diff --git a/agent-builder/.claude/context.md b/agent-builder/.claude/context.md
index ba70bd0..5aa7ce2 100644
--- a/agent-builder/.claude/context.md
+++ b/agent-builder/.claude/context.md
@@ -461,14 +461,42 @@ Build, test, and push both builder agents to production. Work as long as it take
 - Cookie jar required for Jenkins crumb across urllib requests
 - Claude Max upgrade needed — daily token limits hit during background agent sessions
 
-**Next session first tasks (in order):**
-1. id=163 — Redeploy secrets-proxy to activate Jenkins caller key (BLOCKER for all Jenkins Promote-to-Production)
-2. id=164 — Fix sudo-bridge sandbox compose IP on server-01
-3. Re-run jellyfin Jenkins job (verify full pipeline end-to-end after id=163)
-4. id=161 — Hermes→Jenkins trigger (needs id=163 first)
-5. Hermes config: add hermes-cli to telegram toolset
-6. id=154 Domain playbooks → Gitea
-7. Build id=24 Agent Builder Agent + id=67 N8N Builder Agent
+### 2026-06-26 Sprint Day 10 session 4 facts
+- id=161 grill-me COMPLETE — full v1 design locked (see below)
+- id=112 model decision: claude-sonnet-4-6 + --thinking medium for all claude -p automation scripts
+- id=161 v2 logged as personal_projects id=165 (3-tier AI fix pipeline, next sprint)
+- Phase plan locked: 11 tasks across 3 phases of background agents
+
+#### id=161 v1 design (locked)
+- Trigger: auto (Hermes health failure) + manual (Telegram /redeploy <service>)
+- Recovery: always full Jenkins redeploy — no restart shortcut
+- Auto-fire scope: non-critical auto; critical services (secrets-proxy, authelia, sudo-bridge, bitwarden-bridge) → stop + NTFY immediately on first failure
+- Max retries: 3 Jenkins attempts → if still unhealthy → stop container + NTFY user
+- Hermes auth: dedicated `hermes` caller key in proxy/callers (new entry needed)
+- Telegram format: structured /redeploy <service> prefix
+- Diagnosis: 8B model classifies failure type (constrained JSON list) before each attempt
+- Logging: hermes_redeploy_log table (container_name, failure_type, hermes_diagnosis, attempt_number, triggered_by, outcome, jenkins_build_url, timestamp)
+- v2 (id=165): adds Tier 1 in-place fixes + Claude -p review gate + 3-tier escalation
+
+#### Phase plan for next session
+**Phase 1** (5 parallel agents):
+1. id=163 — Redeploy secrets-proxy (BLOCKER)
+2. id=164 — Fix sudo-bridge sandbox compose IP
+3. Hermes config — add hermes-cli to telegram platform_toolsets
+4. container-health-sweep SKILL.md
+5. semantic-recall SKILL.md
+
+[inline: jellyfin Jenkins verify after Phase 1]
+
+**Phase 2** (5 parallel agents):
+6. id=161 — Hermes→Jenkins trigger v1
+7. id=154 — Domain playbooks → Gitea
+8. Content repurposing proposal (research + write + PDF)
+9. id=135 — Update N8N playbook sandbox section
+10. id=112 — Add --model claude-sonnet-4-6 --thinking medium to all claude -p automation scripts
+
+**Phase 3** (1 agent):
+11. id=155 — required_playbooks precision pass (needs id=154 from Phase 2)
 
 ## Update instructions
 Update at the end of every agent-builder session. Keep agent status, key decisions, and prereq checklist current.