# Janus-35B convenience Makefile.
#
# All work is delegated to scripts/* — this file just gives common
# operations short, discoverable names.
#
# Variables you can override on the command line:
#   QUANT     GGUF quant suffix       (default: Q4_K_M)
#   TAG       Ollama model tag        (default: janus)
#   GGUF_PATH path to existing GGUF   (skip the download)
#   GGUF      GGUF for live-check     (default: GGUF_PATH, else the bundled file)
#   MODEL     model tag for smoke     (default: $(TAG))
#
# Examples:
#   make build                          # Q4_K_M from the Heretic GGUF repo (the MTP strip no-ops on these quants)
#   make build QUANT=Q5_K_M             # higher-quality quant
#   make build GGUF_PATH=~/models/Qwen3.6-35B-A3B-uncensored-heretic-Q4_K_M.gguf
#   make load-bundle                    # this repo's bundled GGUF -> local Ollama tag (smudge LFS if needed)
#   make smoke
#   make check
#   make clean

QUANT ?= Q4_K_M
TAG   ?= janus
MODEL ?= $(TAG)
CTX   ?= 4096

.DEFAULT_GOAL := help

PRECISION ?= BF16

.PHONY: help build load-bundle cap-ctx smoke smoke-tools bench check hooks mmproj verify-arch clean live-check check-tag

help:  ## Show this help.
	@awk 'BEGIN {FS = ":.*##"; printf "Targets:\n"} /^[a-zA-Z_-]+:.*?##/ { printf "  \033[36m%-12s\033[0m %s\n", $$1, $$2 }' $(MAKEFILE_LIST)
	@echo
	@echo "Current settings:"
	@echo "  QUANT=$(QUANT) TAG=$(TAG) PRECISION=$(PRECISION)"
ifdef GGUF_PATH
	@echo "  GGUF_PATH=$(GGUF_PATH)"
endif

build:  ## Download a Heretic GGUF, run the MTP strip (a no-op on these quants), and run 'ollama create'.
	GGUF_PATH=$(GGUF_PATH) TAG=$(TAG) ./scripts/build.sh $(QUANT)

load-bundle:  ## Load THIS repo's bundled GGUF into a local Ollama tag (smudge LFS + ollama create).
	TAG=$(TAG) ./scripts/load_bundle.sh

cap-ctx:  ## Bake a small-num_ctx local tag for OpenAI /v1 clients (CTX default 4096).
	CTX=$(CTX) TAG=$(TAG) ./scripts/cap_ctx.sh

smoke:  ## Verify the model is reachable and round-trips.
	MODEL=$(MODEL) ./scripts/smoke_test.sh

smoke-tools:  ## smoke + end-to-end tool-call round-trip (~10s extra).
	MODEL=$(MODEL) TOOLS_TEST=1 ./scripts/smoke_test.sh

bench:  ## Measure tok/s using Ollama's eval timing (3 prompts).
	MODEL=$(MODEL) ./scripts/bench.sh

mmproj:  ## Fetch the vision projector for llama.cpp (Ollama vision is broken upstream).
	./scripts/fetch_vision.sh $(PRECISION)

check:  ## Lint, bridge-file sync, the Go-template guard, and that the Modelfile's FROM is the GGUF this repo ships.
	./scripts/check.sh

live-check:  ## Live end-to-end checks in an isolated Ollama (GGUF=path or GGUF_PATH=path; tens of minutes on CPU).
	./scripts/live_check.sh "$(or $(GGUF),$(GGUF_PATH))"

check-tag:  ## Check an installed Ollama tag still carries this repo's template (TAG=name).
	./scripts/check_tag_sync.sh $(TAG)

verify-arch:  ## Cross-check README "Architecture" bullets against GGUF metadata.
	./scripts/verify_arch.py

hooks:  ## Install scripts/check.sh as the git pre-commit hook.
	./scripts/install-hooks.sh

clean:  ## Remove local GGUF copies and ephemeral caches in this repo.
	@echo "[*] removing local GGUFs and ephemeral caches in $$PWD"
	@rm -f ./Qwen3.6-35B-A3B-uncensored-*.gguf ./mmproj-*.gguf ./*.stripped.gguf
	@rm -rf ./.cache __pycache__ examples/__pycache__
	@echo "[+] clean"