#!/usr/bin/env bash
# ─────────────────────────────────────────────────────────────────────────────
# Reproducible build of the CUSTOM llama.cpp that backs the char-rp-reasoning
# seat (Deckard-PKD, ana-ml2:8018).
#
#   = llama.cpp latest master (pinned 6eddde0, 2026-07-13, ~b9990 era)
#     + UNMERGED PR #25544 (aldehir:reasoning-budget-multi-seq)
#
# WHY THIS EXISTS (do not "clean this up" without reading README.md):
#   Stock llama.cpp b8840 (and every released build to date) has a reasoning-
#   budget sampler that knows only ONE end-tag (</think>). Qwen3.5's tool-call
#   path terminates reasoning with <tool_call>, which the single-tag sampler
#   cannot match, so --reasoning-budget forcing NEVER fires on the tool-retry
#   path → the model loops in reasoning to max_tokens (32768) ≈ 22 min. That is
#   Worldtree #355's residual. PR #25544 teaches the budget MULTIPLE terminating
#   sequences (</think> OR <tool_call>) — the exact fix — but it is UNMERGED
#   upstream, so we build it ourselves.
#
# ⚠️  REMOVE-WHEN-MERGED: once #25544 merges upstream and lands in a release,
#     retire this custom build and switch the seat back to a stock image
#     (see README.md → "Retiring this custom build").
#
# Run on ana-ml2 (Blackwell RTX PRO 6000, sm_120; docker + buildx; ~120G free).
# Produces: llamacpp-charrp:6eddde0-pr25544  (+ :custom-latest)
# Runtime ~20-40 min (CUDA compile for sm_120).
# ─────────────────────────────────────────────────────────────────────────────
set -euo pipefail

MASTER_SHA="${MASTER_SHA:-6eddde0}"          # llama.cpp master pin
PR="${PR:-25544}"                             # aldehir:reasoning-budget-multi-seq
BUILDDIR="${BUILDDIR:-/home/lkraven/llamacpp-build}"
IMAGE="${IMAGE:-llamacpp-charrp}"
CUDA_VERSION="${CUDA_VERSION:-12.8.1}"        # 12.8+ required for Blackwell sm_120
CUDA_ARCH="${CUDA_ARCH:-120}"                 # RTX PRO 6000 = compute 12.0

echo "== fetch master@${MASTER_SHA} + PR #${PR} =="
rm -rf "$BUILDDIR"
git clone https://github.com/ggml-org/llama.cpp "$BUILDDIR"
cd "$BUILDDIR"
git checkout "$MASTER_SHA"
git fetch origin "pull/${PR}/head:pr${PR}"
git config user.email infra-ops@phasefinal.com
git config user.name infra-ops

echo "== merge PR #${PR} (expect 1 conflict in server-common.cpp) =="
git merge --no-commit --no-ff "pr${PR}" || true
# Resolve the single conflict: keep the PR's PLURAL reasoning_budget_end_tags
# (the whole point of the fix) AND master's per-request body-read of
# reasoning_budget_message (a newer master feature the PR's base predates).
python3 - <<'PY'
p = "tools/server/server-common.cpp"
s = open(p).read()
i = s.index("<<<<<<< HEAD")
j = s.index(">>>>>>> pr25544") + len(">>>>>>> pr25544")
new = ('            llama_params["reasoning_budget_end_tags"] = chat_params.thinking_end_tags;\n'
       '            llama_params["reasoning_budget_message"] = json_value(body, "reasoning_budget_message", opt.reasoning_budget_message);')
open(p, "w").write(s[:i] + new + s[j:])
assert open(p).read().count("<<<<<<<") == 0, "unresolved conflict markers remain"
print("resolved server-common.cpp")
PY
git add -A
git commit -m "merge PR #${PR} (reasoning-budget multi-seq) onto master ${MASTER_SHA} — char-rp-reasoning seat custom build"

echo "== docker build (server target, CUDA ${CUDA_VERSION}, sm_${CUDA_ARCH}) =="
docker build -f .devops/cuda.Dockerfile --target server \
  --build-arg CUDA_VERSION="${CUDA_VERSION}" \
  --build-arg CUDA_DOCKER_ARCH="${CUDA_ARCH}" \
  --build-arg APP_VERSION="${MASTER_SHA}-pr${PR}" \
  --build-arg APP_REVISION="$(git rev-parse HEAD)" \
  -t "${IMAGE}:${MASTER_SHA}-pr${PR}" \
  -t "${IMAGE}:custom-latest" \
  .

echo "== built ${IMAGE}:${MASTER_SHA}-pr${PR} (entrypoint /app/llama-server, drop-in for the seat) =="