mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-12 08:42:18 +00:00
chore: remove dead files from the repo root (#50936)
This commit is contained in:
Yassin Kortam
GitHub
parent
2c7ed0713a
commit
89a6b5fbb2
9 changed files with 0 additions and 5588 deletions
|
|
@ -1 +0,0 @@
|
|||
Read @AGENTS.md for coding guidelines
|
||||
|
|
@ -1,63 +0,0 @@
|
|||
# BigModel (Zhipu AI)
|
||||
|
||||
Use `bigmodel/` for the domestic BigModel platform and `zai/` for international Z.AI. Each platform uses its own credentials and default URL
|
||||
|
||||
```yaml
|
||||
model_list:
|
||||
- model_name: glm
|
||||
litellm_params:
|
||||
model: bigmodel/glm-5.3
|
||||
api_key: os.environ/BIGMODEL_API_KEY
|
||||
api_base: https://open.bigmodel.cn
|
||||
```
|
||||
|
||||
One model configuration supports all three native APIs. The provider selects the upstream endpoint from the requested API
|
||||
|
||||
| Proxy endpoint | BigModel endpoint |
|
||||
| --- | --- |
|
||||
| `/v1/chat/completions` | `/api/paas/v4/chat/completions` |
|
||||
| `/v1/responses` | `/api/v1/responses` |
|
||||
| `/v1/messages` | `/api/anthropic/v1/messages` |
|
||||
|
||||
`api_base` is optional and defaults to `https://open.bigmodel.cn`. Set `BIGMODEL_API_BASE` to override the default, or pass an explicit `api_base` to override the environment value. Existing API-specific base URLs and complete endpoint URLs are normalized, preserving a custom proxy's path prefix
|
||||
|
||||
A GLM Coding Plan key uses `https://open.bigmodel.cn/api/coding/paas/v4` as its `api_base`, since Coding Plan and standard keys do not work on each other's endpoints. Chat Completions then calls the Coding Plan endpoint, and Responses and Messages keep the endpoints in the table above
|
||||
|
||||
The Admin UI lists BigModel (Zhipu AI), displays its official logo, and provides a required password API Key field and an optional API Base field with the default URL. Authentication uses an explicit `api_key` or `BIGMODEL_API_KEY`
|
||||
|
||||
```python
|
||||
import litellm
|
||||
|
||||
chat = litellm.completion(
|
||||
model="bigmodel/glm-5.3",
|
||||
messages=[{"role": "user", "content": "Hello"}],
|
||||
thinking={"type": "enabled"},
|
||||
reasoning_effort="low",
|
||||
)
|
||||
|
||||
response = litellm.responses(
|
||||
model="bigmodel/glm-5.3",
|
||||
input="Hello",
|
||||
reasoning={"effort": "low"},
|
||||
store=True,
|
||||
)
|
||||
|
||||
async def messages():
|
||||
return await litellm.anthropic.messages.acreate(
|
||||
model="bigmodel/glm-5.3",
|
||||
max_tokens=1024,
|
||||
messages=[{"role": "user", "content": "Hello"}],
|
||||
thinking={"type": "adaptive"},
|
||||
output_config={"effort": "low"},
|
||||
)
|
||||
```
|
||||
|
||||
Each API retains its native response format and streaming events. The native Messages SDK entry point is asynchronous, as is the proxy's `/v1/messages` route
|
||||
|
||||
GLM-5.3, GLM-5.3-Flash, and GLM-5.3-FlashX use always-on thinking. GLM-5.3 supports `low`, `high`, and `max` reasoning effort. Messages preserves native `thinking`, `output_config`, and `reasoning_effort` parameters
|
||||
|
||||
Set `store=True` when creating a Responses request if you need continuation, retrieval, or deletion. Use the response ID returned by LiteLLM. BigModel documents a seven-day retention period and does not support cancel, compact, native WebSocket, or file_search
|
||||
|
||||
The model catalog and packaged backup include GLM-5.3, GLM-5.3-Flash, and GLM-5.3-FlashX. Prices are expressed in USD/token using a static 7.0 CNY/USD conversion, with the source and verification date in each entry's metadata. Use existing `litellm_params` cost fields for contract-specific deployment prices
|
||||
|
||||
API references: [Chat Completions](https://docs.bigmodel.cn/cn/guide/develop/openai/introduction), [Responses](https://docs.bigmodel.cn/cn/guide/develop/responses/introduction), [Messages](https://docs.bigmodel.cn/cn/guide/develop/claude/introduction), and [pricing](https://docs.bigmodel.cn/cn/guide/start/pricing), checked on 2026-10-27
|
||||
|
|
@ -1,45 +0,0 @@
|
|||
model_list:
|
||||
- model_name: agent-router
|
||||
litellm_params:
|
||||
model: ollama/qwen3.5:9b
|
||||
api_base: http://127.0.0.1:11434
|
||||
model_info:
|
||||
id: cloud-smart
|
||||
type: cloud-smart
|
||||
|
||||
- model_name: agent-router
|
||||
litellm_params:
|
||||
model: ollama/phi4-mini:latest
|
||||
api_base: http://127.0.0.1:11434
|
||||
model_info:
|
||||
id: cloud-fast
|
||||
type: cloud-fast
|
||||
|
||||
- model_name: agent-router
|
||||
litellm_params:
|
||||
model: ollama/llama3.2:3b
|
||||
api_base: http://127.0.0.1:11434
|
||||
model_info:
|
||||
id: local
|
||||
type: local
|
||||
|
||||
- model_name: agent-router
|
||||
litellm_params:
|
||||
model: ollama/lfm2.5-thinking:latest
|
||||
api_base: http://127.0.0.1:11434
|
||||
model_info:
|
||||
id: deep
|
||||
type: deep
|
||||
|
||||
router_settings:
|
||||
routing_strategy: lar1
|
||||
routing_strategy_args:
|
||||
confidence_threshold_low: 0.3
|
||||
confidence_threshold_medium: 0.5
|
||||
confidence_threshold_high: 0.7
|
||||
|
||||
general_settings:
|
||||
master_key: sk-lar1-demo
|
||||
|
||||
litellm_settings:
|
||||
set_verbose: true
|
||||
|
|
@ -1,23 +0,0 @@
|
|||
{
|
||||
"zapier": {
|
||||
"sse_url": "https://mcp.zapier.com/api/mcp"
|
||||
},
|
||||
"deepwiki": {
|
||||
"http_url": "https://mcp.deepwiki.com/mcp",
|
||||
"sse_url": "https://mcp.deepwiki.com/sse",
|
||||
"description": "The DeepWiki MCP server provides programmatic access to DeepWiki's repository documentation (Devin Wiki) and search capabilities (Devin Search)."
|
||||
},
|
||||
"jira": {
|
||||
"sse_url": "https://mcp.atlassian.com/v1/sse",
|
||||
"description": "The Jira MCP server provides programmatic access to Jira's issue tracking capabilities."
|
||||
},
|
||||
"linear": {
|
||||
"sse_url": "https://mcp.linear.app/sse",
|
||||
"description": "The Linear MCP server provides programmatic access to Linear's issue tracking capabilities."
|
||||
},
|
||||
"scrapegraph": {
|
||||
"http_url": "https://smithery.ai/api/mcp/scrapegraph-mcp",
|
||||
"sse_url": "https://smithery.ai/api/mcp/scrapegraph-mcp/sse",
|
||||
"description": "The ScrapeGraph MCP server provides programmatic access to ScrapeGraph AI's web scraping capabilities, including smart scraping, web crawling, search scraping, and agentic scraping workflows."
|
||||
}
|
||||
}
|
||||
5325
package-lock.json
generated
5325
package-lock.json
generated
File diff suppressed because it is too large
Load diff
21
package.json
21
package.json
|
|
@ -1,21 +0,0 @@
|
|||
{
|
||||
"dependencies": {
|
||||
"prism-react-renderer": "2.4.1",
|
||||
"prisma": "5.17.0",
|
||||
"react-copy-to-clipboard": "5.1.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@testing-library/jest-dom": "6.8.0",
|
||||
"@testing-library/react": "14.3.1",
|
||||
"@types/react-copy-to-clipboard": "5.0.7",
|
||||
"jest": "29.7.0"
|
||||
},
|
||||
"overrides": {
|
||||
"glob": "13.0.0",
|
||||
"minimatch": "10.2.5",
|
||||
"picomatch": "2.3.2",
|
||||
"@isaacs/brace-expansion": "5.0.0",
|
||||
"@babel/traverse": "7.28.5",
|
||||
"braces": "3.0.3"
|
||||
}
|
||||
}
|
||||
|
|
@ -1,59 +0,0 @@
|
|||
#!/usr/bin/env bash
|
||||
# QA: code interpreter sandbox stickiness via metadata.session_id
|
||||
# bash qa_sticky_session.sh
|
||||
# LITELLM_BASE_URL=http://localhost:4000 LITELLM_KEY="$LITELLM_MASTER_KEY" bash qa_sticky_session.sh
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
BASE="${LITELLM_BASE_URL:-http://localhost:4000}"
|
||||
KEY="${LITELLM_KEY:-${LITELLM_MASTER_KEY:?set LITELLM_KEY or LITELLM_MASTER_KEY}}"
|
||||
MODEL="${LITELLM_MODEL:-gpt-4o-mini}"
|
||||
# proxy running at http://localhost:4000
|
||||
SESSION_A="qa-session-$(date +%s)-A"
|
||||
SESSION_B="qa-session-$(date +%s)-B"
|
||||
|
||||
content() {
|
||||
echo "$1" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('choices',[{}])[0].get('message',{}).get('content','<error>'))"
|
||||
}
|
||||
|
||||
call() {
|
||||
local session="${1:-}" code="$2" meta=""
|
||||
[[ -n "$session" ]] && meta=", \"metadata\": {\"session_id\": \"$session\"}"
|
||||
curl -s -X POST "$BASE/chat/completions" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "Authorization: Bearer $KEY" \
|
||||
-d "{\"model\":\"$MODEL\"$meta,\"tools\":[{\"type\":\"code_interpreter\"}],\"messages\":[{\"role\":\"user\",\"content\":\"Run this Python code and tell me the result: $code\"}]}"
|
||||
}
|
||||
|
||||
assert_match() {
|
||||
local label="$1" body="$2" pattern="$3"
|
||||
if echo "$body" | grep -qiE "$pattern"; then
|
||||
echo "PASS $label"
|
||||
else
|
||||
echo "FAIL $label (expected /$pattern/)"
|
||||
echo " $(content "$body")"
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
echo "=== Sticky Session Sandbox QA ==="
|
||||
echo "base: $BASE session A: $SESSION_A session B: $SESSION_B"
|
||||
echo
|
||||
|
||||
R=$(call "$SESSION_A" "x = 42; print(x)")
|
||||
assert_match "same session_id reuses sandbox (set x=42)" "$R" "42"
|
||||
|
||||
R=$(call "$SESSION_A" "print(x)")
|
||||
assert_match "same session_id keeps state (x still 42)" "$R" "42"
|
||||
|
||||
R=$(call "$SESSION_B" "print(x)")
|
||||
assert_match "different session_id is isolated" "$R" "not defined|NameError|undefined|error"
|
||||
|
||||
R=$(call "" "y = 99; print(y)")
|
||||
assert_match "no session_id runs code" "$R" "99"
|
||||
|
||||
R=$(call "" "print(y)")
|
||||
assert_match "no session_id gets fresh sandbox each request" "$R" "not defined|NameError|undefined|error"
|
||||
|
||||
echo
|
||||
echo "All checks passed."
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
[
|
||||
{
|
||||
"name": "TEMPLATE: copy this block for a new plugin, then delete this entry",
|
||||
"description": "One line on what the plugin does and the routing signal it publishes.",
|
||||
"author": "Plugin author's name.",
|
||||
"repo": "https://github.com/<owner>/<repo> (public source repository).",
|
||||
"commit": "Full 40-char git SHA to pin when the plugin is not yet on PyPI; omit once 'pypi' is set.",
|
||||
"version": "Plugin release version, e.g. 1.0.0.",
|
||||
"pypi": "PyPI spec pinned to a version, e.g. my-plugin==1.0.0, or null if unpublished.",
|
||||
"litellm_version": "Minimum compatible litellm version, e.g. >=1.94.0.",
|
||||
"entrypoint": "Dotted import path to the plugin instance, e.g. my_plugin.plugin.instance.",
|
||||
"license": "SPDX license id, e.g. MIT.",
|
||||
"tags": ["searchable", "keywords"]
|
||||
},
|
||||
{
|
||||
"name": "language-detector",
|
||||
"description": "Detects the user's language and publishes a routing signal.",
|
||||
"author": "Jean Nuñez",
|
||||
"repo": "https://github.com/jeann2013/language-detector",
|
||||
"commit": "9e712819269173fc25a16f59ca3e9890f7864ac1",
|
||||
"version": "1.0.0",
|
||||
"pypi": null,
|
||||
"litellm_version": ">=1.94.0",
|
||||
"entrypoint": "litellm_plugin_language_detector.plugin.language_detector_plugin",
|
||||
"license": "MIT",
|
||||
"tags": ["language", "classification", "routing"]
|
||||
}
|
||||
]
|
||||
23
taplo.toml
23
taplo.toml
|
|
@ -1,23 +0,0 @@
|
|||
[formatting]
|
||||
|
||||
# Keep your table/key order as written (project, project.scripts, dependency-groups, tool.uv, ...)
|
||||
reorder_keys = false
|
||||
|
||||
# Force arrays to stay multiline once expanded
|
||||
array_auto_expand = true
|
||||
array_auto_collapse = false
|
||||
|
||||
# Keep nice spacing inside arrays and inline tables
|
||||
compact_arrays = false
|
||||
compact_inline_tables = true
|
||||
|
||||
# Don’t align `=` vertically (matches your example)
|
||||
align_entries = true
|
||||
|
||||
# Reasonable defaults
|
||||
align_comments = true
|
||||
trailing_newline = true
|
||||
reorder_arrays = true
|
||||
reorder_inline_tables = false
|
||||
allowed_blank_lines = 2
|
||||
crlf = false
|
||||
Loading…
Add table
Reference in a new issue