From 83c543a0baa4d7095d127de983cb2c5e79458b68 Mon Sep 17 00:00:00 2001
From: Inferencebot <bot@inference.coop>
Date: Sat, 31 Oct 2026 21:26:03 +0000
Subject: [PATCH] gateway: expose the eight telemetry headers requested in
 co-op/support#39

Adds x-litellm-model-name, -call-id, -key-spend, -response-duration-ms, -overhead-duration-ms, -callback-duration-ms, -attempted-retries and -attempted-fallbacks to the CORS expose list, on the GM's go-ahead. Renames COST_HEADERS to EXPOSED_HEADERS since the list is no longer only costs. x-litellm-key-spend discloses the caller's own key spend, which is their own data; noted in the thread so it can be dropped if anyone objects.
---
 .../patch_expose_cost_headers.cpython-314.pyc | Bin 3951 -> 4172 bytes
 patch_expose_cost_headers.py                  |  16 +++++++++++++---
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/__pycache__/patch_expose_cost_headers.cpython-314.pyc b/__pycache__/patch_expose_cost_headers.cpython-314.pyc
index 4558d99a80a38ce242ae60d322d161edc3157b98..7fac41fb781c1661745199816c28cceeb2722ff5 100644
GIT binary patch
delta 396
zcmaDacSeCvn~#@^0SJ!7Jj<HHw~^0}UC|cEEtUilFBuvbF7R5fv|o@ofpdo94B;6r
zSNRlI+fS}#?`L${%*%0unS<XoBEUb`)n)Q4Zf8cP$$C5+bm}i_+h5RfxZsd+Av6C%
zM!^NH!YeFAH@SI=1b~L#;)svWP0Y-TkJl8b5}zE%C%##cH<!_&N~A(JC$l6qCnr}o
zH$NpcM>j7qH?>L-A)1_+lcSrNQYDNK%1*7+EiOpSOR16rnj~DGQd*Q)l9`{Un_FBZ
zhftPZmRgjNnwX-CLmp&uQetv8io7&Je_}~VYHmSEYKm@AYDrOMYH^h;Hpw&&s5!-x
z`}mqQ#D$p}_&*piu$wn9e_&x`6?nkL(VpIzei0O;mwBx(vsr&-Wn#6NY{_p104DT_
AOaK4?

delta 187
zcmX@3@LrBjn~#@^0SF9~pJlz^*~sU|u4oM87E1z&mkbRI7kDjJ+AK(%z&S&4hVTrR
zt9**9Z6?>U_cK~-=H<A-%*x~J9~?6IEw?kH#biUC4LUWKwQVkF*<P?sy^xl3AvN~`
zSKbwt{F~f7MFKz*Z*j!O=O$+6#m8&%REbYE<P+bl!kf!DIh(&(gI9p5f#-u91G{+x
k^9L42R)Gg>9PR0i=@&sRxXf#Dna$!WD-)~bWHA9V0Ne&Se*gdg

diff --git a/patch_expose_cost_headers.py b/patch_expose_cost_headers.py
index be6e078..72f9bc1 100644
--- a/patch_expose_cost_headers.py
+++ b/patch_expose_cost_headers.py
@@ -29,7 +29,7 @@ import sys
 
 # The header names the proxy can set, taken from the running image rather than
 # guessed: grep -rhoE 'x-litellm-[a-z0-9-]*cost[a-z0-9-]*' over the litellm package.
-COST_HEADERS = [
+EXPOSED_HEADERS = [
     "x-litellm-response-cost",
     "x-litellm-response-cost-input",
     "x-litellm-response-cost-output",
@@ -42,13 +42,23 @@ COST_HEADERS = [
     "x-litellm-response-cost-reasoning",
     "x-litellm-response-cost-tool-usage",
     "x-litellm-classifier-cost",
+    # Telemetry names, requested in co-op/support#39 (2026-10-31): model identity,
+    # call id, the caller's own key spend, timings and retry/fallback counts.
+    "x-litellm-model-name",
+    "x-litellm-call-id",
+    "x-litellm-key-spend",
+    "x-litellm-response-duration-ms",
+    "x-litellm-overhead-duration-ms",
+    "x-litellm-callback-duration-ms",
+    "x-litellm-attempted-retries",
+    "x-litellm-attempted-fallbacks",
 ]
 
 OLD = "    expose_headers=LITELLM_UI_ALLOW_HEADERS,\n"
 NEW = (
     "    expose_headers=LITELLM_UI_ALLOW_HEADERS\n"
     "    + [\n"
-    + "".join(f'        "{h}",\n' for h in COST_HEADERS)
+    + "".join(f'        "{h}",\n' for h in EXPOSED_HEADERS)
     + "    ],\n"
 )
 
@@ -72,7 +82,7 @@ def main() -> int:
         return 0
 
     target.write_text(src.replace(OLD, NEW))
-    print(f"expose-cost-headers: appended {len(COST_HEADERS)} cost header names to expose_headers in {target}")
+    print(f"expose-cost-headers: appended {len(EXPOSED_HEADERS)} cost header names to expose_headers in {target}")
     return 0