mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
feat(cherry-pick): fixes for 0.3.1 release (#3998)
## Summary Cherry-picks 5 critical fixes from main to the release-0.3.x branch for the v0.3.1 release, plus CI workflow updates. **Note**: This recreates the cherry-picks from the closed PR #3991, now targeting the renamed `release-0.3.x` branch (previously `release-0.3.x-maint`). ## Commits 1. **2c56a8560** - fix(context): prevent provider data leak between streaming requests (#3924) - **CRITICAL SECURITY FIX**: Prevents provider credentials from leaking between requests - Fixed import path for 0.3.0 compatibility 2. **ddd32b187** - fix(inference): enable routing of models with provider_data alone (#3928) - Enables routing for fully qualified model IDs with provider_data - Resolved merge conflicts, adapted for 0.3.0 structure 3. **f7c2973aa** - fix: Avoid BadRequestError due to invalid max_tokens (#3667) - Fixes failures with Gemini and other providers that reject max_tokens=0 - Non-breaking API change 4. **d7f9da616** - fix(responses): sync conversation before yielding terminal events in streaming (#3888) - Ensures conversation sync executes even when streaming consumers break early 5. **0ffa8658b** - fix(logging): ensure logs go to stderr, loggers obey levels (#3885) - Fixes logging infrastructure 6. **75b49cb3c** - ci: support release branches and match client branch (#3990) - Updates CI workflows to support release-X.Y.x branches - Matches client branch from llama-stack-client-python for release testing - Fixes artifact name collisions ## Adaptations for 0.3.0 - Fixed import paths: `llama_stack.core.telemetry.tracing` → `llama_stack.providers.utils.telemetry.tracing` - Fixed import paths: `llama_stack.core.telemetry.telemetry` → `llama_stack.apis.telemetry` - Changed `self.telemetry_enabled` → `self.telemetry` (0.3.0 attribute name) - Removed `rerank()` method that doesn't exist in 0.3.0 ## Testing All imports verified and tests should pass once CI is set up.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
bf091306fe
commit
39f33f7f12
11 changed files with 182 additions and 65 deletions
|
|
@ -7,6 +7,10 @@
|
|||
from collections.abc import AsyncGenerator
|
||||
from contextvars import ContextVar
|
||||
|
||||
from llama_stack.providers.utils.telemetry.tracing import CURRENT_TRACE_CONTEXT
|
||||
|
||||
_MISSING = object()
|
||||
|
||||
|
||||
def preserve_contexts_async_generator[T](
|
||||
gen: AsyncGenerator[T, None], context_vars: list[ContextVar]
|
||||
|
|
@ -21,20 +25,60 @@ def preserve_contexts_async_generator[T](
|
|||
|
||||
async def wrapper() -> AsyncGenerator[T, None]:
|
||||
while True:
|
||||
previous_values: dict[ContextVar, object] = {}
|
||||
tokens: dict[ContextVar, object] = {}
|
||||
|
||||
# Restore ALL context values before any await and capture previous state
|
||||
# This is needed to propagate context across async generator boundaries
|
||||
for context_var in context_vars:
|
||||
try:
|
||||
previous_values[context_var] = context_var.get()
|
||||
except LookupError:
|
||||
previous_values[context_var] = _MISSING
|
||||
tokens[context_var] = context_var.set(initial_context_values[context_var.name])
|
||||
|
||||
def _restore_context_var(context_var: ContextVar, *, _tokens=tokens, _prev=previous_values) -> None:
|
||||
token = _tokens.get(context_var)
|
||||
previous_value = _prev.get(context_var, _MISSING)
|
||||
if token is not None:
|
||||
try:
|
||||
context_var.reset(token)
|
||||
return
|
||||
except (RuntimeError, ValueError):
|
||||
pass
|
||||
|
||||
if previous_value is _MISSING:
|
||||
context_var.set(None)
|
||||
else:
|
||||
context_var.set(previous_value)
|
||||
|
||||
try:
|
||||
# Restore context values before any await
|
||||
for context_var in context_vars:
|
||||
context_var.set(initial_context_values[context_var.name])
|
||||
|
||||
item = await gen.__anext__()
|
||||
|
||||
# Update our tracked values with any changes made during this iteration
|
||||
for context_var in context_vars:
|
||||
initial_context_values[context_var.name] = context_var.get()
|
||||
|
||||
yield item
|
||||
|
||||
except StopAsyncIteration:
|
||||
# Restore all context vars before exiting to prevent leaks
|
||||
# Use _restore_context_var for all vars to properly restore to previous values
|
||||
for context_var in context_vars:
|
||||
_restore_context_var(context_var)
|
||||
break
|
||||
except Exception:
|
||||
# Restore all context vars on exception
|
||||
for context_var in context_vars:
|
||||
_restore_context_var(context_var)
|
||||
raise
|
||||
|
||||
try:
|
||||
yield item
|
||||
# Update our tracked values with any changes made during this iteration
|
||||
# Only for non-trace context vars - trace context must persist across yields
|
||||
# to allow nested span tracking for telemetry
|
||||
for context_var in context_vars:
|
||||
if context_var is not CURRENT_TRACE_CONTEXT:
|
||||
initial_context_values[context_var.name] = context_var.get()
|
||||
finally:
|
||||
# Restore non-trace context vars after each yield to prevent leaks between requests
|
||||
# CURRENT_TRACE_CONTEXT is NOT restored here to preserve telemetry span stack
|
||||
for context_var in context_vars:
|
||||
if context_var is not CURRENT_TRACE_CONTEXT:
|
||||
_restore_context_var(context_var)
|
||||
|
||||
return wrapper()
|
||||
|
|
|
|||
33
llama_stack/ui/package-lock.json
generated
33
llama_stack/ui/package-lock.json
generated
|
|
@ -18,7 +18,7 @@
|
|||
"class-variance-authority": "^0.7.1",
|
||||
"clsx": "^2.1.1",
|
||||
"framer-motion": "^12.23.24",
|
||||
"llama-stack-client": "^0.2.23",
|
||||
"llama-stack-client": "^0.3.0",
|
||||
"lucide-react": "^0.545.0",
|
||||
"next": "15.5.4",
|
||||
"next-auth": "^4.24.11",
|
||||
|
|
@ -75,20 +75,6 @@
|
|||
"url": "https://github.com/sponsors/sindresorhus"
|
||||
}
|
||||
},
|
||||
"node_modules/@ampproject/remapping": {
|
||||
"version": "2.3.0",
|
||||
"resolved": "https://registry.npmjs.org/@ampproject/remapping/-/remapping-2.3.0.tgz",
|
||||
"integrity": "sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw==",
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@jridgewell/gen-mapping": "^0.3.5",
|
||||
"@jridgewell/trace-mapping": "^0.3.24"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=6.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@asamuzakjp/css-color": {
|
||||
"version": "3.2.0",
|
||||
"resolved": "https://registry.npmjs.org/@asamuzakjp/css-color/-/css-color-3.2.0.tgz",
|
||||
|
|
@ -3647,17 +3633,6 @@
|
|||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@tybys/wasm-util": {
|
||||
"version": "0.9.0",
|
||||
"resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.9.0.tgz",
|
||||
"integrity": "sha512-6+7nlbMVX/PVDCwaIQ8nTOPveOcFLSt8GcXdx8hD0bt39uWxYT88uXzqTd4fTvqta7oeUJqudepapKNt2DYJFw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"optional": true,
|
||||
"dependencies": {
|
||||
"tslib": "^2.4.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/aria-query": {
|
||||
"version": "5.0.4",
|
||||
"resolved": "https://registry.npmjs.org/@types/aria-query/-/aria-query-5.0.4.tgz",
|
||||
|
|
@ -9660,9 +9635,9 @@
|
|||
"license": "MIT"
|
||||
},
|
||||
"node_modules/llama-stack-client": {
|
||||
"version": "0.2.23",
|
||||
"resolved": "https://registry.npmjs.org/llama-stack-client/-/llama-stack-client-0.2.23.tgz",
|
||||
"integrity": "sha512-J3YFH1HW2K70capejQxGlCyTgKdfx+sQf8Ab+HFi1j2Q00KtpHXB79RxejvBxjWC3X2E++P9iU57KdU2Tp/rIQ==",
|
||||
"version": "0.3.0",
|
||||
"resolved": "https://registry.npmjs.org/llama-stack-client/-/llama-stack-client-0.3.0.tgz",
|
||||
"integrity": "sha512-76K/t1doaGmlBbDxCADaral9Vccvys9P8pqAMIhwBhMAqWudCEORrMMhUSg+pjhamWmEKj3wa++d4zeOGbfN/w==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/node": "^18.11.18",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue