Skip to content

LCORE-1140: Updated LiteLLM #993

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tisnik merged 1 commit into from
Jan 14, 2026
+66 −66
Merged

LCORE-1140: Updated LiteLLM #993

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions requirements-build.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#
# This file is autogenerated by pip-compile with Python 3.12
# This file is autogenerated by pip-compile with Python 3.13
# by the following command:
#
# pybuild-deps compile --output-file=requirements-build.txt /dev/fd/62 /dev/fd/63
Expand Down Expand Up @@ -211,7 +211,7 @@ setuptools-scm==9.2.2
# tqdm
# urllib3
# zipp
tomlkit==0.13.3
tomlkit==0.14.0
# via uv-dynamic-versioning
trove-classifiers==2026.1.12.15
# via hatchling
Expand Down
40 changes: 20 additions & 20 deletions requirements.aarch64.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1177,9 +1177,9 @@ langdetect==1.0.9 \
--hash=sha256:7cbc0746252f19e76f77c0b1690aadf01963be835ef0cd4b56dddf2a8f1dfc2a \
--hash=sha256:cbc1fef89f8d062739774bd51eda3da3274006b3661d199c2655f6b3f6d605a0
# via lightspeed-stack (pyproject.toml:llslibdev)
litellm==1.80.13 \
--hash=sha256:43dcdbca010961f17d7a5a6a995a38d1a46101350959b0e8269576cfe913cf0b \
--hash=sha256:61ed22dfad633ada3b97dd8a50d8e8d804da0115105006d2f9d77ba3fb247a0b
litellm==1.80.16 \
--hash=sha256:21be641b350561b293b831addb25249676b72ebff973a5a1d73b5d7cf35bcd1d \
--hash=sha256:f96233649f99ab097f7d8a3ff9898680207b9eea7d2e23f438074a3dbcf50cca
# via lightspeed-stack (pyproject.toml)
llama-stack==0.3.5 \
--hash=sha256:4a0ce8014b17d14a06858251736f1170f12580fafc519daf75ee1df6c4fbf64b \
Expand Down Expand Up @@ -1982,9 +1982,9 @@ polyleven==0.9.0 \
--hash=sha256:f21e6c050f6f0d259cf9c6367042ba6a69e553b8294143c83bb47f6481486f9c \
--hash=sha256:ff60e2da0864b3d4bec2826eadbbb0a8967384d53bec9e693aad7b0089e1258c
# via autoevals
prometheus-client==0.23.1 \
--hash=sha256:6ae8f9081eaaaf153a2e959d2e6c4f4fb57b12ef76c8c7980202f1e57b48b2ce \
--hash=sha256:dd1913e6e76b59cfe44e7a4b83e01afc9873c1bdfd2ed8739f1e76aeca115f99
prometheus-client==0.24.0 \
--hash=sha256:4ab6d4fb5a1b25ad74b58e6271857e356fff3399473e599d227ab5d0ce6637f0 \
--hash=sha256:726b40c0d499f4904d4b5b7abe8d43e6aff090de0d468ae8f2226290b331c667
Comment on lines +1985 to +1987
Copy link
Contributor

@coderabbitai coderabbitai bot Jan 14, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🌐 Web query:

prometheus-client 0.24.0 changelog release notes breaking changes

💡 Result:

prometheus-client 0.24.0 — no breaking changes listed. Notable changes:

  • Added EncodeLabelSet for tuples (A,B). (docs.rs)
  • Added Family::get_or_create_owned to avoid runtime deadlocks. (docs.rs)
  • impl<T: Collector> Collector for std::sync::Arc. (docs.rs)
  • Changed: EncodeLabelSet::encode() now takes &mut encoder; exemplar timestamps may be provided (needed for convert_classic_histograms_to_nhcb: true). (docs.rs)

If you want, I can paste the full changelog text or link the release/PRs.

Citations:

🏁 Script executed:

# Check what version was previously used and get more context from the requirements file
head -n 1990 requirements.aarch64.txt | tail -n 20

Repository: lightspeed-core/lightspeed-stack

Length of output: 1548

🏁 Script executed:

# Search for any other prometheus-client references to see what version was replaced
rg "prometheus-client" requirements.aarch64.txt -B 2 -A 2

Repository: lightspeed-core/lightspeed-stack

Length of output: 374

🌐 Web query:

prometheus-client python pypi 0.24.0 release notes changelog

💡 Result:

There is no prometheus-client (Python) v0.24.0 on PyPI or the project's GitHub releases. The latest published release (as of the project’s releases page) is v0.23.1. See the releases/changelog on GitHub and the PyPI project page for details:

  • GitHub releases (client_python) — latest v0.23.1. [1]
  • PyPI prometheus-client project page. [2]

Sources:
[1] https://github.com/prometheus/client_python/releases.
[2] https://pypi.org/project/prometheus-client/.

🏁 Script executed:

# Check pyproject.toml or setup.py to see what the previous version was
find . -name "pyproject.toml" -o -name "setup.py" | head -5

Repository: lightspeed-core/lightspeed-stack

Length of output: 92

🏁 Script executed:

# Look for prometheus-client version in project config files
rg "prometheus-client" . -t toml -t txt --max-count 5 -B 1 -A 1

Repository: lightspeed-core/lightspeed-stack

Length of output: 805

prometheus-client version 0.24.0 does not exist on PyPI—latest is v0.23.1. This will cause pip install to fail. Correct the pinned version and update hashes to match a real published release.

🤖 Prompt for AI Agents 
In `@requirements.aarch64.txt` around lines 1985 - 1987, The requirements pin
references a non-existent release "prometheus-client==0.24.0" with invalid
hashes, causing installs to fail; change the pin to the real published version
"prometheus-client==0.23.1" (or another confirmed real version), replace the two
--hash values with the correct SHA256 hashes for that release, and
regenerate/verify hashes (e.g., via pip hash or rebuild your requirements lock)
so the entry for prometheus-client in requirements.aarch64.txt matches a real
PyPI release and its valid hashes.

# via lightspeed-stack (pyproject.toml)
prompt-toolkit==3.0.52 \
--hash=sha256:28cde192929c8e7321de85de1ddbe736f1375148b02f2e17edd840042b1be855 \
Expand Down Expand Up @@ -2122,17 +2122,17 @@ proto-plus==1.27.0 \
--hash=sha256:1baa7f81cf0f8acb8bc1f6d085008ba4171eaf669629d1b6d1673b21ed1c0a82 \
--hash=sha256:873af56dd0d7e91836aee871e5799e1c6f1bda86ac9a983e0bb9f0c266a568c4
# via google-api-core
protobuf==6.33.3 \
--hash=sha256:08a6ca12f60ba99097dd3625ef4275280f99c9037990e47ce9368826b159b890 \
--hash=sha256:1fd18f030ae9df97712fbbb0849b6e54c63e3edd9b88d8c3bb4771f84d8db7a4 \
--hash=sha256:2756963dcfd414eba46bcbb341f0e2c652036e5d700f112b3bb90fa1a031893a \
--hash=sha256:642fce7187526c98683c79a3ad68e5d646a5ef5eb004582fe123fc9a33a9456b \
--hash=sha256:648b7b0144222eb06cf529a3d7b01333c5f30b4196773b682d388f04db373759 \
--hash=sha256:6fa9b5f4baa12257542273e5e6f3c3d3867b30bc2770c14ad9ac8315264bf986 \
--hash=sha256:b4046f9f2ede57ad5b1d9917baafcbcad42f8151a73c755a1e2ec9557b0a764f \
--hash=sha256:c2bf221076b0d463551efa2e1319f08d4cffcc5f0d864614ccd3d0e77a637794 \
--hash=sha256:c46dcc47b243b299f4f7eabeed21929c07f0d36fffe2ea8431793b53c308ab80 \
--hash=sha256:c8794debeb402963fddff41a595e1f649bcd76616ba56c835645cab4539e810e
protobuf==6.33.4 \
--hash=sha256:0f12ddbf96912690c3582f9dffb55530ef32015ad8e678cd494312bd78314c4f \
--hash=sha256:1fe3730068fcf2e595816a6c34fe66eeedd37d51d0400b72fabc848811fdc1bc \
--hash=sha256:2fe67f6c014c84f655ee06f6f66213f9254b3a8b6bda6cda0ccd4232c73c06f0 \
--hash=sha256:3df850c2f8db9934de4cf8f9152f8dc2558f49f298f37f90c517e8e5c84c30e9 \
--hash=sha256:757c978f82e74d75cba88eddec479df9b99a42b31193313b75e492c06a51764e \
--hash=sha256:8f11ffae31ec67fc2554c2ef891dcb561dae9a2a3ed941f9e134c2db06657dbc \
--hash=sha256:918966612c8232fc6c24c78e1cd89784307f5814ad7506c308ee3cf86662850d \
--hash=sha256:955478a89559fa4568f5a81dce77260eabc5c686f9e8366219ebd30debf06aa6 \
--hash=sha256:c7c64f259c618f0bef7bee042075e390debbf9682334be2b67408ec7c1c09ee6 \
--hash=sha256:dc2e61bca3b10470c1912d166fe0af67bfc20eb55971dcef8dfa48ce14f0ed91
Comment on lines +2125 to +2135
Copy link
Contributor

@coderabbitai coderabbitai bot Jan 14, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

pkg="protobuf"; ver="6.33.4"
json="$(curl -fsSL "https://pypi.org/pypi/${pkg}/${ver}/json")"

# List aarch64 linux wheels (if any) and whether any files are yanked
echo "$json" | python3 - <<'PY'
import json,sys,re
d=json.load(sys.stdin)
print("any yanked:", any(u.get("yanked") for u in d["urls"]))
wheels=[u["filename"] for u in d["urls"] if u["packagetype"]=="bdist_wheel"]
aarch=[w for w in wheels if "aarch64" in w and "manylinux" in w]
print("aarch64 wheels:", aarch)
print("\nall wheels available:")
for w in sorted(wheels):
    print(f"  {w}")
PY

Repository: lightspeed-core/lightspeed-stack

Length of output: 162

🏁 Script executed:

# Search for protobuf usage, codegen, and protoc in the repository
echo "=== Searching for protobuf-related codegen, protoc, or build scripts ==="
rg -i "(protoc|protobuf|codegen|\.proto)" --type py --type sh --type txt -l | head -20

Repository: lightspeed-core/lightspeed-stack

Length of output: 844

🌐 Web query:

protobuf 6.33.4 aarch64 wheel availability PyPI

💡 Result:

Short answer: No — PyPI does not (yet) show protobuf 6.33.4 aarch64 wheels. PyPI's protobuf project page still lists 6.33.2 as the latest uploaded build, while the 6.33.4 release is visible in other places (conda-forge / security trackers). [1][2][3]

Sources:

  • PyPI protobuf project files (latest shown: 6.33.2). [1]
  • conda-forge package listing showing libprotobuf 6.33.4 (includes linux-aarch64). [2]
  • Snyk / other trackers reporting protobuf latest version = 6.33.4. [3]

🏁 Script executed:

# Check key source files for protobuf usage patterns
echo "=== Checking src/utils/common.py for protobuf usage ==="
rg "protobuf|proto" src/utils/common.py -A 3 -B 3

echo -e "\n=== Checking src/models/responses.py ==="
rg "protobuf|proto|Message" src/models/responses.py -A 2 -B 2

echo -e "\n=== Checking src/a2a_storage/__init__.py ==="
rg "protobuf|proto" src/a2a_storage/ -r . -A 2 -B 2

echo -e "\n=== Checking for any .proto files or protoc invocations ==="
find . -name "*.proto" -o -name "*protoc*" -o -name "*codegen*" 2>/dev/null | grep -v ".git"

echo -e "\n=== Checking requirements files for protobuf version lock ==="
grep -A 2 -B 2 "protobuf" requirements.aarch64.txt | head -20

Repository: lightspeed-core/lightspeed-stack

Length of output: 1590

protobuf 6.33.4: aarch64 wheel missing on PyPI.
This version does not have an aarch64 wheel published to PyPI (only 6.33.2 is the latest there). The aarch64 image build will fail when attempting to install this exact pin. Consider downgrading to 6.33.2 or waiting for 6.33.4 wheels to be published to PyPI.

🤖 Prompt for AI Agents 
In `@requirements.aarch64.txt` around lines 2125 - 2135, The
requirements.aarch64.txt pins protobuf==6.33.4 which lacks an aarch64 wheel on
PyPI; update the protobuf pin in requirements.aarch64.txt (the line containing
"protobuf==6.33.4") to a published aarch64-compatible version such as
"protobuf==6.33.2" or relax the pin (e.g., "protobuf>=6.33.2,<6.34") so the
aarch64 image build can install a valid wheel; ensure any CI/build scripts that
install from this file use the updated version.

# via
# a2a-sdk
# google-api-core
Expand Down Expand Up @@ -3225,9 +3225,9 @@ tqdm==4.67.1 \
# peft
# sentence-transformers
# transformers
transformers==4.57.3 \
--hash=sha256:c77d353a4851b1880191603d36acb313411d3577f6e2897814f333841f7003f4 \
--hash=sha256:df4945029aaddd7c09eec5cad851f30662f8bd1746721b34cc031d70c65afebc
transformers==4.57.5 \
--hash=sha256:5a1e0deb989cd0b8f141b6d8c9b7c956fc029cd288d68844f57dc0acbaf2fe39 \
--hash=sha256:d631faea6bd32fc51962e482744afeaa70170c70e5e991cf8e355d7275631524
Comment on lines +3228 to +3230
Copy link
Contributor

@coderabbitai coderabbitai bot Jan 14, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🌐 Web query:

transformers 4.57.5 release notes breaking changes

💡 Result:

Do you want the full 4.57.5 release notes or just a brief list of the breaking changes?

🌐 Web query:

transformers 4.57.5 changelog compared to 4.57.3

💡 Result:

There is no transformers v4.57.5 release — the latest stable v4 release is v4.57.3 (Nov 25, 2025). If you meant changes after v4.57.3, the project has moved to v5 release-candidates (e.g., v5.0.0rc0/rc1/rc2). Sources: GitHub releases (shows v4.57.3 as latest v4) and release tracker. [1][2]

Would you like me to list the changes in v4.57.3 or compare v4.57.3 to a specific later RC (v5.0.0rc1/rc2)?

Sources:
[1] Hugging Face Transformers — Releases (GitHub).
[2] ReleaseAlert listing for huggingface/transformers (shows v4.57.3 and v5 RCs).

🌐 Web query:

transformers 4.57.5 dependencies tokenizers huggingface-hub peft torch versions

💡 Result:

For transformers 4.57.x (e.g. 4.57.5) the commonly required / compatible dependency ranges are:

  • tokenizers: >=0.22.0, <=0.23.0. [1]
  • huggingface-hub: >=0.34.0, <1.0. [1][2]
  • torch (PyTorch): >=2.2 (use the appropriate CUDA build from PyTorch). [1]
  • peft: use a peft release that targets transformers 4.55–4.57 (recent peft 0.16–0.17 series; verify exact peft patch if you rely on specific features). [3]

Notes: these ranges are what transformers 4.57.* packages and community reports indicate; if you need exact pins for 4.57.5 (not just 4.57.x) I can fetch that package’s pyproject/metadata and return precise version specifiers.

Sources: [1] oven/packaging listing for transformers 4.57.x, [2] troubleshooting/community notes about transformers 4.57 requiring huggingface-hub <1.0, [3] peft GitHub/PyPI compatibility discussion.

transformers 4.57.5 does not exist — use 4.57.3 (latest stable v4) or confirm if you intended a v5 release candidate.

The specified version transformers==4.57.5 is not a valid release. The latest stable v4 release is 4.57.3 (Nov 25, 2025). If this was a typo, update to 4.57.3. If you need to test a newer version, verify compatibility with v5 release candidates (5.0.0rc1 or rc2) and their transitive constraints.

Before releasing, verify transitive dependency compatibility:

  • tokenizers: >=0.22.0, <=0.23.0
  • huggingface-hub: >=0.34.0, <1.0
  • torch: >=2.2
  • peft: 0.16–0.17 series for 4.55–4.57 compatibility

Run at least one "load + tokenize + forward" smoke test for the models you ship to confirm no regressions from the version change.

🤖 Prompt for AI Agents 
In `@requirements.aarch64.txt` around lines 3228 - 3230, The requirements entry
pins a non-existent transformers version (transformers==4.57.5); update that
line to a valid release (e.g., transformers==4.57.3) or explicitly change it to
a verified v5 candidate (e.g., 5.0.0rc1/rc2) if you intentionally target a
release candidate; after changing the dependency on the transformers line, run
compatibility checks for tokenizers, huggingface-hub, torch, and peft versions
and perform a simple "load + tokenize + forward" smoke test for your shipped
models to confirm no regressions.

# via
# lightspeed-stack (pyproject.toml:llslibdev)
# peft
Expand Down
40 changes: 20 additions & 20 deletions requirements.x86_64.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1177,9 +1177,9 @@ langdetect==1.0.9 \
--hash=sha256:7cbc0746252f19e76f77c0b1690aadf01963be835ef0cd4b56dddf2a8f1dfc2a \
--hash=sha256:cbc1fef89f8d062739774bd51eda3da3274006b3661d199c2655f6b3f6d605a0
# via lightspeed-stack (pyproject.toml:llslibdev)
litellm==1.80.13 \
--hash=sha256:43dcdbca010961f17d7a5a6a995a38d1a46101350959b0e8269576cfe913cf0b \
--hash=sha256:61ed22dfad633ada3b97dd8a50d8e8d804da0115105006d2f9d77ba3fb247a0b
litellm==1.80.16 \
--hash=sha256:21be641b350561b293b831addb25249676b72ebff973a5a1d73b5d7cf35bcd1d \
--hash=sha256:f96233649f99ab097f7d8a3ff9898680207b9eea7d2e23f438074a3dbcf50cca
# via lightspeed-stack (pyproject.toml)
llama-stack==0.3.5 \
--hash=sha256:4a0ce8014b17d14a06858251736f1170f12580fafc519daf75ee1df6c4fbf64b \
Expand Down Expand Up @@ -1982,9 +1982,9 @@ polyleven==0.9.0 \
--hash=sha256:f21e6c050f6f0d259cf9c6367042ba6a69e553b8294143c83bb47f6481486f9c \
--hash=sha256:ff60e2da0864b3d4bec2826eadbbb0a8967384d53bec9e693aad7b0089e1258c
# via autoevals
prometheus-client==0.23.1 \
--hash=sha256:6ae8f9081eaaaf153a2e959d2e6c4f4fb57b12ef76c8c7980202f1e57b48b2ce \
--hash=sha256:dd1913e6e76b59cfe44e7a4b83e01afc9873c1bdfd2ed8739f1e76aeca115f99
prometheus-client==0.24.0 \
--hash=sha256:4ab6d4fb5a1b25ad74b58e6271857e356fff3399473e599d227ab5d0ce6637f0 \
--hash=sha256:726b40c0d499f4904d4b5b7abe8d43e6aff090de0d468ae8f2226290b331c667
# via lightspeed-stack (pyproject.toml)
prompt-toolkit==3.0.52 \
--hash=sha256:28cde192929c8e7321de85de1ddbe736f1375148b02f2e17edd840042b1be855 \
Expand Down Expand Up @@ -2122,17 +2122,17 @@ proto-plus==1.27.0 \
--hash=sha256:1baa7f81cf0f8acb8bc1f6d085008ba4171eaf669629d1b6d1673b21ed1c0a82 \
--hash=sha256:873af56dd0d7e91836aee871e5799e1c6f1bda86ac9a983e0bb9f0c266a568c4
# via google-api-core
protobuf==6.33.3 \
--hash=sha256:08a6ca12f60ba99097dd3625ef4275280f99c9037990e47ce9368826b159b890 \
--hash=sha256:1fd18f030ae9df97712fbbb0849b6e54c63e3edd9b88d8c3bb4771f84d8db7a4 \
--hash=sha256:2756963dcfd414eba46bcbb341f0e2c652036e5d700f112b3bb90fa1a031893a \
--hash=sha256:642fce7187526c98683c79a3ad68e5d646a5ef5eb004582fe123fc9a33a9456b \
--hash=sha256:648b7b0144222eb06cf529a3d7b01333c5f30b4196773b682d388f04db373759 \
--hash=sha256:6fa9b5f4baa12257542273e5e6f3c3d3867b30bc2770c14ad9ac8315264bf986 \
--hash=sha256:b4046f9f2ede57ad5b1d9917baafcbcad42f8151a73c755a1e2ec9557b0a764f \
--hash=sha256:c2bf221076b0d463551efa2e1319f08d4cffcc5f0d864614ccd3d0e77a637794 \
--hash=sha256:c46dcc47b243b299f4f7eabeed21929c07f0d36fffe2ea8431793b53c308ab80 \
--hash=sha256:c8794debeb402963fddff41a595e1f649bcd76616ba56c835645cab4539e810e
protobuf==6.33.4 \
--hash=sha256:0f12ddbf96912690c3582f9dffb55530ef32015ad8e678cd494312bd78314c4f \
--hash=sha256:1fe3730068fcf2e595816a6c34fe66eeedd37d51d0400b72fabc848811fdc1bc \
--hash=sha256:2fe67f6c014c84f655ee06f6f66213f9254b3a8b6bda6cda0ccd4232c73c06f0 \
--hash=sha256:3df850c2f8db9934de4cf8f9152f8dc2558f49f298f37f90c517e8e5c84c30e9 \
--hash=sha256:757c978f82e74d75cba88eddec479df9b99a42b31193313b75e492c06a51764e \
--hash=sha256:8f11ffae31ec67fc2554c2ef891dcb561dae9a2a3ed941f9e134c2db06657dbc \
--hash=sha256:918966612c8232fc6c24c78e1cd89784307f5814ad7506c308ee3cf86662850d \
--hash=sha256:955478a89559fa4568f5a81dce77260eabc5c686f9e8366219ebd30debf06aa6 \
--hash=sha256:c7c64f259c618f0bef7bee042075e390debbf9682334be2b67408ec7c1c09ee6 \
--hash=sha256:dc2e61bca3b10470c1912d166fe0af67bfc20eb55971dcef8dfa48ce14f0ed91
# via
# a2a-sdk
# google-api-core
Expand Down Expand Up @@ -3225,9 +3225,9 @@ tqdm==4.67.1 \
# peft
# sentence-transformers
# transformers
transformers==4.57.3 \
--hash=sha256:c77d353a4851b1880191603d36acb313411d3577f6e2897814f333841f7003f4 \
--hash=sha256:df4945029aaddd7c09eec5cad851f30662f8bd1746721b34cc031d70c65afebc
transformers==4.57.5 \
--hash=sha256:5a1e0deb989cd0b8f141b6d8c9b7c956fc029cd288d68844f57dc0acbaf2fe39 \
--hash=sha256:d631faea6bd32fc51962e482744afeaa70170c70e5e991cf8e355d7275631524
# via
# lightspeed-stack (pyproject.toml:llslibdev)
# peft
Expand Down
Loading
Loading