUID();
+        const repoId = slugFor(repoUrl);
         const pipelineSession = {
           id: repoId,
           repo: repoUrl,
diff --git a/k8s/apps/agent-pod/deployment.yaml b/k8s/apps/agent-pod/deployment.yaml
index 13a65e2..8a944e4 100644
--- a/k8s/apps/agent-pod/deployment.yaml
+++ b/k8s/apps/agent-pod/deployment.yaml
@@ -77,6 +77,16 @@ spec:
               value: /usr/local/bin/agent-manager
             - name: HUB_WORK_DIR
               value: /root/agent-harness-work
+            # planner/investigator/implementer stay on the default
+            # (homelab-ornith/ornith:35b, pi's settings.json default). Judge
+            # moves to the separate homelab-reasoning backend (DeepSeek-R1,
+            # its own 2 GPU replicas) so judge calls stop contending with the
+            # other 3 roles for the 2 ornith pods -- an entire role's worth
+            # of traffic moves onto otherwise-idle capacity instead.
+            - name: JUDGE_PROVIDER
+              value: homelab-reasoning
+            - name: JUDGE_MODEL
+              value: reasoning
           ports:
             - containerPort: 9090
           resources: