diff --git a/HANDOVER-AGENTS-2026-05-17.md b/Handover 17.05.2026 - Agents Pointer.md similarity index 87% rename from HANDOVER-AGENTS-2026-05-17.md rename to Handover 17.05.2026 - Agents Pointer.md index ec1efb4..519f495 100644 --- a/HANDOVER-AGENTS-2026-05-17.md +++ b/Handover 17.05.2026 - Agents Pointer.md @@ -4,13 +4,13 @@ This file is a pointer. The agent-aware master handover lives in the magatama repo: -> **`gitea.context-x.org/rene/magatama` → `HANDOVER-AGENTS-2026-05-17.md`** +> **`gitea.context-x.org/rene/magatama` → `Handover 17.05.2026 - Agents.md`** Read it first. It covers ALL projects touched today (magatama + llm-gateway + codex-bridge + LLM Gym), with explicit Codex-vs-Claude-Code conventions, the path map (Mac vs Erik), the emergency disable one-liner, and the verification cheat-sheet. The operator-facing (non-agent) handover specifically for today's work in this repo lives at: -> **`llm-gateway/HANDOVER-2026-05-17-pointer.md`** — Layer-3 activation, smoke test, rollback. +> **`llm-gateway/Handover 17.05.2026 - Gateway.md`** — Layer-3 activation, smoke test, rollback. ## TL;DR for this repo (so you don't have to switch context immediately) @@ -57,8 +57,8 @@ tr "\0" "\n" < /proc/$PID/environ | grep -E "INJECTION_DEFENSE_MODE|LLM_JUDGE_MO ## See also (in the magatama repo, already pushed) -- `HANDOVER-2026-05-17.md` — master operator handover (519 lines, all phases, rollback matrix) -- `HANDOVER-AGENTS-2026-05-17.md` — agent-aware wrapper (Codex vs Claude Code, path maps, operating constraints) +- `Handover 17.05.2026 - Master.md` — master operator handover (519 lines, all phases, rollback matrix) +- `Handover 17.05.2026 - Agents.md` — agent-aware wrapper (Codex vs Claude Code, path maps, operating constraints) - `docs/handover-2026-05-17/wiki/15-llm-injection-defense-stack.md` — Layer-1/2/3 architecture + cache-bypass post-mortem - `docs/handover-2026-05-17/wiki/18-magatama-judge-model.md` — judge bench + LoRA audit (12/12 vs 9/12) - `docs/handover-2026-05-17/wiki/22-adr-grafana-cadillac.md` ADR-03 — qwen2.5:14b vs magatamallm decision rationale diff --git a/HANDOVER-2026-05-17-pointer.md b/Handover 17.05.2026 - Gateway.md similarity index 93% rename from HANDOVER-2026-05-17-pointer.md rename to Handover 17.05.2026 - Gateway.md index 72d8788..cffe258 100644 --- a/HANDOVER-2026-05-17-pointer.md +++ b/Handover 17.05.2026 - Gateway.md @@ -2,7 +2,7 @@ This is just a pointer. Master handover lives in the magatama repo: -> **`gitea.context-x.org/rene/magatama` → `HANDOVER-2026-05-17.md`** +> **`gitea.context-x.org/rene/magatama` → `Handover 17.05.2026 - Master.md`** ## What changed in llm-gateway today @@ -57,7 +57,7 @@ tr "\0" "\n" < /proc/$PID/environ | grep -E "INJECTION_DEFENSE_MODE|LLM_JUDGE_MO ## See also -- magatama repo `HANDOVER-2026-05-17.md` — master handover for today's work +- magatama repo `Handover 17.05.2026 - Master.md` — master handover for today's work - magatama repo `docs/handover-2026-05-17/wiki/15-llm-injection-defense-stack.md` — full Layer-1/2/3 architecture + cache-bypass post-mortem - magatama repo `docs/handover-2026-05-17/wiki/18-magatama-judge-model.md` — judge bench + LoRA audit (12/12 vs 9/12) - magatama repo `docs/handover-2026-05-17/wiki/22-adr-grafana-cadillac.md` ADR-03 — qwen2.5:14b vs magatamallm decision rationale