gateway: build-time patch keeping image-gen pricing on the shared cost-map key (upstream #10023/#12471) so image spend is tracked

Dockerfile

@@ -29,6 +29,12 @@ COPY config.yaml /app/data/config.yaml
 COPY patch_budget_message.py /app/code/patch_budget_message.py
 RUN python3 /app/code/patch_budget_message.py
 
+# Image-cost tracking: keep image-generation pricing on the shared cost-map
+# key so successful image generations appear in SpendLogs (upstream bug
+# BerriAI/litellm#10023/#12471 — closed not-planned). Non-fatal at build.
+COPY patch_image_cost.py /app/code/patch_image_cost.py
+RUN python3 /app/code/patch_image_cost.py
+
 # Audio keep-alive: scheduled pings keep the Tinfoil TEE audio enclave
 # warm so voice mode skips the ~24s cold-start (see audio_keepalive.py header).
 COPY audio_keepalive.py /app/code/audio_keepalive.py

patch_image_cost.py

@@ -0,0 +1,75 @@
+"""Keep image-generation pricing on the shared cost-map key.
+
+Run at BUILD time (the runtime rootfs is read-only under Cloudron). Non-fatal:
+if the target file or anchor strings are missing (e.g. after an upstream
+version bump), it prints a warning and exits 0 so the build — and the
+gateway — still succeeds.
+
+Why: LiteLLM's image cost calculator (default_image_cost_calculator) looks
+pricing up ONLY in the shared ``{provider}/{model}`` key of
+``litellm.model_cost`` — it never consults the per-deployment entry. But the
+router deliberately strips per-deployment pricing from that shared key
+("so one deployment's overrides don't pollute sibling deployments"), which
+makes every successful image generation on a custom backend invisible:
+the cost lookup raises, the spend-log write is skipped, and SpendLogs /
+the dashboards show nothing. Upstream: BerriAI/litellm#10023 and #12471,
+closed not-planned.
+
+Patch: for image_generation deployments, re-add the custom pricing fields to
+the shared-key entry. Safe for us: the co-op gateway has a single deployment
+per image backend, so there are no sibling deployments to pollute.
+"""
+import sys
+import glob
+
+ANCHOR = "        # Always register the (possibly mode-preserved) shared backend info."
+INSERT = '''        # CO-OP PATCH (2026-10-19): image-generation deployments must keep
+        # their pricing on the shared cost-map key — the image cost calculator
+        # (default_image_cost_calculator) reads ONLY this key and never the
+        # per-deployment model_id entry, so stripping pricing here makes every
+        # successful image generation invisible in SpendLogs (upstream:
+        # BerriAI/litellm#10023, #12471, closed not-planned). Safe: the co-op
+        # gateway has a single deployment per image backend — no siblings.
+        if deployment_mode == "image_generation":
+            for _pk, _pv in model_info.items():
+                if _pk in CustomPricingLiteLLMParams.model_fields and _pv is not None:
+                    shared_model_info[_pk] = _pv
+
+'''
+
+candidates = glob.glob(
+    "/app/.venv/lib/python*/site-packages/litellm/router.py"
+)
+
+patched_any = False
+for p in candidates:
+    with open(p) as f:
+        src = f.read()
+
+    if "CO-OP PATCH (2026-10-19)" in src:
+        print(f"INFO: image-cost patch already present in {p}")
+        continue
+
+    if ANCHOR not in src:
+        print(f"WARN: anchor not found in {p}; patch not applied (non-fatal)",
+              file=sys.stderr)
+        continue
+
+    new = src.replace(ANCHOR, INSERT + ANCHOR, 1)
+
+    if new == src:
+        print(f"WARN: insertion failed in {p} (non-fatal)", file=sys.stderr)
+        continue
+
+    with open(p, "w") as f:
+        f.write(new)
+    print(f"INFO: patched image-cost registration in {p}")
+    patched_any = True
+
+if not candidates:
+    print("WARN: router.py not found; patch not applied (non-fatal)",
+          file=sys.stderr)
+elif not patched_any:
+    print("WARN: no files patched (non-fatal)", file=sys.stderr)
+
+sys.exit(0)