Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 267c030457 | |||
| c19309fe7e | |||
| 4413881b2d |
@@ -1,5 +1,3 @@
|
|||||||
# Project: llama-swap
|
|
||||||
|
|
||||||
## Project Description:
|
## Project Description:
|
||||||
|
|
||||||
llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
|
llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
|
||||||
@@ -9,6 +7,13 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
|
|||||||
- golang
|
- golang
|
||||||
- typescript, vite and react for UI (ui/)
|
- typescript, vite and react for UI (ui/)
|
||||||
|
|
||||||
|
## Workflow Tasks
|
||||||
|
|
||||||
|
- when summarizing changes only include details that require further action
|
||||||
|
- just say "Done." when there is no further action
|
||||||
|
- use `gh` to create PRs and load issues
|
||||||
|
- do not mention "created by claude" in commit messages
|
||||||
|
|
||||||
## Testing
|
## Testing
|
||||||
|
|
||||||
- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
|
- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
|
||||||
@@ -16,30 +21,26 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
|
|||||||
- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
|
- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
|
||||||
- Use `make test-all` before completing work. This includes long running concurrency tests.
|
- Use `make test-all` before completing work. This includes long running concurrency tests.
|
||||||
|
|
||||||
## Workflow Tasks
|
### Commit message example format:
|
||||||
|
|
||||||
### Plan Improvements
|
```
|
||||||
|
proxy: add new feature
|
||||||
|
|
||||||
Work plans are located in ai-plans/. Plans written by the user may be incomplete, contain inconsistencies or errors.
|
Add new feature that implements functionality X and Y.
|
||||||
|
|
||||||
When the user asks to improve a plan follow these guidelines for expanding and improving it.
|
- key change 1
|
||||||
|
- key change 2
|
||||||
|
- key change 3
|
||||||
|
|
||||||
- Identify any inconsistencies.
|
fixes #123
|
||||||
- Expand plans out to be detailed specification of requirements and changes to be made.
|
```
|
||||||
- Plans should have at least these sections:
|
|
||||||
- Title - very short, describes changes
|
|
||||||
- Overview: A more detailed summary of goal and outcomes desired
|
|
||||||
- Design Requirements: Detailed descriptions of what needs to be done
|
|
||||||
- Testing Plan: Tests to be implemented
|
|
||||||
- Checklist: A detailed list of changes to be made
|
|
||||||
|
|
||||||
Look for "plan expansion" as explicit instructions to improve a plan.
|
## Code Reviews
|
||||||
|
|
||||||
### Implementation of plans
|
- use three levels High, Medium, Low severity
|
||||||
|
- label each discovered issue with a label like H1, M2, L3 respectively
|
||||||
|
- High severity are must fix issues:
|
||||||
|
|
||||||
When the user says "paint it", respond with "commencing automated assembly". Then implement the changes as described by the plan. Update the checklist as you complete items.
|
- security issues
|
||||||
|
|
||||||
## General Rules
|
- Medium are recommended improvements
|
||||||
|
|
||||||
- when summarizing changes only include details that require further action (action items)
|
|
||||||
- when there are no action items, just say "Done."
|
|
||||||
|
|||||||
@@ -277,6 +277,7 @@ func (pm *ProxyManager) setupGinEngine() {
|
|||||||
// Set up routes using the Gin engine
|
// Set up routes using the Gin engine
|
||||||
// Protected routes use pm.apiKeyAuth() middleware
|
// Protected routes use pm.apiKeyAuth() middleware
|
||||||
pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
|
pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
|
||||||
|
pm.ginEngine.POST("/v1/responses", pm.apiKeyAuth(), pm.proxyInferenceHandler)
|
||||||
// Support legacy /v1/completions api, see issue #12
|
// Support legacy /v1/completions api, see issue #12
|
||||||
pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
|
pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
|
||||||
// Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)
|
// Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)
|
||||||
|
|||||||
Generated
+18
-14
@@ -12,7 +12,7 @@
|
|||||||
"react-dom": "^19.1.0",
|
"react-dom": "^19.1.0",
|
||||||
"react-icons": "^5.5.0",
|
"react-icons": "^5.5.0",
|
||||||
"react-resizable-panels": "^3.0.4",
|
"react-resizable-panels": "^3.0.4",
|
||||||
"react-router-dom": "^7.6.2"
|
"react-router-dom": "^7.12.0"
|
||||||
},
|
},
|
||||||
"devDependencies": {
|
"devDependencies": {
|
||||||
"@eslint/js": "^9.25.0",
|
"@eslint/js": "^9.25.0",
|
||||||
@@ -2232,12 +2232,16 @@
|
|||||||
"license": "MIT"
|
"license": "MIT"
|
||||||
},
|
},
|
||||||
"node_modules/cookie": {
|
"node_modules/cookie": {
|
||||||
"version": "1.0.2",
|
"version": "1.1.1",
|
||||||
"resolved": "https://registry.npmjs.org/cookie/-/cookie-1.0.2.tgz",
|
"resolved": "https://registry.npmjs.org/cookie/-/cookie-1.1.1.tgz",
|
||||||
"integrity": "sha512-9Kr/j4O16ISv8zBBhJoi4bXOYNTkFLOqSL3UDB0njXxCXNezjeyVrJyGOWtgfs/q2km1gwBcfH8q1yEGoMYunA==",
|
"integrity": "sha512-ei8Aos7ja0weRpFzJnEA9UHJ/7XQmqglbRwnf2ATjcB9Wq874VKH9kfjjirM6UhU2/E5fFYadylyhFldcqSidQ==",
|
||||||
"license": "MIT",
|
"license": "MIT",
|
||||||
"engines": {
|
"engines": {
|
||||||
"node": ">=18"
|
"node": ">=18"
|
||||||
|
},
|
||||||
|
"funding": {
|
||||||
|
"type": "opencollective",
|
||||||
|
"url": "https://opencollective.com/express"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"node_modules/cross-spawn": {
|
"node_modules/cross-spawn": {
|
||||||
@@ -3559,9 +3563,9 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"node_modules/react-router": {
|
"node_modules/react-router": {
|
||||||
"version": "7.6.2",
|
"version": "7.12.0",
|
||||||
"resolved": "https://registry.npmjs.org/react-router/-/react-router-7.6.2.tgz",
|
"resolved": "https://registry.npmjs.org/react-router/-/react-router-7.12.0.tgz",
|
||||||
"integrity": "sha512-U7Nv3y+bMimgWjhlT5CRdzHPu2/KVmqPwKUCChW8en5P3znxUqwlYFlbmyj8Rgp1SF6zs5X4+77kBVknkg6a0w==",
|
"integrity": "sha512-kTPDYPFzDVGIIGNLS5VJykK0HfHLY5MF3b+xj0/tTyNYL1gF1qs7u67Z9jEhQk2sQ98SUaHxlG31g1JtF7IfVw==",
|
||||||
"license": "MIT",
|
"license": "MIT",
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"cookie": "^1.0.1",
|
"cookie": "^1.0.1",
|
||||||
@@ -3581,12 +3585,12 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"node_modules/react-router-dom": {
|
"node_modules/react-router-dom": {
|
||||||
"version": "7.6.2",
|
"version": "7.12.0",
|
||||||
"resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.6.2.tgz",
|
"resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.12.0.tgz",
|
||||||
"integrity": "sha512-Q8zb6VlTbdYKK5JJBLQEN06oTUa/RAbG/oQS1auK1I0TbJOXktqm+QENEVJU6QvWynlXPRBXI3fiOQcSEA78rA==",
|
"integrity": "sha512-pfO9fiBcpEfX4Tx+iTYKDtPbrSLLCbwJ5EqP+SPYQu1VYCXdy79GSj0wttR0U4cikVdlImZuEZ/9ZNCgoaxwBA==",
|
||||||
"license": "MIT",
|
"license": "MIT",
|
||||||
"dependencies": {
|
"dependencies": {
|
||||||
"react-router": "7.6.2"
|
"react-router": "7.12.0"
|
||||||
},
|
},
|
||||||
"engines": {
|
"engines": {
|
||||||
"node": ">=20.0.0"
|
"node": ">=20.0.0"
|
||||||
@@ -3705,9 +3709,9 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"node_modules/set-cookie-parser": {
|
"node_modules/set-cookie-parser": {
|
||||||
"version": "2.7.1",
|
"version": "2.7.2",
|
||||||
"resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.1.tgz",
|
"resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.2.tgz",
|
||||||
"integrity": "sha512-IOc8uWeOZgnb3ptbCURJWNjWUPcO3ZnTTdzsurqERrP6nPyv+paC55vJM0LpOlT2ne+Ix+9+CRG1MNLlyZ4GjQ==",
|
"integrity": "sha512-oeM1lpU/UvhTxw+g3cIfxXHyJRc/uidd3yK1P242gzHds0udQBYzs3y8j4gCCW+ZJ7ad0yctld8RYO+bdurlvw==",
|
||||||
"license": "MIT"
|
"license": "MIT"
|
||||||
},
|
},
|
||||||
"node_modules/shebang-command": {
|
"node_modules/shebang-command": {
|
||||||
|
|||||||
+1
-1
@@ -14,7 +14,7 @@
|
|||||||
"react-dom": "^19.1.0",
|
"react-dom": "^19.1.0",
|
||||||
"react-icons": "^5.5.0",
|
"react-icons": "^5.5.0",
|
||||||
"react-resizable-panels": "^3.0.4",
|
"react-resizable-panels": "^3.0.4",
|
||||||
"react-router-dom": "^7.6.2"
|
"react-router-dom": "^7.12.0"
|
||||||
},
|
},
|
||||||
"devDependencies": {
|
"devDependencies": {
|
||||||
"@eslint/js": "^9.25.0",
|
"@eslint/js": "^9.25.0",
|
||||||
|
|||||||
Reference in New Issue
Block a user