feat(pricing): litellm sync generator + table

Add tools/pricing-sync: a standalone, compiled Go tool that fetches
LiteLLM's model_prices_and_context_window.json at build time and
regenerates pricing_data_gen.go, a plain map[string]builtinModelMeta
literal keyed by bare model id (context window, input/output cost in
micro-USD per million tokens).

Pruning rule (documented on the tool's own package doc comment): keep
only entries whose litellm_provider matches this gateway's own provider
types (openai, anthropic, deepseek, xai, minimax, cerebras, dashscope
for qwen/alibaba, and moonshot for Kimi models) and whose mode is chat
or embedding, dropping everything else — a 3111-entry table is a real
startup cost under Yaegi interpretation, so the generated table stays at
236 entries. Bare-id collisions across LiteLLM keys resolve
deterministically: a bare key beats a provider-prefixed one, then
provider priority, then lexicographic order.

Naming bridges: a small, data-driven table (namingBridges) duplicates an
entry under a second bare id when a provider's own live API disagrees
with LiteLLM's naming for the identical model — seeded with MiniMax's
lightning/highspeed dual naming, verified against a live deployment.

Coverage-audit follow-up (verified against a live fetch of the same
source, 2026-08): moonshot's own "litellm_provider" tag carries 23
real Kimi entries (kimi-k2.5, kimi-k3, ...), added to the allowlist as a
first-class provider rather than a per-id bridge, since the table is
already keyed by bare id regardless of provider. Two claims from a
coverage-audit request could NOT be verified against this same fetched
file and were deliberately NOT implemented: no key anywhere in the
3111-entry source ends in ":free" (an openrouter free-tier naming
convention the request assumed exists in this file), and no
"qwen/"-prefixed key exists at all — see the report for the full
grounding note. Also confirmed already-correct by design, no change
needed: audio/responses-mode OpenAI entries ("codex-mini-latest" and
friends) are excluded by the existing mode allowlist, not by any
provider special-case; image/video media models are excluded the same
way.

builtinModelMeta itself lives in its own file (builtin_model_meta.go),
separate from modelmeta.go's resolution logic, so this commit's table
and generator compile standalone.

make pricing-sync regenerates the table; add its gitignore entry for the
tool's own compiled binary.

Makefile

@@ -3,7 +3,7 @@
 # two of them concurrently would corrupt each other's containers.
 .NOTPARALLEL:
 
-.PHONY: test lint yaegi-check admin-ui integration integration-keep integration-up integration-wait integration-down
+.PHONY: test lint yaegi-check admin-ui pricing-sync integration integration-keep integration-up integration-wait integration-down
 
 test:
 	go test ./... -count=1
@@ -32,6 +32,18 @@ admin-ui:
 yaegi-check:
 	cd tools/yaegi-check && GOWORK=off go run . $(CURDIR)
 
+# pricing-sync regenerates the repo-root pricing_data_gen.go: the
+# built-in, LiteLLM-synced per-model context/cost table feature v0.23's
+# metadata resolution falls back to (modelmeta.go's resolveModelMeta).
+# Fetches LiteLLM's model_prices_and_context_window.json at BUILD TIME
+# only — see tools/pricing-sync/main.go's own doc comment for the
+# pruning rule and naming-bridge mechanism. Not run by CI (network
+# fetch, and the generated table is committed); an operator re-runs this
+# by hand when LiteLLM's own pricing drifts.
+pricing-sync:
+	cd tools/pricing-sync && GOWORK=off go run . $(CURDIR)
+	gofmt -w pricing_data_gen.go
+
 INTEGRATION_COMPOSE := integration/docker-compose.yml
 INTEGRATION_HEALTH_URL := http://localhost:19081/v1/models
 INTEGRATION_ALICE_KEY := sk-int-alice