Executive summary
cocoyes/zhizhi-agent-runtime falls short of our standard for production because we found no automated security scanning of the code, its secrets or its dependencies. It scores 66.4 out of 100 and is rated Adequate, and five of its six critical findings are security problems in the build pipeline and in the packages it uses.
Production Readiness, at 59.4, is the weakest lens and counts most in the score. The best first step for the work it takes is fixing the test that passed on some runs and failed on others, worth about 3.4 points. Adding automated security scanning would lift Production Readiness itself, worth about 6.2 points. Raising Production Readiness to 70 would lift the score to about 70.0.
Four pipeline tools are referenced by a changeable name, so the build pipeline can be tampered with. One known security hole in a package the code depends on can be used by attackers. Pinning each tool to an exact version and updating the vulnerable packages would close both risks.
The product code is 12,997 lines, about €23,000 to rebuild.
If Production Readiness rose from 59.4 to 70, the lowest score rated Strong, the score would rise from 66.4 to about 70.0.
Rebuild cost: about €23,000 · Estimate
| Cost to rebuild | €7,500 to €38,000, for 125 to 396 hours of work, about 0.2 person-years for one engineer |
|---|---|
| Difficulty of the problem | Standard, judged from the kind of software and how it is built. Code that solves a harder problem, such as payments or medical bookings, costs more per line to write. |
| Quality factor | ×0.9 at a score of 66. Better code takes more work to write, so the factor is ×1.0 at a score of 70, lower below it and higher above it. |
| Size | Small: 12,997 lines of product code |
| What it is not | Not a quotation: nobody has offered to build it for that. Not a valuation: it says nothing about what the business is worth. Not a certified figure: no professional has signed it as one. |
Top priorities
Diagnosis: what the measurements show together
Architecture: which parts of the code depend on which
| uses → | 1 com/cocoyes/zhizhi-agent-runtime/contract | 2 com/cocoyes/zhizhi-agent-runtime/internal/budget | 3 com/cocoyes/zhizhi-agent-runtime/model | 4 com/cocoyes/zhizhi-agent-runtime/observe | 5 com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat | 6 com/cocoyes/zhizhi-agent-runtime/checkpoint | 7 com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput | 8 com/cocoyes/zhizhi-agent-runtime/plan | 9 com/cocoyes/zhizhi-agent-runtime/route | 10 com/cocoyes/zhizhi-agent-runtime/tool | 11 com/cocoyes/zhizhi-agent-runtime/internal/runtime/react | 12 com/cocoyes/zhizhi-agent-runtime/mcp | 13 com/cocoyes/zhizhi-agent-runtime/middleware | 14 com/cocoyes/zhizhi-agent-runtime/policy | 15 com/cocoyes/zhizhi-agent-runtime/skill | 16 com/cocoyes/zhizhi-agent-runtime/speech | 17 com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao | 18 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec | 19 com/cocoyes/zhizhi-agent-runtime/skill/script | 20 com/cocoyes/zhizhi-agent-runtime | 21 com/cocoyes/zhizhi-agent-runtime/skill/script/docker | 22 com/cocoyes/zhizhi-agent-runtime/adapter/otel | 23 com/cocoyes/zhizhi-agent-runtime/eval |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 com/cocoyes/zhizhi-agent-runtime/contract | |||||||||||||||||||||||
| 2 com/cocoyes/zhizhi-agent-runtime/internal/budget | |||||||||||||||||||||||
| 3 com/cocoyes/zhizhi-agent-runtime/model | |||||||||||||||||||||||
| 4 com/cocoyes/zhizhi-agent-runtime/observe | |||||||||||||||||||||||
| 5 com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat | 1 | 17 | |||||||||||||||||||||
| 6 com/cocoyes/zhizhi-agent-runtime/checkpoint | 2 | 1 | |||||||||||||||||||||
| 7 com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput | 2 | ||||||||||||||||||||||
| 8 com/cocoyes/zhizhi-agent-runtime/plan | 13 | ||||||||||||||||||||||
| 9 com/cocoyes/zhizhi-agent-runtime/route | 5 | ||||||||||||||||||||||
| 10 com/cocoyes/zhizhi-agent-runtime/tool | 5 | 3 | |||||||||||||||||||||
| 11 com/cocoyes/zhizhi-agent-runtime/internal/runtime/react | 2 | 7 | 1 | ||||||||||||||||||||
| 12 com/cocoyes/zhizhi-agent-runtime/mcp | 3 | 13 | |||||||||||||||||||||
| 13 com/cocoyes/zhizhi-agent-runtime/middleware | 8 | 8 | |||||||||||||||||||||
| 14 com/cocoyes/zhizhi-agent-runtime/policy | 3 | ||||||||||||||||||||||
| 15 com/cocoyes/zhizhi-agent-runtime/skill | 1 | ||||||||||||||||||||||
| 16 com/cocoyes/zhizhi-agent-runtime/speech | 1 | ||||||||||||||||||||||
| 17 com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao | 18 | ||||||||||||||||||||||
| 18 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec | 2 | 1 | 9 | 4 | 3 | 1 | |||||||||||||||||
| 19 com/cocoyes/zhizhi-agent-runtime/skill/script | 2 | ||||||||||||||||||||||
| 20 com/cocoyes/zhizhi-agent-runtime | 15 | 1 | 32 | 5 | 3 | 8 | 2 | 21 | 2 | 7 | 20 | 2 | 8 | 5 | 3 | ||||||||
| 21 com/cocoyes/zhizhi-agent-runtime/skill/script/docker | 2 | 7 | |||||||||||||||||||||
| 22 com/cocoyes/zhizhi-agent-runtime/adapter/otel | 2 | 1 | 2 | 6 | 1 | ||||||||||||||||||
| 23 com/cocoyes/zhizhi-agent-runtime/eval | 3 |
5→1 com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Error→github.com/cocoyes/zhizhi-agent-runtime/contract.ErrorClass
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses a module listed above it, which is the healthy direction.
5→3 com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 17 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Client→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Client→github.com/cocoyes/zhizhi-agent-runtime/model.ModelCapabilitiesgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Client→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Client→github.com/cocoyes/zhizhi-agent-runtime/model.ModelOutputgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Client→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.Config→github.com/cocoyes/zhizhi-agent-runtime/model.ModelCapabilitiesgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.chatRequest→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.chatResponse→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.openaicompat→github.com/cocoyes/zhizhi-agent-runtime/model.Messagegithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.openaicompat→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.openaicompat→github.com/cocoyes/zhizhi-agent-runtime/model.ToolChoicegithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.stream→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.stream→github.com/cocoyes/zhizhi-agent-runtime/model.StreamEventgithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.stream→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallDeltagithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.streamChunk→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.wireMessage→github.com/cocoyes/zhizhi-agent-runtime/model.Rolegithub.com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat.wireMessage→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallRequest
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/model/openaicompat uses a module listed above it, which is the healthy direction.
6→1 com/cocoyes/zhizhi-agent-runtime/checkpoint uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/checkpoint uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/checkpoint.Checkpoint→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/checkpoint.Checkpoint→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidence
- Direction
- com/cocoyes/zhizhi-agent-runtime/checkpoint uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime/checkpoint, while a change to com/cocoyes/zhizhi-agent-runtime/checkpoint can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/checkpoint uses a module listed above it, which is the healthy direction.
6→3 com/cocoyes/zhizhi-agent-runtime/checkpoint uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/checkpoint uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/checkpoint.Checkpoint→github.com/cocoyes/zhizhi-agent-runtime/model.Message
- Direction
- com/cocoyes/zhizhi-agent-runtime/checkpoint uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/checkpoint, while a change to com/cocoyes/zhizhi-agent-runtime/checkpoint can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/checkpoint uses a module listed above it, which is the healthy direction.
7→3 com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput.structuredoutput→github.com/cocoyes/zhizhi-agent-runtime/model.ModelOutputgithub.com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput.structuredoutput→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput, while a change to com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/structuredoutput uses a module listed above it, which is the healthy direction.
8→3 com/cocoyes/zhizhi-agent-runtime/plan uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 13 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/plan uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/plan.BudgetConflictFix→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.FixRule→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.Input→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.ModelPlanner→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/plan.ModelPlanner→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.ModelReplanner→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/plan.Planner→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.RuleFixer→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.SchemalessBindingFix→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/plan.plan→github.com/cocoyes/zhizhi-agent-runtime/model.Messagegithub.com/cocoyes/zhizhi-agent-runtime/plan.plan→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/plan.plan→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/plan.plan→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/plan uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/plan, while a change to com/cocoyes/zhizhi-agent-runtime/plan can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/plan uses a module listed above it, which is the healthy direction.
9→3 com/cocoyes/zhizhi-agent-runtime/route uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 5 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/route uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/route.DefaultRouter→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/route.ModelRouter→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/route.ModelRouter→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/route.Router→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/route.route→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/route uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/route, while a change to com/cocoyes/zhizhi-agent-runtime/route can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/route uses a module listed above it, which is the healthy direction.
10→1 com/cocoyes/zhizhi-agent-runtime/tool uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 5 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/tool uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/tool.CompositeResult→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/tool.CompositeResult→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime/tool.Result→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/tool.tool→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/tool.tool→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidence
- Direction
- com/cocoyes/zhizhi-agent-runtime/tool uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime/tool, while a change to com/cocoyes/zhizhi-agent-runtime/tool can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/tool uses a module listed above it, which is the healthy direction.
10→3 com/cocoyes/zhizhi-agent-runtime/tool uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/tool uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/tool.Registry→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/tool.Tool→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/tool.funcTool→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/tool uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/tool, while a change to com/cocoyes/zhizhi-agent-runtime/tool can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/tool uses a module listed above it, which is the healthy direction.
11→1 com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Result→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Result→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidence
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/react, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/react can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a module listed above it, which is the healthy direction.
11→3 com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 7 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuation→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuation→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallRequestgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Result→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Runner→github.com/cocoyes/zhizhi-agent-runtime/model.Messagegithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Runner→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Runner→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.react→github.com/cocoyes/zhizhi-agent-runtime/model.Usage
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/react, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/react can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a module listed above it, which is the healthy direction.
11→10 com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Runner→github.com/cocoyes/zhizhi-agent-runtime/tool.Registry
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/react, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/react can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/react uses a module listed above it, which is the healthy direction.
12→3 com/cocoyes/zhizhi-agent-runtime/mcp uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/mcp uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/mcp.CapabilityProvider→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/mcp.Selection→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime/mcp.remoteTool→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/mcp uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/mcp, while a change to com/cocoyes/zhizhi-agent-runtime/mcp can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/mcp uses a module listed above it, which is the healthy direction.
12→10 com/cocoyes/zhizhi-agent-runtime/mcp uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 13 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/mcp uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/mcp.Catalog→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/mcp.Provider→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime/mcp.Provider→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/mcp.Selection→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/mcp.ToolPolicy→github.com/cocoyes/zhizhi-agent-runtime/tool.ConfirmationPolicygithub.com/cocoyes/zhizhi-agent-runtime/mcp.ToolPolicy→github.com/cocoyes/zhizhi-agent-runtime/tool.Idempotencygithub.com/cocoyes/zhizhi-agent-runtime/mcp.ToolPolicy→github.com/cocoyes/zhizhi-agent-runtime/tool.RiskLevelgithub.com/cocoyes/zhizhi-agent-runtime/mcp.ToolPolicy→github.com/cocoyes/zhizhi-agent-runtime/tool.SideEffectClassgithub.com/cocoyes/zhizhi-agent-runtime/mcp.mcp→github.com/cocoyes/zhizhi-agent-runtime/tool.Specgithub.com/cocoyes/zhizhi-agent-runtime/mcp.mcp→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/mcp.remoteTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime/mcp.remoteTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Specgithub.com/cocoyes/zhizhi-agent-runtime/mcp.remoteTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Tool
- Direction
- com/cocoyes/zhizhi-agent-runtime/mcp uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/mcp, while a change to com/cocoyes/zhizhi-agent-runtime/mcp can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/mcp uses a module listed above it, which is the healthy direction.
13→3 com/cocoyes/zhizhi-agent-runtime/middleware uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 8 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/middleware uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/middleware.PlannerInput→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpecgithub.com/cocoyes/zhizhi-agent-runtime/middleware.middleware→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedModel→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedModel→github.com/cocoyes/zhizhi-agent-runtime/model.ModelCapabilitiesgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedModel→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedModel→github.com/cocoyes/zhizhi-agent-runtime/model.ModelOutputgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedModel→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/middleware uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/middleware, while a change to com/cocoyes/zhizhi-agent-runtime/middleware can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/middleware uses a module listed above it, which is the healthy direction.
13→10 com/cocoyes/zhizhi-agent-runtime/middleware uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 8 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/middleware uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolInvocation→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/middleware.middleware→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.CollectingToolgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Specgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.StreamableToolgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime/middleware.wrappedTool→github.com/cocoyes/zhizhi-agent-runtime/tool.ToolStream
- Direction
- com/cocoyes/zhizhi-agent-runtime/middleware uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/middleware, while a change to com/cocoyes/zhizhi-agent-runtime/middleware can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/middleware uses a module listed above it, which is the healthy direction.
14→10 com/cocoyes/zhizhi-agent-runtime/policy uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/policy uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/policy.Observation→github.com/cocoyes/zhizhi-agent-runtime/tool.Specgithub.com/cocoyes/zhizhi-agent-runtime/policy.Result→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime/policy.Runner→github.com/cocoyes/zhizhi-agent-runtime/tool.Tool
- Direction
- com/cocoyes/zhizhi-agent-runtime/policy uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/policy, while a change to com/cocoyes/zhizhi-agent-runtime/policy can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/policy uses a module listed above it, which is the healthy direction.
15→10 com/cocoyes/zhizhi-agent-runtime/skill uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/skill uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/skill.Executor→github.com/cocoyes/zhizhi-agent-runtime/tool.Result
- Direction
- com/cocoyes/zhizhi-agent-runtime/skill uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/skill, while a change to com/cocoyes/zhizhi-agent-runtime/skill can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/skill uses a module listed above it, which is the healthy direction.
16→10 com/cocoyes/zhizhi-agent-runtime/speech uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/speech uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/speech.speech→github.com/cocoyes/zhizhi-agent-runtime/tool.Registry
- Direction
- com/cocoyes/zhizhi-agent-runtime/speech uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/speech, while a change to com/cocoyes/zhizhi-agent-runtime/speech can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/speech uses a module listed above it, which is the healthy direction.
17→16 com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao uses com/cocoyes/zhizhi-agent-runtime/speech✕
- Connections
- 18 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao uses a type in com/cocoyes/zhizhi-agent-runtime/speech.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.Client→github.com/cocoyes/zhizhi-agent-runtime/speech.Clientgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.Client→github.com/cocoyes/zhizhi-agent-runtime/speech.Sessiongithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.Client→github.com/cocoyes/zhizhi-agent-runtime/speech.SessionConfiggithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.doubao→github.com/cocoyes/zhizhi-agent-runtime/speech.Eventgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.doubao→github.com/cocoyes/zhizhi-agent-runtime/speech.SessionConfiggithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.itemsEvent→github.com/cocoyes/zhizhi-agent-runtime/speech.ConversationItemgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.ConversationItemgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.Eventgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.FunctionCallgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.FunctionOutputgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.Sessiongithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.SessionConfiggithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.session→github.com/cocoyes/zhizhi-agent-runtime/speech.ToolExecutorgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.wireEvent→github.com/cocoyes/zhizhi-agent-runtime/speech.ConversationItemgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.wireEvent→github.com/cocoyes/zhizhi-agent-runtime/speech.FunctionCallgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.wireEvent→github.com/cocoyes/zhizhi-agent-runtime/speech.ProviderErrorgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.wireItem→github.com/cocoyes/zhizhi-agent-runtime/speech.Contentgithub.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.wireSession→github.com/cocoyes/zhizhi-agent-runtime/speech.AudioConfig
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao uses com/cocoyes/zhizhi-agent-runtime/speech, so a change to com/cocoyes/zhizhi-agent-runtime/speech can break com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao can't break com/cocoyes/zhizhi-agent-runtime/speech.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao uses a module listed above it, which is the healthy direction.
18→1 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.AgenticResult→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResult→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceipt
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
18→3 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Request→github.com/cocoyes/zhizhi-agent-runtime/model.ToolSpec
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
18→8 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/plan✕
- Connections
- 9 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/plan.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.Conditiongithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.InputBindinggithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.StepImportancegithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.StepKindgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.StepModegithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/plan.ToolCallBudgetgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.exec→github.com/cocoyes/zhizhi-agent-runtime/plan.Conditiongithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.exec→github.com/cocoyes/zhizhi-agent-runtime/plan.InputBindinggithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.exec→github.com/cocoyes/zhizhi-agent-runtime/plan.Plan
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/plan, so a change to com/cocoyes/zhizhi-agent-runtime/plan can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/plan.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
18→10 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 4 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.AgenticResult→github.com/cocoyes/zhizhi-agent-runtime/tool.CompositeResultgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Barrier→github.com/cocoyes/zhizhi-agent-runtime/tool.Specgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Scheduler→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResult→github.com/cocoyes/zhizhi-agent-runtime/tool.CompositeResult
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
18→11 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/react✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.AgenticResult→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuationgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Step→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuationgithub.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResult→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuation
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/react, so a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/react can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
18→14 com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/policy✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a type in com/cocoyes/zhizhi-agent-runtime/policy.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.Scheduler→github.com/cocoyes/zhizhi-agent-runtime/policy.Runner
- Direction
- com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses com/cocoyes/zhizhi-agent-runtime/policy, so a change to com/cocoyes/zhizhi-agent-runtime/policy can break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, while a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can't break com/cocoyes/zhizhi-agent-runtime/policy.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec uses a module listed above it, which is the healthy direction.
19→15 com/cocoyes/zhizhi-agent-runtime/skill/script uses com/cocoyes/zhizhi-agent-runtime/skill✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/skill/script uses a type in com/cocoyes/zhizhi-agent-runtime/skill.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/skill/script.Approval→github.com/cocoyes/zhizhi-agent-runtime/skill.Metadatagithub.com/cocoyes/zhizhi-agent-runtime/skill/script.script→github.com/cocoyes/zhizhi-agent-runtime/skill.Catalog
- Direction
- com/cocoyes/zhizhi-agent-runtime/skill/script uses com/cocoyes/zhizhi-agent-runtime/skill, so a change to com/cocoyes/zhizhi-agent-runtime/skill can break com/cocoyes/zhizhi-agent-runtime/skill/script, while a change to com/cocoyes/zhizhi-agent-runtime/skill/script can't break com/cocoyes/zhizhi-agent-runtime/skill.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/skill/script uses a module listed above it, which is the healthy direction.
20→1 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/contract✕
- Connections
- 15 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/contract.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/contract.RunOutcomegithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/contract.RunStatsgithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/contract.Warninggithub.com/cocoyes/zhizhi-agent-runtime.checkpointStepResult→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime.simpleResumeState→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.simpleResumeState→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime.skillInvokeOutput→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.skillInvokeOutput→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/contract.ActionReceiptgithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/contract.Evidencegithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/contract.RunOutcome
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/contract, so a change to com/cocoyes/zhizhi-agent-runtime/contract can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/contract.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→2 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/budget✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/internal/budget.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/internal/budget.Ledger
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/budget, so a change to com/cocoyes/zhizhi-agent-runtime/internal/budget can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/internal/budget.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→3 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 32 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/model. Showing 25 of them; the rest are in namespace-graph.json in this report's bundle.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.Event→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallDeltagithub.com/cocoyes/zhizhi-agent-runtime.Request→github.com/cocoyes/zhizhi-agent-runtime/model.Messagegithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/model.FinishReasongithub.com/cocoyes/zhizhi-agent-runtime.Response→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime.complexResumeState→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.FinishReasongithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallRequestgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.ModelCapabilitiesgithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInputgithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.ModelOutputgithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime.modelCounter→github.com/cocoyes/zhizhi-agent-runtime/model.Usagegithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/model.ResponseFormatgithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/model.ToolChoicegithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/model.Messagegithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/model.Modelgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/model.ToolCallRequestgithub.com/cocoyes/zhizhi-agent-runtime.simpleResumeState→github.com/cocoyes/zhizhi-agent-runtime/model.ModelInput
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→4 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/observe✕
- Connections
- 5 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/observe.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/observe.Observergithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/observe.Observergithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/observe.Eventgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/observe.Observergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/observe.Observer
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/observe, so a change to com/cocoyes/zhizhi-agent-runtime/observe can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/observe.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→6 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/checkpoint✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/checkpoint.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/checkpoint.Storegithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/checkpoint.Checkpointgithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/checkpoint.Store
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/checkpoint, so a change to com/cocoyes/zhizhi-agent-runtime/checkpoint can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/checkpoint.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→8 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/plan✕
- Connections
- 8 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/plan.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.complexResumeState→github.com/cocoyes/zhizhi-agent-runtime/plan.Plangithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/plan.Plannergithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/plan.Replannergithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/plan.Plangithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/plan.Plangithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/plan.Plannergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/plan.Replannergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/plan.Step
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/plan, so a change to com/cocoyes/zhizhi-agent-runtime/plan can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/plan.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→9 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/route✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/route.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/route.Routergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/route.Router
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/route, so a change to com/cocoyes/zhizhi-agent-runtime/route can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/route.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→10 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 21 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.SkillOptions→github.com/cocoyes/zhizhi-agent-runtime/tool.ConfirmationPolicygithub.com/cocoyes/zhizhi-agent-runtime.checkpointStepResult→github.com/cocoyes/zhizhi-agent-runtime/tool.CompositeResultgithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/tool.Brokergithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.eventStream→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/tool.Brokergithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.skillExecutor→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.skillInvokeTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.skillInvokeTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.skillScriptTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.skillScriptTool→github.com/cocoyes/zhizhi-agent-runtime/tool.Toolgithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/tool.Registrygithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/tool.Resultgithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/tool.Tool
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→11 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/react✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.checkpointStepResult→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuationgithub.com/cocoyes/zhizhi-agent-runtime.skillInvocation→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.Continuation
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/react, so a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/react can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/internal/runtime/react.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→12 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/mcp✕
- Connections
- 7 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/mcp.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.FileMCPServer→github.com/cocoyes/zhizhi-agent-runtime/mcp.ConnectionStrategygithub.com/cocoyes/zhizhi-agent-runtime.FileMCPServer→github.com/cocoyes/zhizhi-agent-runtime/mcp.ToolPolicygithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/mcp.CapabilityProvidergithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/mcp.Configgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/mcp.Providergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/mcp.CapabilityProvidergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/mcp.Config
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/mcp, so a change to com/cocoyes/zhizhi-agent-runtime/mcp can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/mcp.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→13 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/middleware✕
- Connections
- 20 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/middleware.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.PlannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.ReplannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.PlannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.ReplannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.runConfig→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelStreamMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.PlannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.ReplannerMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolMiddlewaregithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolStreamMiddleware
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/middleware, so a change to com/cocoyes/zhizhi-agent-runtime/middleware can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/middleware.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→14 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/policy✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/policy.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.config→github.com/cocoyes/zhizhi-agent-runtime/policy.Runnergithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/policy.Runner
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/policy, so a change to com/cocoyes/zhizhi-agent-runtime/policy can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/policy.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→15 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/skill✕
- Connections
- 8 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/skill.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.SkillOptions→github.com/cocoyes/zhizhi-agent-runtime/skill.Searchergithub.com/cocoyes/zhizhi-agent-runtime.skillConfig→github.com/cocoyes/zhizhi-agent-runtime/skill.Cataloggithub.com/cocoyes/zhizhi-agent-runtime.skillExecutor→github.com/cocoyes/zhizhi-agent-runtime/skill.Loadedgithub.com/cocoyes/zhizhi-agent-runtime.skillGrant→github.com/cocoyes/zhizhi-agent-runtime/skill.Candidategithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/skill.Loadedgithub.com/cocoyes/zhizhi-agent-runtime.skillScriptTool→github.com/cocoyes/zhizhi-agent-runtime/skill.Loadedgithub.com/cocoyes/zhizhi-agent-runtime.skillSearchOutput→github.com/cocoyes/zhizhi-agent-runtime/skill.Candidategithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/skill.Catalog
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/skill, so a change to com/cocoyes/zhizhi-agent-runtime/skill can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/skill.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→18 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec✕
- Connections
- 5 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.completedStep→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResultgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.AgenticExecutorgithub.com/cocoyes/zhizhi-agent-runtime.runtime→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResultgithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.ExecutionPlangithub.com/cocoyes/zhizhi-agent-runtime.zhizhi→github.com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.StepResult
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec, so a change to com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/internal/runtime/exec.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
20→19 com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/skill/script✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime uses a type in com/cocoyes/zhizhi-agent-runtime/skill/script.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime.SkillOptions→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Executorgithub.com/cocoyes/zhizhi-agent-runtime.skillScope→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Workspacegithub.com/cocoyes/zhizhi-agent-runtime.skillScopeState→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Workspace
- Direction
- com/cocoyes/zhizhi-agent-runtime uses com/cocoyes/zhizhi-agent-runtime/skill/script, so a change to com/cocoyes/zhizhi-agent-runtime/skill/script can break com/cocoyes/zhizhi-agent-runtime, while a change to com/cocoyes/zhizhi-agent-runtime can't break com/cocoyes/zhizhi-agent-runtime/skill/script.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime uses a module listed above it, which is the healthy direction.
21→15 com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses com/cocoyes/zhizhi-agent-runtime/skill✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses a type in com/cocoyes/zhizhi-agent-runtime/skill.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Config→github.com/cocoyes/zhizhi-agent-runtime/skill.Cataloggithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill.Catalog
- Direction
- com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses com/cocoyes/zhizhi-agent-runtime/skill, so a change to com/cocoyes/zhizhi-agent-runtime/skill can break com/cocoyes/zhizhi-agent-runtime/skill/script/docker, while a change to com/cocoyes/zhizhi-agent-runtime/skill/script/docker can't break com/cocoyes/zhizhi-agent-runtime/skill.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses a module listed above it, which is the healthy direction.
21→19 com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses com/cocoyes/zhizhi-agent-runtime/skill/script✕
- Connections
- 7 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses a type in com/cocoyes/zhizhi-agent-runtime/skill/script.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Config→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Registrationgithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Approvalgithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Executorgithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Filegithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Requestgithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Resultgithub.com/cocoyes/zhizhi-agent-runtime/skill/script/docker.Executor→github.com/cocoyes/zhizhi-agent-runtime/skill/script.Workspace
- Direction
- com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses com/cocoyes/zhizhi-agent-runtime/skill/script, so a change to com/cocoyes/zhizhi-agent-runtime/skill/script can break com/cocoyes/zhizhi-agent-runtime/skill/script/docker, while a change to com/cocoyes/zhizhi-agent-runtime/skill/script/docker can't break com/cocoyes/zhizhi-agent-runtime/skill/script.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/skill/script/docker uses a module listed above it, which is the healthy direction.
22→3 com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/model✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a type in com/cocoyes/zhizhi-agent-runtime/model.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/otel.modelStream→github.com/cocoyes/zhizhi-agent-runtime/model.Streamgithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.modelStream→github.com/cocoyes/zhizhi-agent-runtime/model.StreamEvent
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/model, so a change to com/cocoyes/zhizhi-agent-runtime/model can break com/cocoyes/zhizhi-agent-runtime/adapter/otel, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/otel can't break com/cocoyes/zhizhi-agent-runtime/model.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a module listed above it, which is the healthy direction.
22→4 com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/observe✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a type in com/cocoyes/zhizhi-agent-runtime/observe.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/observe.Observer
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/observe, so a change to com/cocoyes/zhizhi-agent-runtime/observe can break com/cocoyes/zhizhi-agent-runtime/adapter/otel, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/otel can't break com/cocoyes/zhizhi-agent-runtime/observe.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a module listed above it, which is the healthy direction.
22→10 com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/tool✕
- Connections
- 2 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a type in com/cocoyes/zhizhi-agent-runtime/tool.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/otel.toolStream→github.com/cocoyes/zhizhi-agent-runtime/tool.StreamEventgithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.toolStream→github.com/cocoyes/zhizhi-agent-runtime/tool.ToolStream
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/tool, so a change to com/cocoyes/zhizhi-agent-runtime/tool can break com/cocoyes/zhizhi-agent-runtime/adapter/otel, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/otel can't break com/cocoyes/zhizhi-agent-runtime/tool.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a module listed above it, which is the healthy direction.
22→13 com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/middleware✕
- Connections
- 6 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a type in com/cocoyes/zhizhi-agent-runtime/middleware.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelHandlergithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.ModelStreamHandlergithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.PlannerHandlergithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.ReplannerHandlergithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolHandlergithub.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime/middleware.ToolStreamHandler
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime/middleware, so a change to com/cocoyes/zhizhi-agent-runtime/middleware can break com/cocoyes/zhizhi-agent-runtime/adapter/otel, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/otel can't break com/cocoyes/zhizhi-agent-runtime/middleware.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a module listed above it, which is the healthy direction.
22→20 com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime✕
- Connections
- 1 pair of types, where a type in com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a type in com/cocoyes/zhizhi-agent-runtime.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/adapter/otel.Instrumentation→github.com/cocoyes/zhizhi-agent-runtime.AgentHandler
- Direction
- com/cocoyes/zhizhi-agent-runtime/adapter/otel uses com/cocoyes/zhizhi-agent-runtime, so a change to com/cocoyes/zhizhi-agent-runtime can break com/cocoyes/zhizhi-agent-runtime/adapter/otel, while a change to com/cocoyes/zhizhi-agent-runtime/adapter/otel can't break com/cocoyes/zhizhi-agent-runtime.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/adapter/otel uses a module listed above it, which is the healthy direction.
23→20 com/cocoyes/zhizhi-agent-runtime/eval uses com/cocoyes/zhizhi-agent-runtime✕
- Connections
- 3 pairs of types, where a type in com/cocoyes/zhizhi-agent-runtime/eval uses a type in com/cocoyes/zhizhi-agent-runtime.
- The types involved
github.com/cocoyes/zhizhi-agent-runtime/eval.Result→github.com/cocoyes/zhizhi-agent-runtime.Responsegithub.com/cocoyes/zhizhi-agent-runtime/eval.Scenario→github.com/cocoyes/zhizhi-agent-runtime.RunModegithub.com/cocoyes/zhizhi-agent-runtime/eval.eval→github.com/cocoyes/zhizhi-agent-runtime.Agent
- Direction
- com/cocoyes/zhizhi-agent-runtime/eval uses com/cocoyes/zhizhi-agent-runtime, so a change to com/cocoyes/zhizhi-agent-runtime can break com/cocoyes/zhizhi-agent-runtime/eval, while a change to com/cocoyes/zhizhi-agent-runtime/eval can't break com/cocoyes/zhizhi-agent-runtime.
- Position
- Below the diagonal: com/cocoyes/zhizhi-agent-runtime/eval uses a module listed above it, which is the healthy direction.
At a glance — Code Health
At a glance — Architecture
At a glance — Maturity
At a glance — Readiness
At a glance — Security
Security & Compliance — OWASP Top-10 mapping
| OWASP category | Findings | Severity |
|---|---|---|
| A05:2025 — Injection | 6 | High / Critical |
| A03:2025 — Software Supply Chain Failures | 5 | High / Critical |
| A02:2025 — Security Misconfiguration | 1 | Medium |
Roadmap
Top priorities: Add a SAST step to CI running what this repository's stack ships: gosec / govulncheck (or golangci-lint) — or `semgrep --config=auto`, which runs on any language — so a security regression fails the build instead of landing; Record your significant design decisions. Write one short document per decision, giving its date, the situation, the decision and its consequences, and keep them together with your other design documents. A docs/adr folder with each file named by number and title is the easiest place to find them; Resolve the 1 Flaky test finding(s) in Test Reliability.
| Do this | Helps | Effort | Dimension |
|---|---|---|---|
| Resolve the 1 Flaky test finding(s) in Test Reliability. | +3.4 pts | Low | Test Reliability |
| Add a SAST step to CI running what this repository's stack ships: gosec / govulncheck (or golangci-lint) — or `semgrep --config=auto`, which runs on any language — so a security regression fails the build instead of landing. | +6.2 pts | Medium | Security & performance tooling |
| Record your significant design decisions. Write one short document per decision, giving its date, the situation, the decision and its consequences, and keep them together with your other design documents. A docs/adr folder with each file named by number and title is the easiest place to find them. | +4.8 pts | Medium | Architecture documentation |
| Nothing pauses a release for a human: publish as a draft release (or gate the release job on a protected tag/manual dispatch) so a bad build can be stopped before users can download it. | +3.3 pts | Medium | Deployment & Rollback |
| Resolve the 9 Hotspot finding(s) in Churn × Complexity Hotspots — start with agent.go, scheduler.go, react.go. | +3.3 pts | High | Churn × Complexity Hotspots |
| Bring the 58 bodies over 15 down to 15 or less in Cognitive Complexity — start with Scheduler.Run (cognitive 172), runtime.runComplex (cognitive 133), Runner.RunInput (cognitive 110). | +2.1 pts | High | Cognitive Complexity |
| Explain in the README how to run the tests. Add a section called Testing to the README in the repository's top folder, saying how to run the test suite. | +1.9 pts | Medium | Documentation (README) |
| Resolve the 1 REDACTED finding(s) in Vulnerability-disclosure Policy — start with REDACTED. | +0.6 pts | Low | Vulnerability-disclosure Policy |
File quality
| File | Score | Band | Worst signal |
|---|---|---|---|
| REDACTED | 3.3 | Slop | Dependency Vulnerabilities: High CVE: REDACTED |
| REDACTED | 4.8 | Mixed | Static Analysis (SAST): High: REDACTED |
| examples/14-skills/main.go | 5.9 | Mixed | Code Duplication: Edited copy of a member (7 corresponding lines) |
| route/router.go | 6.3 | Mixed | Cognitive Complexity: ModelRouter.Route (cognitive 29) |
| REDACTED | 6.4 | Mixed | Static Analysis (SAST): Medium: REDACTED |
| REDACTED | 6.4 | Mixed | Static Analysis (SAST): Medium: REDACTED |
| agent.go | 7.0 | Mixed | Cyclomatic Complexity: runtime.runComplex (cyclomatic 79) |
| policy/decision.go | 7.0 | Mixed | Cyclomatic Complexity: DecisionEngine.Decide (cyclomatic 16) |
| adapter/otel/otel.go | 7.0 | Mixed | Code Duplication: Edited copy of a member (8 corresponding lines) |
| internal/runtime/exec/resolve.go | 7.0 | Mixed | Code Duplication: Edited copy of a member (11 corresponding lines) |
| examples/00-chat/main.go | 7.0 | Mixed | Code Duplication: Edited copy of a member (15 corresponding lines) |
| examples/10-full-agent/main.go | 7.0 | Mixed | Code Duplication: Duplicated block (12 lines × 2) |
| adapter/model/openaicompat/openaicompat.go | 7.0 | Mixed | Cyclomatic Complexity: Client.request (cyclomatic 23) |
| skill.go | 7.0 | Mixed | Cyclomatic Complexity: skillExecutor.Execute (cyclomatic 20) |
| skill/script/docker/config.go | 7.1 | Mixed | Cyclomatic Complexity: docker.New (cyclomatic 63) |
| plan/output.go | 7.1 | Mixed | Cyclomatic Complexity: plan.generateCandidate (cyclomatic 22) |
| internal/runtime/exec/scheduler.go | 7.2 | Mixed | Cyclomatic Complexity: Scheduler.Run (cyclomatic 71) |
| plan/plan.go | 7.2 | Mixed | Cyclomatic Complexity: Plan.Validate (cyclomatic 41) |
| skill/catalog.go | 7.2 | Mixed | Cyclomatic Complexity: Catalog.LoadRoot (cyclomatic 32) |
| recovery.go | 7.2 | Mixed | Cyclomatic Complexity: runtime.initialRecovery (cyclomatic 28) |
How the grades work
A definite problem that already costs you something and drags the score down: a missing authorisation check, a dependency with a known exploit, a build that does not reproduce. Failure here tends to cause failures elsewhere.
Likely wrong, but not failing yet. It degrades the codebase over a longer horizon and can cause failures elsewhere — not urgent this week, not something to carry for two years either.
Recorded, with no effect on how the codebase functions. Present so the survey is complete, not because it needs doing.
Something this survey could not settle from the outside, and which could be critical or serious. Either a control was required and no positive evidence of it exists in the repository — a backup job that nothing shows was ever restored from proves nothing about restores — or our own analysis could not run over that part of the tree. This is not a clean result. These are excluded from the score rather than awarded a pass, so the number on the cover neither rewards nor penalises them: if you act on this survey without resolving them, you carry that risk yourself. Each one is named under Limitations.
Methodology & how to trust this report
This survey is a deep, periodic assessment — run each sprint, monthly, or quarterly, taking the time to go wider and deeper than a quick check and surfacing in one coherent report what you'd otherwise piece together from a dozen separate tools. It scores deterministically: the same commit yields the same score, every run. All 42 evaluated dimensions are computed by tools and static analysis; no language model sets or judges any of them. Overall confidence is 0.9, the weighted average across measured dimensions.
What we checked — 42 dimensions across the health lenses
- Can you open the finding? Real findings cite a repo-relative file and line you can open at the cited line — never an absolute scratch path. Here, 213 of 224 do; the remainder are repo-wide signals — a dimension-level measurement, not a single line.
- Is there a tool behind the number? Every score below names the method that produced it: Roslyn, git or a scanner, not a narrative.
- Does re-running give the same result? Run it again on the same commit and the score — and this report, byte for byte — is identical. A report whose numbers move between runs is describing the run, not the code.
Tools & methods
| Method | Backs | Version | Evaluator |
|---|---|---|---|
| Roslyn static analysis | Complexity, cohesion, coupling, dead code, API surface, layering | 5.3.0 | ✓ deterministic |
| Native secret scanner | Hardcoded secrets / credentials | 1.0.0 | ✓ deterministic |
| Canine Code Analyzer duplication detector (in-process) | Code duplication | 1.0.0 | ✓ deterministic |
| Coverage (coverlet / dotnet-coverage) | Line & branch coverage | 10.0.400 | ✓ deterministic |
| NuGet / dotnet | Outdated, vulnerable & deprecated dependencies | 10.0.400 | ✓ deterministic |
| git / LibGit2Sharp | Churn hotspots, knowledge concentration, history | 2.43.0 · 0.31.0 | ✓ deterministic |
| gitleaks · semgrep · trivy · checkov | Secrets in history, SAST, CVEs, IaC & container, PII / GDPR | 1.86.0 · 0.69.3 · 3.2.533 | ✓ deterministic |
Run transparency — what happened this run
- D15 Churn × Complexity Hotspots — measured, with a gap in what it reached — This is a true statement about the repository that carries nothing for its owner to act on, so it is reported here rather than as a defect in their code. Git history depth insufficient — this repository has 29 commit(s), too few for a reliable trend signal. The clone is complete, so there is no deeper history to fetch: the signal returns as the project accumulates history.
- D16 Bus Factor — not measured this run — This is a true statement about the repository that carries nothing for its owner to act on, so it is reported here rather than as a defect in their code. Too few commits for a meaningful bus factor (29 commit(s) sampled, fewer than the 50 this dimension needs before a bus factor means anything).
- D19 Documentation Quality — measured, with a gap in what it reached — We measured this, but not all of it. What we did not reach is a gap on our side — a collector, parser or image we have not built yet — so the numbers on that dimension cover less than the repository, and the part left out is not evidence that it would have passed. This kind did not reach the 95 % precision gate in three adjudicated runs (docs/plans/deterministic-engine/adjudication/D19-sample3-v3.md), so by the pre-registered fallback it publishes no row until a re-measurement shows it does. The candidates are counted here, not reported as findings, and the score does not include them.
- D24 Comment Value — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check's reader does not cover the language this repository's product is written in, so it had nothing of the product to read. That is a gap in this analyzer's language reach — not a finding about this repository.
- D26 Project Cohesion — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. `(repository root)` (12988 LoC, 264 module-visible types across 39 directories) is over its size bounds, and whether one unit is a coherent whole or a grab-bag is read from its type references: the parts of it that reach the rest only through its shared core. Those are read over the C#/VB code model, which this unit's source did not supply. Its size alone is no verdict on its cohesion, so none is published.
- D34 Knowledge Freshness — not measured this run — This is a true statement about the repository that carries nothing for its owner to act on, so it is reported here rather than as a defect in their code. Too few commits to judge knowledge freshness (29 commit(s) sampled).
- D35 Change Coupling — measured, with a gap in what it reached — This is a true statement about the repository that carries nothing for its owner to act on, so it is reported here rather than as a defect in their code. Git history depth insufficient — this repository has 29 commit(s), too few for a reliable change-coupling signal. The clone is complete, so there is no deeper history to fetch: the signal returns as the project accumulates history.
- AXR1 Runtime accessibility — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. Render strategy: boot via Dockerfile (examples/15-docker-skills/Dockerfile). the image ran but published no HTTP port — nothing to crawl (EXPOSE the web port to unlock runtime evidence).
- C1 Data Protection — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These personal data controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks personal data controls.
- C2 Access Controls — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These authorization controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks authorization controls.
- C3 Audit Trail — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These audit controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks audit controls.
- C4 Data Retention — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These retention controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks retention controls.
- C5 Data-Subject Rights — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These data-subject rights controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks data-subject rights controls.
- GD1 Unfinished & placeholder code — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, F#, JavaScript/TypeScript, Dart, Ruby, Scala, Rust and Java source only, and no C#, F#, JavaScript/TypeScript, Dart, Ruby, Scala, Rust or Java was found, and this repository's Go is not read yet, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- IC1 Incompleteness & stubs — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, JavaScript/TypeScript, Java, Dart, Ruby, Scala and Rust source only, and no C#, JavaScript/TypeScript, Java, Dart, Ruby, Scala or Rust was found, and this repository's Go is not read yet, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- M4 Documentation accuracy — measured, with a gap in what it reached — We measured this, but not all of it. What we did not reach is a gap on our side — a collector, parser or image we have not built yet — so the numbers on that dimension cover less than the repository, and the part left out is not evidence that it would have passed. M4 checks only the claim kinds adjudicated at or above 95 % precision: links and versions (PREREGISTRATION version 9), and artefact counts an order of magnitude off. Paths, command arguments, installs, environment variables, settings, projects, packages, routes, cd targets, infrastructure products and removed modules are read but not checked, and none of them is reported or counted.
- P5 DR & Backup — not measured this run — This is a true statement about the repository that carries nothing for its owner to act on, so it is reported here rather than as a defect in their code. No backup/snapshot/replication config, RTO/RPO or restore-procedure documentation was found — and no production persistence was detected either (no data-access packages, no data-store services, no database resources), so there is nothing in this repository whose loss a DR control would recover. If this system's data lives in a platform or ops repo we can't see, that's where the DR evidence belongs.
- S1 Web-Security Posture — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. These web-security controls are read from declarative annotations, request middleware, entity/column names and guard methods in a C# source model, and none was loaded on this run, so there was nothing to gather. That is a gap in this analyzer's language reach — not a finding that the repository lacks web-security controls.
- X1 Async correctness — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Python, Dart, Ruby, Scala, Rust and Kotlin source only, and no C# was loaded and no JavaScript/TypeScript, Python, Dart, Ruby, Scala, Rust or Kotlin was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X12 Unreachable branch — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Python, Dart, Ruby, Scala, Kotlin, Java and Rust source only, and no C# was loaded and no JavaScript/TypeScript, Python, Dart, Ruby, Scala, Kotlin, Java or Rust was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X13 Undrained process stream — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Python, Dart, Ruby, Scala, Kotlin, Rust and Java source only, and no C# was loaded and no JavaScript/TypeScript, Python, Dart, Ruby, Scala, Kotlin, Rust or Java was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X16 Unfloored truncation loop — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, PHP, Dart, Ruby, Scala, Kotlin and Rust source only, and no C# was loaded and no JavaScript/TypeScript, Java, PHP, Dart, Ruby, Scala, Kotlin or Rust was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X17 Uncapped recursion over a caller-supplied document — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, Python, Dart, Ruby, Scala, Kotlin and Rust source only, and no C# was loaded and no JavaScript/TypeScript, Java, Python, Dart, Ruby, Scala, Kotlin or Rust was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X18 Disposal-pattern correctness — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, Kotlin, Dart, Ruby, Scala, PHP, Rust and Elixir source only, and no C# was loaded and no JavaScript/TypeScript, Java, Kotlin, Dart, Ruby, Scala, PHP, Rust or Elixir was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X22 Contradicted release guard — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# and Visual Basic syntax, and Java, TypeScript/JavaScript, Python, Dart, Ruby, Scala, Kotlin, PHP, F#, Rust and Visual Basic source only, and no C# was loaded, and this repository's Go is not read yet, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X23 Unguarded diagnostic materialisation — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, F#, Python, Dart, Ruby, Scala, Kotlin, PHP and Rust source only, and no C# was loaded and no JavaScript/TypeScript, Java, F#, Python, Dart, Ruby, Scala, Kotlin, PHP or Rust was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X24 Document value interpolated into markup unescaped — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, Scala, Ruby and Python source only, and no C# was loaded and no JavaScript/TypeScript, Java, Scala, Ruby or Python was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X25 Inert configuration knob — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript, Java, Kotlin, Scala, PHP, Erlang, Python, Dart, Ruby and Rust source only, and no C# was loaded and no JavaScript/TypeScript, Java, Kotlin, Scala, PHP, Erlang, Python, Dart, Ruby or Rust was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
- X29 Per-element action decided by a fixed element — not measured this run — We could not measure this here. That is a gap on our side — a collector, parser or image we have not built yet — and it is neither a defect in this repository nor evidence that the check would have passed. This check reads C# syntax, and JavaScript/TypeScript (Vue and Svelte components included), Java, Rust, Dart, Ruby, Scala, Kotlin and PHP source only, and no C# was loaded and no JavaScript/TypeScript, Java, Rust, Dart, Ruby, Scala or Kotlin was found in this repository, so it had nothing of this repository's product to read. That is a gap in this analyzer's language reach — not a finding that the repository is free of what this check looks for.
Limitations & what we did not check
We assess the repository exactly as committed, and only the repository. By design we do not reach outside the source tree: the live cloud account, the running CI/CD pipeline, the host's branch-protection and approval rules, the production configuration, or a restore actually exercised against a backup are all out of scope. That boundary is a feature, not a gap — a repo-relative, deterministic scan re-runs identically on any commit and every finding opens at a real file and line, where a live audit can neither be reproduced nor traced. The visible consequence is that controls which leave no in-repo evidence are reported as "not evidenced" and excluded from the score rather than awarded a number a static scan cannot justify.
Per-dimension blind spots
- D1 Cyclomatic Complexity: Cyclomatic complexity counts branches statically — it cannot tell an essential decision tree from accidental tangle, nor see complexity that lives in data or configuration (large switch-case token tables, DSL lexers/parsers, data-as-code rule tables) rather than control flow: a tokenizer's many single-character cases read as high complexity though each branch is trivial.
- D2 Cognitive Complexity: Cognitive-complexity heuristics approximate how hard code is to follow; genuine domain difficulty and well-named intent that eases reading are not captured.
- D3 God Classes: "God class" is sized by members and responsibilities visible in the type — a deliberately broad facade over a coherent subsystem can read the same as an accidental grab-bag. For front-end JS the file-length check is cohesion-aware (a single-responsibility module — one class/IIFE — earns a 3× threshold), but cohesion is approximated from top-level declarations, not true dependency structure.
- D4 Code Duplication: Duplication is token-similarity — an in-process token-stream comparison over sliding windows, with type-aware normalization — so it finds copy-paste, not semantic duplication expressed differently. Committed machine-written code (scaffolded migrations, designer/codegen output, protobuf/OpenAPI stubs, model snapshots) is EXCLUDED — its repetition is the tool's, not the team's — so the score reflects hand-written duplication only.
- D6 Cohesion (LCOM4): LCOM4 cohesion is syntactic — it infers connectivity from which methods touch which fields/methods by name, not from real runtime behaviour or intent.
- D8 Code Coverage: Coverage is measured by building and running the test suite inside our isolated image — the target repo is never modified, and nothing on your systems runs. So coverage exists only when the suite builds and runs within the inline time budget; one that needs external services, can't build, or exceeds the budget yields no coverage (D8 then degrades to not-measured, not a low score). Line coverage also says nothing about assertion quality.
- D11 Test Reliability: Flakiness is inferred from history/markers — we run the suite once (for coverage), not the repeated runs under varied conditions that reveal nondeterminism, so a flaky test never recorded as failing is invisible here.
- D12 Dependency Hygiene: Dependency health reads manifests and lockfiles — a vulnerability in a vendored/copied dependency, or risk from how a dependency is actually used, is outside this view.
- D13 Secret Scanning: Secret detection is signature- and entropy-based on the current tree — a secret that does not match a known pattern, or one already rotated, will not be flagged (a clean scan is "nothing matched", not "no secrets exist").
- D14 License Compliance: License compatibility is checked against declared package metadata and a policy — mislabelled or missing license metadata, and obligations that depend on how you distribute, are not resolved here.
- D15 Churn × Complexity Hotspots: Churn hotspots come from git history — a freshly imported or squashed repository has no churn signal, and recent rewrites can mask a historically risky file.
- D17 Explicit Debt: Acknowledged-debt signals (TODO/FIXME, suppressions, dead code) are textual — undocumented debt that nobody marked, and debt that lives in design rather than annotations, is invisible. Committed machine-written code (scaffolded migrations, designer/codegen output, generated stubs) is excluded — it is never the team's dead code to delete.
- D19 Documentation Quality: Documentation quality publishes two things only: a runnable or packaged unit with no example, and a multi-project root README that maps none of its parts. It does not judge clarity, and its other checks (overview, licence, boilerplate, structure, empty sections, XML-doc coverage) are withheld after adjudication: their candidates are counted in the card's gaps, not shown as rows. A false statement in a document is M4's; units are .NET projects only.
- D22 Internal API Consistency: API consistency compares the call shapes of members that play the same role on the exposed C# surface: whether the API suits its callers is not measured, and surfaces in other languages are not measured.
- D27 Navigability: Indirection/navigability is structural — it measures hops to follow a call, not whether that indirection buys real flexibility or just ceremony.
- D28 Secrets (history): Secret-history scanning sweeps the git log for known patterns — a secret that predates the available history, or never matched a signature, is not found (clean means "nothing matched in the history we can see").
- D29 Static Analysis (SAST): SAST findings are pattern-based (semgrep) — it finds classes of bug it has rules for; logic flaws, auth/authorization gaps and issues needing runtime context are out of reach (and clean means "no rule matched").
- D30 Dependency Vulnerabilities: CVE matching depends on accurate package/version metadata and on the advisory databases — a vulnerability with no published advisory, or in code not declared as a dependency, is not seen. Coverage needs a RESOLVED graph: an unpinned requirements.txt, or a pom without a resolved build, yields partial coverage rather than a clean verdict. An ecosystem the analyzer cannot scan is reported as unmeasured, never as clean.
- D31 IaC & Container Security: IaC scanning checks Dockerfiles/Terraform/Kubernetes against best-practice rules — it cannot see the live cloud account, runtime configuration, or drift between the committed config and what is actually deployed.
- D35 Change Coupling: Change coupling is co-change in COMMITS — files split across separate commits, or coupled only through a shared config/build step, read as uncoupled, and a sweeping commit (rename/format) is excluded so it doesn't couple everything. It shows that files change together, not WHY: a high coupling can be a healthy cohesive pair as readily as a hidden leak.
- D43 Malicious Dependencies: Only packages some vulnerability database has already NAMED as malicious are seen — a compromise published in the last hours, or never reported at all, is invisible here, and this dimension reading 10 is not evidence that a dependency is trustworthy. There is no typosquat or dependency-confusion analysis: a package nobody has reported is simply absent from the feeds. Coverage is the dependency scan's: an ecosystem that could not be scanned is disclosed as unmeasured, never as clean.
- D44 Platform End-of-Life: The support table is FROZEN, so it goes out of date by losing RECALL: a release that ended support after the table was written is missed until the table is refreshed, and this dimension reading 10 is not evidence that a platform is current. Only platforms the repository DECLARES in a place this pass reads are seen — a runtime named only in a Dockerfile (D31's subject), in a CI workflow (D29's), or in a file this pass does not parse (REDACTED, a Gemfile ruby directive) is invisible here, which is why a repository declaring none of them abstains rather than scoring. Only frameworks with a PUBLISHED support policy are tracked: React, Flask and Express publish none, so their age cannot be judged and their absence from a report is not a statement that they are supported.
- AX10 Code composition: Role is inferred from namespace/folder convention, not semantics — a domain concept living in a folder named "Services" reads as application, and the split is lines-of-code, not business value. The business-logic-share score is a SOFT, FLOORED signal: it contributes to the Architecture lens but is floored at the Critical gate, so an infrastructure-heavy design (a gateway, an ETL, a driver) is legitimately low without being nuked to zero.
- M4 Documentation accuracy: Documentation accuracy checks links, versions and artefact counts against the tree: other claims (paths, commands, settings, routes) are read but not checked, and it cannot run the onboarding or measure how long a real new joiner takes.
- P4 Deployment & Rollback: Approval/branch-protection rules live in repository settings the scan cannot see — only their in-repo evidence (config files, workflows) is checked, so a control enforced purely in the host's settings reads as "not evidenced".
- P6 Release Hygiene: Rollback/observability controls are inferred from repo artefacts (pipelines, dashboards-as-code) — controls configured in external tooling, with no in-repo trace, cannot be credited.
Dimensions
D1 · Cyclomatic Complexity
42 function(s) exceeded the cyclomatic complexity threshold of 15; the worst was runtime.runComplex at 79. A further 1 function(s) were over the threshold but excluded as flat dispatchers (a long switch/match over independent cases: many branches, almost no nesting), the largest being zhizhi.standardizeError at 21 — they are counted neither in the figure above nor in this dimension's score. 1 file carries no cyclomatic complexity row at all for this reason — every one of its over-threshold functions was excluded, so the exclusion is disclosed nowhere in the file itself: errors.go (zhizhi.standardizeError at 21). They are named here because the per-file figures other dimensions report are taken BEFORE this exclusion, so such a file can show a high maximum complexity elsewhere in this report and nothing here, with nothing to reconcile the two.
What to do
- Bring the 3 bodies over 60 down to 60 or less in Cyclomatic Complexity — start with runtime.runComplex (cyclomatic 79), Scheduler.Run (cyclomatic 71), docker.New (cyclomatic 63). — This score is capped by its worst body, so a finding fixed alone moves it by almost nothing — the next one down takes its place. Refactoring these 3 together lifts Cyclomatic Complexity from 2.2 to about 3.2/10, projected with the scoring formula itself and assuming each lands exactly at 60; a cleaner split scores higher.
D2 · Cognitive Complexity
58 function(s) exceeded the cognitive complexity threshold of 15; the worst was Scheduler.Run at 172.
What to do
- Bring the 58 bodies over 15 down to 15 or less in Cognitive Complexity — start with Scheduler.Run (cognitive 172), runtime.runComplex (cognitive 133), Runner.RunInput (cognitive 110). — This score is capped by its worst body, so a finding fixed alone moves it by almost nothing — the next one down takes its place. Refactoring these 58 together lifts Cognitive Complexity from 2.0 to about 10.0/10, projected with the scoring formula itself and assuming each lands exactly at 15.
D3 · God Classes
8 over-large unit(s) detected — types, modules or files that carry too much.
What to do
- Resolve the 5 MethodTooLong finding(s) in God Classes — start with agent.go (2), scheduler.go, execute.go. — One of this dimension's main actionable groups (5 warning-level).
- Resolve the 1 FileTooLong finding(s) in God Classes — start with agent.go. — One of this dimension's main actionable groups (1 warning-level).
- Resolve the 1 ClassTooLong finding(s) in God Classes — start with agent.go. — One of this dimension's main actionable groups (1 warning-level).
D4 · Code Duplication
21 duplicated block group(s) detected. 4.1 % of the production lines (536 of 12,997) are in a reported copy. A further 10 rows report members as variants of one another; the share counts each copied line once, however many rows cite it. 5 of the 31 are in trees this repository does not ship — vendored, example/demo, project-template, fixture and benchmark code — and are ranked below the shipped groups rather than excluded from them: the duplication there is real and is still counted in this dimension's score. The dimensions that publish a production-file census leave those trees out of theirs, so this count is deliberately drawn over the wider population.
What to do
- Resolve the 4 Duplicated block (7 lines × 2) finding(s) in Code Duplication — start with tool.go, agent.go, skill.go. — One of this dimension's main actionable groups (4 warning-level).
- Resolve the 3 Duplicated block (13 lines × 2) finding(s) in Code Duplication — start with agent.go (2), rule_fixer.go. — One of this dimension's main actionable groups (3 warning-level).
- Resolve the 3 Duplicated block (9 lines × 2) finding(s) in Code Duplication — start with agent.go (2), modelcounter.go. — One of this dimension's main actionable groups (3 warning-level).
D6 · Cohesion (LCOM4)
0 of 40 classes have LCOM4 above 3.
D8 · Code Coverage
Line coverage 65.3% — 24 file(s) below 50%. Measured from the Go suite (github.com/cocoyes/zhizhi-agent-runtime: `go test -coverprofile -coverpkg=./...`, the 3 run(s) test reliability made). Taken over 3 runs of the suite: a line counts as covered only when every run executed it. 6 line(s) in 1 file(s) were executed in some runs and not in others, so they are not counted.
What to do
- Resolve the 24 Low coverage finding(s) in Code Coverage — start with REDACTED (15), otel.go, config.go. — One of this dimension's main actionable groups (24 warning-level).
- Resolve the 1 Tests reach code only in some runs finding(s) in Code Coverage — start with client.go. — One of this dimension's main actionable groups (1 recommendation-level).
D11 · Test Reliability
1 flaky across 1 measured tier(s). Go (github.com/cocoyes/zhizhi-agent-runtime): measured (1 flaky).
What to do
- Resolve the 1 Flaky test finding(s) in Test Reliability. — One of this dimension's main actionable groups (1 issue-level).
D12 · Dependency Hygiene
8 outdated, 0 author-deprecated direct Go module(s), 0 pinning or checksum defect(s). Whether any of these modules is UNMAINTAINED is not graded — proxy.golang.org publishes no maintenance status, and release age does not stand in for one. Whether any is UNUSED is not graded either: that is a source question, not a registry one. Known CVEs in this module graph are D30's question, read from REDACTED and go.sum there.
D13 · Secret Scanning
Secret scan ran and found no leaked secrets.
D14 · License Compliance
0 of 42 required Go module(s) use a banned license. Licences were read per module version from the licence files pkg.go.dev detects (via api.deps.dev), over every module this repository's REDACTED requires, direct and indirect, at the version the build uses. Go records no test-only scope at module level, so modules only this repository's own tests import are included.
D15 · Churn × Complexity Hotspots
Top hotspots: agent.go (10×79=790); internal/runtime/exec/scheduler.go (7×71=497); internal/runtime/react/react.go (4×51=204)
What to do
- Resolve the 9 Hotspot finding(s) in Churn × Complexity Hotspots — start with agent.go, scheduler.go, react.go. — One of this dimension's main actionable groups (9 warning-level).
D17 · Explicit Debt
0 deducted task-comment markers across 12997 LoC (0.0/KLoC) → score 10.0. Task comments only: this repository's language is read without a compiler, so D17's suppression, dead-code and commented-out-code arms did not run and this score counts fewer marker kinds than a .NET repository's would.
D19 · Documentation Quality
2 of 2 documentation facets pass in full. 10 document(s) read across 16 unit(s).
D22 · Internal API Consistency
0 API inconsistencies among 109 exposed members measured against a convention their peers follow.
D27 · Navigability
45 % of calls cross a namespace and 17 % go through an interface, but 68 % of collaborators are co-located — so following a call takes several hops. Baseline: small — navigation cost is tolerated.
D28 · Secrets (history)
gitleaks scanned the full history AND the current working tree and found no secrets.
D29 · Static Analysis (SAST)
6 finding(s): 0 critical, 4 high, 2 medium, 0 low. 4 unpinned-GitHub-Actions row(s) are reported here but scored by D36 (supply-chain provenance), which measures that posture as `pinned_actions` — one pinning decision is charged once, not once per lens.
What to do
- Resolve the 1 REDACTED finding(s) in Static Analysis (SAST) — start with REDACTED. — One of this dimension's main actionable groups (1 warning-level).
- Resolve the 1 REDACTED finding(s) in Static Analysis (SAST) — start with REDACTED. — One of this dimension's main actionable groups (1 warning-level).
- No action in Static Analysis (SAST) — all 4 REDACTED finding(s) are reported here at file:line but scored by D36 (supply-chain provenance), so none is charged to this dimension. — One of this dimension's main actionable groups (4 issue-level, 0 of them charged here).
D30 · Dependency Vulnerabilities
5 finding(s): 0 critical, 1 high, 4 medium, 0 low.
What to do
- Resolve the 1 High CVE finding(s) in Dependency Vulnerabilities — start with REDACTED. — One of this dimension's main actionable groups (1 issue-level).
- Resolve the 4 Medium CVE finding(s) in Dependency Vulnerabilities — start with REDACTED (4). — One of this dimension's main actionable groups (4 warning-level).
D31 · IaC & Container Security
trivy and checkov found no infrastructure-as-code or container misconfigurations.
D35 · Change Coupling
No strong hidden change-coupling between production files.
D37 · Vulnerability-disclosure Policy
A vulnerability-disclosure policy (REDACTED) is present but lists no reporting contact.
What to do
- Resolve the 1 REDACTED finding(s) in Vulnerability-disclosure Policy — start with REDACTED. — One of this dimension's main actionable groups (1 recommendation-level).
D43 · Malicious Dependencies
No dependency in any ecosystem this repository declares is published as malicious.
D44 · Platform End-of-Life
0 end-of-life runtime(s) and 0 end-of-life framework(s), read from 1 platform declaration(s) and 0 dependency declaration(s). This dimension reads what the repository says about ITSELF — a pinned target framework, a version file, a capped requires-python, a Rust toolchain pin, a framework major a constraint cannot move off. A FLOOR is deliberately never charged: `requires-python = ">=3.8"` states what the package SUPPORTS, not what it runs on, and a well-maintained library declares exactly that while running its own CI on a current release. The end-of-life facts are FROZEN and dated, so this dimension needs no network and answers identically inside a closed scan fence; as the table ages it loses recall and never precision, because a statement about support that ended in the past cannot become false. The OS layer of a container image is D31's question and the toolchain a CI workflow installs is D29's; this row is neither.
Frontend & cross-cutting dimensions
AX10 · Code composition
AX3 · Project dependency cycles
AX4 · Dependency direction
AX6 · Interface segregation
- `Session` declares 16 methods: `ID`, `SendAudio`, `CommitAudio`, `SetMuted`, `Say`, `ReplaceSpeech`, `CreateItems`, `UpdateItems`, `RetrieveItems`, `DeleteItems`, `Update`, `CancelResponse`, `Recv`, `SubmitFunctionOutputs`, `ExecuteFunctionCalls`, `Close`. Counted over the exported method specs the interface itself declares, once per name; an embedded interface is a role it composes, judged on its own declaration, and is not counted here. A wide interface forces every implementer and caller to depend on methods they don't use (the Interface-Segregation 'I' in SOLID). Split it into focused role-interfaces. — speech/speech.go:177
What to do
- Split fat interfaces into focused role-interfaces so clients depend only on what they use.
M1 · Documentation (README)
What to do
- Explain in the README how to run the tests. Add a section called Testing to the README in the repository's top folder, saying how to run the test suite.
M2 · Architecture documentation
- No Architecture Decision Records found — no conventional ADR directory, no numbered `NNNN-title` documents in any markup this check reads, and nothing ADR-shaped by content. Design rationale recorded elsewhere (a design-notes tree, a mailing list, pull-request discussion) is not visible to this check and is not re-findable per decision, so a future maintainer cannot ask why one choice was made and get an answer.
What to do
- Record your significant design decisions. Write one short document per decision, giving its date, the situation, the decision and its consequences, and keep them together with your other design documents. A docs/adr folder with each file named by number and title is the easiest place to find them.
M3 · Folder & project structure
M4 · Documentation accuracy
P1 · CI/CD gates
P10 · Library API & versioning
P3 · Security & performance tooling
- No static application security testing detected. For this repository's stack, add gosec / govulncheck (or golangci-lint) (or `semgrep --config=auto`, which runs on any language) as a CI step. What was searched, so you can tell an absence from a miss: the 1 CI workflow file(s) in this repository, and the scanner and linter configuration checked in beside them. A scan that runs outside CI, one configured in your forge's web UI rather than in a committed file, or a tool whose name is none of those this check carries, is not seen — if that is your case the row is wrong, and saying so is more useful than adding a second scanner. — REDACTED:6
- `REDACTED` declares packages, and nothing in the repository keeps them current: no Dependabot or Renovate configuration that schedules updates, and no dependency-review gate on pull requests. A pinned dependency stays at the version it was added at until someone notices — including after an advisory is published against it. Add a `.github/dependabot.yml` with one `package-ecosystem` entry per ecosystem the tree uses (or an enabled `renovate.json`), and gate pull requests with `actions/dependency-review-action`. — REDACTED:5
What to do
- Add a SAST step to CI running what this repository's stack ships: gosec / govulncheck (or golangci-lint) — or `semgrep --config=auto`, which runs on any language — so a security regression fails the build instead of landing.
- Enable Dependabot/Renovate or a dependency-review gate.
- Add gitleaks/trufflehog in CI to block PRs that introduce committed secrets.
P4 · Deployment & Rollback
What to do
- Nothing pauses a release for a human: publish as a draft release (or gate the release job on a protected tag/manual dispatch) so a bad build can be stopped before users can download it.
P6 · Release Hygiene
X2 · Cancellation propagation
X26 · Unsynchronised callback handoff
- `ExecuteFunctionCalls` starts a goroutine on every pass of a loop, and each one writes `_`, a variable declared before the loop — `_ = …` on line 328. The loop never waits on `group` before its next pass, so the goroutines of successive passes run at the same time and each one's write races the next one's; waiting on `group` after the loop orders only what follows the wait. A goroutine's closure captures `_` by reference, so every goroutine and the body use ONE variable, and a plain variable has no synchronisation of its own: by the Go memory model a write concurrent with any other access to it is a data race (the race detector reports it), a racing `++` loses updates, and a racing read sees a stale or torn value. `group` is a `sync.WaitGroup`, which orders the handoff's signal and takes no exclusion over the variable's own state. Guard every write to `_` with one `sync.Mutex`, or have each goroutine send its result on a channel that this body alone receives from and writes into `_`. — adapter/speech/doubao/client.go:328
What to do
- In Go, hand values from a goroutine to the body waiting on it over a channel the body receives from, rather than through a map or slice beside a `sync.WaitGroup` or a signal channel — or hold one `sync.Mutex` over every access to the shared map or slice on both sides. The wait orders the signal; it takes no exclusion over the map's or slice's own state.
X27 · Collection changed while being enumerated
X28 · Index access outside its own emptiness guard
X3 · Exception handling
- `encoded, _ := json.Marshal(step)` writes the call's error to `_` and then uses `encoded` as if the call succeeded. When `json.Marshal` fails, `encoded` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `encoded` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — agent.go:1515
- `encoded, _ := json.Marshal(raw)` writes the call's error to `_` and then uses `encoded` as if the call succeeded. When `json.Marshal` fails, `encoded` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `encoded` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. (×2) — agent.go:1575, agent.go:1598
- `b, _ := json.Marshal(in)` writes the call's error to `_` and then uses `b` as if the call succeeded. When `json.Marshal` fails, `b` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `b` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — skill.go:299
- `if err = os.MkdirAll(p, 0700); err != nil` takes every exception and records none of it — the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter. — skill/script/docker/config.go:216
- `if executionErr != nil` takes every exception and records none of it — the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter. — skill/script/docker/execute.go:214
- `b, _ := json.Marshal(w)` writes the call's error to `_` and then uses `b` as if the call succeeded. When `json.Marshal` fails, `b` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `b` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — skill/script/docker/files.go:72
- `if err != nil` takes every exception and records none of it — the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter. (×5) — observe/observe.go:73, mcp/security.go:24, internal/runtime/exec/resolve.go:79, …
- `result.Close()` returns an error, and the statement drops it: when `result.Close` fails nothing records it and the code after it runs as if it had succeeded. Check it (`if err := result.Close(); err != nil { … }`) and return or log it with what was being done, or assign it to `_` with a comment saying why the failure cannot matter. (×4) — mcp/capability_provider.go:48, mcp/capability_provider.go:55, mcp/capability_provider.go:59, …
- `if err := json.Unmarshal(encoded, &generic); err != nil` takes every exception and records none of it — the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter. — internal/runtime/exec/scheduler.go:385
- `if err := json.Unmarshal(encoded, &normalized); err != nil` takes every exception and records none of it — the body neither logs it, rethrows it, nor even names it, so the failure is discarded as completely as by an empty catch and only the substituted value survives. Log it through whatever this codebase already uses to report problems, narrow the catch to the exception this call can actually raise, or say in a comment on the catch why the failure genuinely cannot matter. — internal/runtime/exec/scheduler.go:427
- `result, _ = json.Marshal(map[string]string{"error": err.Error()})` writes the call's error to `_` and then uses `result` as if the call succeeded. When `json.Marshal` fails, `result` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `result` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — adapter/speech/doubao/client.go:328
- `tools, _ = json.Marshal(config.Tools)` writes the call's error to `_` and then uses `tools` as if the call succeeded. When `json.Marshal` fails, `tools` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `tools` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — adapter/speech/doubao/wire.go:27
- `b, _ := io.ReadAll(io.LimitReader(resp.Body, limit))` writes the call's error to `_` and then uses `b` as if the call succeeded. When `io.ReadAll` fails, `b` is its zero value (nil for a pointer, a map or an interface), so the program panics later or goes on with a default it never chose, and nothing records why. Check the error before using `b` (return it, wrapped with what was being done), or, if the failure genuinely cannot matter, say why in a comment on the line. — adapter/model/openaicompat/openaicompat.go:219
What to do
- Discarded error (assigned to `_`, then its result used)
X4 · Structured logging
Reference — by lens
| Lens | Score | Rating | Impact |
|---|---|---|---|
| Code Health | 76.5 | Adequate — gated by D1, D2 | Capped at Fair by a Critical contributor — resolve it before relying on this lens. |
| Architecture | 93.2 | Exemplary | Strongest area. |
| Maturity | 63.3 | Adequate — gated by M2 | Capped at Fair by a Critical contributor — resolve it before relying on this lens. |
| Readiness | 59.4 | Adequate — gated by P3 | Capped at Fair by a Critical contributor — resolve it before relying on this lens. |
| Security | 86.0 | Strong | Solid. |
Unscored — 3 check(s) recorded observations but carry no score
- X10 Duplicated predicate — 1 observation(s) recorded · Advisory — this card reports evidence and never carries a score.
- X7 Silent fallback defaults — 1 observation(s) recorded · Advisory — this card reports evidence and never carries a score.
- X9 Subsumed condition operand — 1 observation(s) recorded · Advisory — this card reports evidence and never carries a score.
Not evidenced — 4 control(s) we could not find positive evidence for
- C3 Audit Trail — Not assessed: these audit controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks audit controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- C4 Data Retention — Not assessed: these retention controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks retention controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- C5 Data-Subject Rights — Not assessed: these data-subject rights controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks data-subject rights controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- P5 DR & Backup — not evidenced — repo shows no backup/RTO/RPO controls; absence of evidence is not evidence of a working control
Not included — 69 check(s) not relevant to this codebase
- AC1 Text alternatives — No web markup found — accessibility is not applicable to this repository.
- AC2 Forms & labels — No web markup found — accessibility is not applicable to this repository.
- AC3 Page structure — No web markup found — accessibility is not applicable to this repository.
- AC4 Keyboard semantics — No web markup found — accessibility is not applicable to this repository.
- AC5 ARIA correctness — No web markup found — accessibility is not applicable to this repository.
- AC6 Visual & motion safety — No web markup found — accessibility is not applicable to this repository.
- AX1 Captive dependencies — Not applicable: this repository's Go imports no dependency-injection container and defines no container of its own — nothing that both registers and resolves bindings, and nothing that names two lifetimes — so nothing holds one lifetime's instance while handing out another's.
- AX2 Stateful singletons — No container singleton was found, so there is no shared instance for concurrent requests to race on. No Go request handler (a net/http, Gin, Echo, Fiber or fasthttp handler, or a gRPC service method) is declared as a method or function, and no handler function literal writes a value captured from outside it, so no state is shared between request goroutines.
- AX5 Architecture & structure — not assessed — architecture style/structure is computed from a project graph (projects, types, module namespaces) that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- AX7 Slice cohesion — not applicable — not a vertical-slice architecture
- AX8 Test isolation — no test/production split to check
- AX9 CQS / query purity — no CQRS query handlers detected — query purity is not applicable to this codebase
- AXB2 Runtime readiness — Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
- AXR1 Runtime accessibility — the image ran but published no HTTP port — nothing to crawl (EXPOSE the web port to unlock runtime evidence) This is a statement about this run, not a statement about your application: nothing here says the surface is inaccessible, only that it was never rendered.
- C1 Data Protection — Not assessed: these personal data controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks personal data controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- C2 Access Controls — Not assessed: these authorization controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks authorization controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- D10 Test Quality — ~5644 lines of test source are present (.go) but no test cases reached the test census for this repository — no test root we could resolve declared them, or the files we read declare no cases in a test framework we recognise — so skipped/assertion-free tests couldn't be counted. Not scored — this is a gap in the analyzer, not a finding about this repository.
- D16 Bus Factor — too few commits for a meaningful bus factor
- D18 Solution Shape — D18 scores the shape of a .NET solution; this repository has no .NET solution or project files, so the dimension does not apply.
- D20 ADR Quality — N/A — ADRs are expected on deployable products with a user-facing host, not consumed libraries; no ADR log is required here.
- D21 Naming Consistency — N/A — too few peers to establish a naming convention (3044 declarations, no unit with a dominant convention).
- D23 Boundary Type-Coupling — No bounded-context organisation was detected either — neither a context-shaped layout, nor 2+ sibling source directories each declaring an aggregate root, nor 2+ sibling projects each declaring an entity of their own or taking another project's integration events. Aggregate roots were found in only one source directory (observe), which is a layered codebase, not two contexts. Declaring this codebase's bounded contexts (≥2) would let cross-boundary type coupling be assessed. Declare them in `.codehealth/config.yaml` at the repository root (create it if absent), mapping each context name to the module-path or namespace prefixes that belong to it — e.g. `architecture:` → `contexts:` → `Billing: ["src/billing", "Acme.Billing"]`, `Catalog: ["src/catalog", "Acme.Catalog"]`.
- D24 Comment Value — D24 reads C#, Visual Basic, TypeScript and JavaScript comments only — this repository's production source is .go, .py, which was left unread. Not scored: this is a gap in the analyzer, not a verdict about this repository.
- D25 ADR Conformance — no ADRs to check
- D26 Project Cohesion — D26 could not read how the parts of this repository's one build unit reference each other, so its cohesion was not measured. Not scored: this is a gap in the analyzer, not a verdict about this repository.
- D32 Data Compliance (PII/GDPR) — No personal data was found crossing a boundary the PII/GDPR ruleset checks — nothing written to a log or console sink, placed in a URL or query string, or persisted to browser storage. That is a clean result for the LEAK surface only: this ruleset detects personal data escaping, it does not inventory the personal data a repository holds, so it is not evidence that this repository has no personal-data surface. The personal-data map (Appendix C) and the C1-C5 compliance cards are what speak to that.
- D34 Knowledge Freshness — too few commits to judge knowledge freshness
- D36 Supply-chain Provenance & Signing — The CI pipeline publishes no artifact — no package publish, container push or release with files to download. Supply-chain provenance, signing and an SBOM describe a PUBLISHED artifact for the people who obtain it, so there is nothing to attest here; a deployment of the service itself publishes nothing for anyone else to verify. Add them to the release pipeline when this repo starts publishing artifacts (a package, a container image, or a release with downloadable files). Build integrity and workflow-token hygiene are reported below: they describe what the CI runs and the token it runs with, neither of which is affected by whether the pipeline ships an artifact.
- D40 Network Egress Confinement — No Kubernetes/orchestration workloads found in the repository manifests; network egress policy is a cluster-native control that may live at the platform/firewall layer, so there is nothing to assess here.
- D41 Kernel & Syscall Confinement — No Kubernetes/orchestration workloads found in the repository manifests; seccomp/AppArmor/SELinux confinement is a workload-level control, so there is nothing to assess here.
- D42 Runtime Threat Enforcement — No Kubernetes/orchestration workloads found in the repository manifests; runtime threat-detection and admission-control policy are cluster-level controls, so there is nothing to assess here.
- D5 Coupling — Not applicable — this Go build ships 1 production module(s), so there is no coupling BETWEEN modules to measure. (Its test and non-production modules are not part of the shipped graph.)
- D7 Architectural Integrity — no checkable ADRs, and no project-reference graph for the cycle pass to read — so this dimension makes no claim about dependency cycles in either direction (where this repository's language has an import-cycle lens, cycles are reported there). Architectural integrity not assessed
- DM1 Domain Modelling — applicable but not scored (2 signals for this style, 2 needed — the count is met but a required primary signal is absent): 3 aggregate root(s) (types guarding their own state behind command methods — this language has no AggregateRoot base to inherit); 1 value object(s)
- ED1 Event-Driven — not scored — this repository shows only 1 of the 3 signals this lens looks for (5 event-sourced shape(s) (event folds / event-recording aggregates))
- ED5 Idempotency — no mutating command handlers or message consumers detected — idempotency check not applicable
- ES1 Event Sourcing — applicable but not scored (2 of 3 signals for this style — below the bar we score at): 1 aggregate(s) with Apply/When folds; 4 Go aggregate(s) recording domain events (own events-slice append / raise-record)
- GD1 Unfinished & placeholder code — no source files were read — this check reads C#, F#, JavaScript/TypeScript, Dart, Ruby, Scala, Rust and Java, and none was read for this repository's product. That is a limit of the analyzer, not a finding about your code.
- IC1 Incompleteness & stubs — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- P12 CI test-gate honesty — Reported, not scored — and nothing was matched here. The coverage check applies to any stack, and the automatic-re-run check to any GitHub-Actions workflow, but the checks for excluded tests, skipped tests and sleep-based synchronisation currently recognise only some ecosystems' test-runner idioms, so on a repository built with another stack the zeros below mean 'not checked', not 'clean'.
- P2 Observability — This repository's Go source (1 module(s), 46 file(s) read) declares no entry point and bootstraps no server, and nothing here deploys a service — it is a library, run inside whatever hosts it, so production observability (structured logging, tracing/metrics, health checks) is N/A. If it grows a binary or a service, the dimension reactivates.
- P7 Outbound HTTP resilience — not applicable — no HTTP server, API framework or worker entry point was found in the Go source, so there is no service whose uptime a failing dependency could take down
- P8 Schema migrations — no ORM, schema-migration tool or schema auto-create was found in this repository's dependency manifests or source, so there is no database schema for this check to judge
- P9 Domain vs controller coverage — coverage data present for 71 file(s), but no domain-layer files were identified: no covered file's path contains any of the markers this check keys on (/domain/, /aggregates/, /valueobjects/, /domainmodel/, .domain/, /entities/), which are matched case-insensitively anywhere in the path. With no domain partition there is nothing to compare the web/controller layer against — if this repository keeps its business rules under a folder named none of those, that naming is what the check cannot see, not the domain logic.
- PF1 Benchmark discipline — Not applicable: no benchmark suite was found. This check searched for a `func BenchmarkXxx(b *testing.B)` in any `_test.go` file, and for a `*benchmark*` script that this repository's CI runs. Benchmarks are credited as a bonus, so their absence is neither scored nor deducted.
- PF2 Allocation hygiene — Not scored: this check counted allocation-aware idioms (Span, pools, stackalloc) per line, which describes what kind of code a repository is rather than whether it has an allocation problem, so it was withdrawn. Nothing here is a finding about your code.
- PF3 Async & latency hygiene — Not applicable: Go has no async/await function colour, so there is no asynchronous code for a blocking call to stall.
- S1 Web-Security Posture — Not assessed: these web-security controls are read from a source model (declarative annotations, request middleware, entity/column names, guard methods) that was not loaded for this repository — because the repository is written in a language this check does not yet model, or because its projects failed to load. Absence of an idiom this check recognises is NOT evidence that this repository lacks web-security controls: it may implement them entirely in its own ecosystem. This is a gap in the analyzer's language coverage, not a finding about this repository.
- SC1 Supply-chain hygiene — Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
- X1 Async correctness — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X12 Unreachable branch — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X13 Undrained process stream — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X14 Bypassable address classification — not applicable — the code was read and holds no site of this kind, so there is nothing for this check to judge
- X15 Unvalidated length from an untrusted reader — not applicable — the code was read and holds no site of this kind, so there is nothing for this check to judge
- X16 Unfloored truncation loop — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X17 Uncapped recursion over a caller-supplied document — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X18 Disposal-pattern correctness — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X19 Unrestored process-global state — not applicable — the code was read and holds no site of this kind, so there is nothing for this check to judge
- X20 Mistyped argument guard — This check asks whether an argument guard reports an EMPTY value as a NULL one, which needs a language that throws a null-specific argument exception — .NET's ArgumentNullException, the JVM's NullPointerException, Dart's ArgumentError.notNull. This repository contains none of those languages: the ones it is written in have a single exception for a bad argument, so there is no pair of exceptions to confuse and nothing here for it to assess. Not a gap in the analyzer and not a finding about your code.
- X21 Side-effecting pattern guard — Not applicable: this check looks for a pattern guard or `case` label that increments, decrements or assigns while the switch is deciding whether it matches, and in this repository's languages none can. Go's `++`, `--` and assignments are STATEMENTS, not expressions, so none of them can appear in a `case` expression or anywhere else in a condition, and a type switch's cases are types. Not a gap in the analyzer and not a finding about your code.
- X22 Contradicted release guard — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X23 Unguarded diagnostic materialisation — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X24 Document value interpolated into markup unescaped — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X25 Inert configuration knob — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X29 Per-element action decided by a fixed element — not analysed — these correctness checks read a source model that was not loaded for this repository, because the repository is written in a language this check does not yet model, or because its projects failed to load. This is a gap in the analyzer, not a finding about this repository
- X30 Support guard that admits what it rejects — not applicable — the code was read and holds no site of this kind, so there is nothing for this check to judge
- X32 Type resolved by simple name across every loaded assembly — This check is about how a .NET program searches the assemblies loaded into its process for a type, and this repository contains no .NET source, so there is nothing here for it to assess. Not a gap in the analyzer and not a finding about your code.
- X5 Nullable reference types — Not applicable: this check asks whether the null-typed discipline a language offers is switched on, and how much of that the assertion operator takes back, and in this repository's languages there is no such switch and no such operator. Go's type system has no nullable and non-nullable types — every pointer, map, slice and interface is nil-able at every position, there is no switch that turns null checking on, and the compiler produces no nullability warning for an operator to silence. Not a gap in the analyzer and not a finding about your code.
- X6 Hand-rolled structured-format parsing — Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
Appendix A — Findings (grouped)
Critical — 6 finding(s)
- REDACTED
- REDACTED
- REDACTED
- REDACTED
- Flaky test: .::github.com/cocoyes/zhizhi-agent-runtime/adapter/speech/doubao.TestSessionLifecycleAudioAndFunctionCall
- REDACTED
Serious — 200 finding(s)
- Low coverage: adapter/otel/otel.go adapter/otel/otel.go:1
- Low coverage: config.go config.go:1
- Low coverage: contract/contract.go contract/contract.go:1
- Low coverage: eval/eval.go eval/eval.go:1
- Low coverage: examples/00-chat/main.go examples/00-chat/main.go:1
- Low coverage: examples/01-stream/main.go examples/01-stream/main.go:1
- Low coverage: examples/02-function-tool/main.go examples/02-function-tool/main.go:1
- Low coverage: examples/03-retry/main.go examples/03-retry/main.go:1
- Low coverage: examples/04-fallback/main.go examples/04-fallback/main.go:1
- Low coverage: REDACTED REDACTED:1
- Low coverage: examples/06-mcp-client/main.go examples/06-mcp-client/main.go:1
- Low coverage: examples/07-complex-plan/main.go examples/07-complex-plan/main.go:1
- Low coverage: examples/08-observability/main.go examples/08-observability/main.go:1
- Low coverage: examples/09-config-agent/main.go examples/09-config-agent/main.go:1
- Low coverage: examples/10-full-agent/main.go examples/10-full-agent/main.go:1
- Low coverage: examples/11-household-workflow/main.go examples/11-household-workflow/main.go:1
- Low coverage: REDACTED REDACTED:1
- Low coverage: examples/14-skills/main.go examples/14-skills/main.go:1
- Low coverage: examples/15-docker-skills/main.go examples/15-docker-skills/main.go:1
- Low coverage: internal/runtime/exec/resolve.go internal/runtime/exec/resolve.go:1
- Low coverage: policy/decision.go policy/decision.go:1
- Low coverage: route/router.go route/router.go:1
- Low coverage: skill/script/docker/engine.go skill/script/docker/engine.go:1
- Low coverage: tool/broker.go tool/broker.go:1
- Hotspot: agent.go agent.go:1177
- Hotspot: internal/runtime/exec/scheduler.go internal/runtime/exec/scheduler.go:118
- Hotspot: internal/runtime/react/react.go internal/runtime/react/react.go:60
- Hotspot: policy/policy.go policy/policy.go:90
- Hotspot: plan/plan.go plan/plan.go:85
- Hotspot: plan/replan.go plan/replan.go:110
- Hotspot: adapter/model/openaicompat/openaicompat.go adapter/model/openaicompat/openaicompat.go:151
- Hotspot: plan/planner.go plan/planner.go:89
- Hotspot: plan/tool_validation.go plan/tool_validation.go:17
- Swallowed exception (caught, then discarded) skill/script/docker/config.go:216
- Swallowed exception (caught, then discarded) skill/script/docker/execute.go:214
- Swallowed exception (caught, then discarded) observe/observe.go:73
- Swallowed exception (caught, then discarded) mcp/security.go:24
- Swallowed exception (caught, then discarded) internal/runtime/exec/resolve.go:79
- Swallowed exception (caught, then discarded) internal/runtime/exec/scheduler.go:381
- Swallowed exception (caught, then discarded) internal/runtime/exec/scheduler.go:385
- Swallowed exception (caught, then discarded) internal/runtime/exec/scheduler.go:423
- Swallowed exception (caught, then discarded) internal/runtime/exec/scheduler.go:427
- Discarded error (assigned to `_`, then its result used) agent.go:1515
- Discarded error (assigned to `_`, then its result used) agent.go:1575
- Discarded error (assigned to `_`, then its result used) agent.go:1598
- Discarded error (assigned to `_`, then its result used) skill.go:299
- Discarded error (assigned to `_`, then its result used) skill/script/docker/files.go:72
- Discarded error (assigned to `_`, then its result used) adapter/speech/doubao/client.go:328
- Discarded error (assigned to `_`, then its result used) adapter/speech/doubao/wire.go:27
- Discarded error (assigned to `_`, then its result used) adapter/model/openaicompat/openaicompat.go:219
- MethodTooLong: runtime.runComplex agent.go:1177
- MethodTooLong: Scheduler.Run internal/runtime/exec/scheduler.go:118
- MethodTooLong: Executor.Execute skill/script/docker/execute.go:32
- MethodTooLong: runtime.run agent.go:983
- MethodTooLong: Runner.RunInput internal/runtime/react/react.go:60
- REDACTED
- REDACTED
- REDACTED
- REDACTED
- Duplicated block (7 lines × 2) tool/tool.go:348
- Duplicated block (7 lines × 2) agent.go:551
- Duplicated block (7 lines × 2) skill.go:162
- Duplicated block (7 lines × 2) examples/14-skills/main.go:35
- Discarded error (an error-returning call as a bare statement) mcp/capability_provider.go:48
- Discarded error (an error-returning call as a bare statement) mcp/capability_provider.go:55
- Discarded error (an error-returning call as a bare statement) mcp/capability_provider.go:59
- Discarded error (an error-returning call as a bare statement) mcp/capability_provider.go:64
- Duplicated block (13 lines × 2) agent.go:865
- Duplicated block (13 lines × 2) agent.go:1027
- Duplicated block (13 lines × 2) plan/rule_fixer.go:178
- Duplicated block (9 lines × 2) agent.go:418
- Duplicated block (9 lines × 2) agent.go:2072
- Duplicated block (9 lines × 2) modelcounter.go:28
- Duplicated block (6 lines × 2) agent.go:751
- Duplicated block (6 lines × 2) agent.go:880
- Duplicated block (6 lines × 2) examples/14-skills/main.go:24
- Edited copy of a member (10 corresponding lines) agent.go:375
- Edited copy of a member (10 corresponding lines) adapter/speech/doubao/wire.go:89
- Edited copy of a member (9 corresponding lines) middleware/middleware.go:81
- Edited copy of a member (9 corresponding lines) skill/script/docker/config.go:256
- Edited copy of a member (11 corresponding lines) speech/tools.go:66
- Edited copy of a member (11 corresponding lines) internal/runtime/exec/resolve.go:62
- Duplicated block (12 lines × 2) internal/runtime/exec/scheduler.go:180
- Duplicated block (12 lines × 2) examples/10-full-agent/main.go:63
- Duplicated block (10 lines × 2) agent.go:400
- Duplicated block (10 lines × 2) agent.go:904
- Duplicated block (5 lines × 2) agent.go:895
- Duplicated block (5 lines × 2) agent.go:1068
- runtime.runComplex (cyclomatic 79) agent.go:1177
- Scheduler.Run (cyclomatic 71) internal/runtime/exec/scheduler.go:118
- docker.New (cyclomatic 63) skill/script/docker/config.go:77
- Executor.Execute (cyclomatic 55) skill/script/docker/execute.go:32
- Runner.RunInput (cyclomatic 51) internal/runtime/react/react.go:60
- Runner.Execute (cyclomatic 48) policy/policy.go:90
- runtime.run (cyclomatic 43) agent.go:983
- Plan.Validate (cyclomatic 41) plan/plan.go:85
- runtime.Resume (cyclomatic 39) agent.go:559
- runtime.resumeComplex (cyclomatic 37) agent.go:792
- model.ValidateCapabilities (cyclomatic 35) model/model.go:284
- Catalog.LoadRoot (cyclomatic 32) skill/catalog.go:165
- runtime.initialRecovery (cyclomatic 28) recovery.go:157
- runtime.Stream (cyclomatic 25) agent.go:1775
- plan.ValidateAgainstTools (cyclomatic 25) plan/tool_validation.go:17
- zhizhi.protectCompletedWrites (cyclomatic 24) recovery.go:37
- SchemalessBindingFix.Apply (cyclomatic 24) plan/fixes.go:30
- Client.request (cyclomatic 23) adapter/model/openaicompat/openaicompat.go:151
- eventStream.finishToolCalls (cyclomatic 23) agent.go:2036
- Executor.snapshot (cyclomatic 23) skill/script/docker/files.go:314
- script.Approve (cyclomatic 23) skill/script/script.go:176
- runtime.resumeSimple (cyclomatic 22) agent.go:696
- eventStream.Recv (cyclomatic 22) agent.go:1947
- plan.generateCandidate (cyclomatic 22) plan/output.go:229
- plan.ValidatePatchCompatibility (cyclomatic 22) plan/replan.go:110
- plan.outputTool (cyclomatic 21) plan/output.go:107
- Executor.scanWorkspace (cyclomatic 21) skill/script/docker/files.go:239
- skillExecutor.Execute (cyclomatic 20) skill.go:374
- openaicompat.normalizeFunctionParameters (cyclomatic 19) adapter/model/openaicompat/openaicompat.go:478
- plan.ClassifyError (cyclomatic 19) plan/rule_fixer.go:100
- Catalog.Search (cyclomatic 19) skill/search.go:24
- plan.validateStepMode (cyclomatic 18) plan/plan.go:225
- skillScope.restore (cyclomatic 18) skill.go:464
- skill.parse (cyclomatic 18) skill/catalog.go:120
- skillScriptTool.Call (cyclomatic 18) skill_script.go:41
- Client.Generate (cyclomatic 17) adapter/model/openaicompat/openaicompat.go:271
- session.readLoop (cyclomatic 17) adapter/speech/doubao/client.go:415
- zhizhi.WithSkillProvider (cyclomatic 16) skill.go:45
- exec.Compile (cyclomatic 16) internal/runtime/exec/compiler.go:45
- Provider.Ensure (cyclomatic 16) mcp/mcp.go:156
- plan.decodePlan (cyclomatic 16) plan/planner.go:89
- DecisionEngine.Decide (cyclomatic 16) policy/decision.go:44
- Scheduler.Run (cognitive 172) internal/runtime/exec/scheduler.go:118
- runtime.runComplex (cognitive 133) agent.go:1177
- Runner.RunInput (cognitive 110) internal/runtime/react/react.go:60
- Executor.Execute (cognitive 93) skill/script/docker/execute.go:32
- runtime.run (cognitive 92) agent.go:983
- Plan.Validate (cognitive 88) plan/plan.go:85
- Runner.Execute (cognitive 88) policy/policy.go:90
- docker.New (cognitive 66) skill/script/docker/config.go:77
- plan.ValidateAgainstTools (cognitive 65) plan/tool_validation.go:17
- Executor.scanWorkspace (cognitive 63) skill/script/docker/files.go:239
- zhizhi.protectCompletedWrites (cognitive 57) recovery.go:37
- runtime.resumeComplex (cognitive 56) agent.go:792
- model.ValidateCapabilities (cognitive 54) model/model.go:284
- runtime.resumeSimple (cognitive 50) agent.go:696
- plan.generateCandidate (cognitive 50) plan/output.go:229
- eventStream.finishToolCalls (cognitive 48) agent.go:2036
- plan.ValidatePatchCompatibility (cognitive 45) plan/replan.go:110
- Catalog.LoadRoot (cognitive 45) skill/catalog.go:165
- runtime.Resume (cognitive 43) agent.go:559
- SchemalessBindingFix.Apply (cognitive 40) plan/fixes.go:30
- plan.outputTool (cognitive 37) plan/output.go:107
- eventStream.Recv (cognitive 36) agent.go:1947
- Executor.snapshot (cognitive 34) skill/script/docker/files.go:314
- Provider.Ensure (cognitive 32) mcp/mcp.go:156
- Client.Generate (cognitive 31) adapter/model/openaicompat/openaicompat.go:271
- runtime.Stream (cognitive 31) agent.go:1775
- plan.validateCandidateSchema (cognitive 31) plan/output.go:63
- session.readLoop (cognitive 30) adapter/speech/doubao/client.go:415
- Catalog.Search (cognitive 30) skill/search.go:24
- ModelRouter.Route (cognitive 29) route/router.go:89
- Client.request (cognitive 28) adapter/model/openaicompat/openaicompat.go:151
- script.Approve (cognitive 28) skill/script/script.go:176
- stream.Recv (cognitive 27) adapter/model/openaicompat/openaicompat.go:380
- openaicompat.normalizeFunctionParameters (cognitive 26) adapter/model/openaicompat/openaicompat.go:478
- exec.Compile (cognitive 26) internal/runtime/exec/compiler.go:45
- plan.decodePlan (cognitive 26) plan/planner.go:89
- openaicompat.wireModelInput (cognitive 25) adapter/model/openaicompat/openaicompat.go:430
- skillScope.restore (cognitive 25) skill.go:464
- runtime.initialRecovery (cognitive 24) recovery.go:157
- zhizhi.New (cognitive 23) agent.go:236
- skillScope.search (cognitive 21) skill.go:229
- skillExecutor.Execute (cognitive 21) skill.go:374
- plan.validateStepMode (cognitive 20) plan/plan.go:225
- skillScope.invoke (cognitive 20) skill.go:311
- skill.parse (cognitive 20) skill/catalog.go:120
- Patch.Apply (cognitive 19) plan/replan.go:61
- CapabilityProvider.Select (cognitive 18) mcp/capability_provider.go:87
- plan.ClassifyError (cognitive 18) plan/rule_fixer.go:100
- Executor.ensureImage (cognitive 18) skill/script/docker/config.go:265
- skillScriptTool.Call (cognitive 18) skill_script.go:41
- runtime.agenticExecutor (cognitive 17) agent.go:495
- runtime.newRunConfig (cognitive 17) runoption.go:112
- observe.Sanitize (cognitive 17) observe/observe.go:143
- BudgetConflictFix.Apply (cognitive 17) plan/fixes.go:162
- DefaultRouter.Route (cognitive 17) route/router.go:35
- remoteTool.Call (cognitive 16) mcp/mcp.go:400
- observe.containsFold (cognitive 16) observe/observe.go:169
- plan.Optimize (cognitive 16) plan/optimizer.go:11
- REDACTED
- REDACTED
- FileTooLong: ./agent.go agent.go
- ClassTooLong: runtime agent.go:921
- FunctionTooLong: docker.New skill/script/docker/config.go:77
- Edited copy of a member (33 corresponding lines) agent.go:397
- Edited copy of a member (8 corresponding lines) adapter/otel/otel.go:91
- Duplicated block (8 lines × 2) speech/tools.go:69
- Duplicated block (8 lines × 3) adapter/model/openaicompat/openaicompat.go:533
- Edited copy of a member (15 corresponding lines) examples/00-chat/main.go:12
- Edited copy of a member (7 corresponding lines) examples/14-skills/main.go:23
- Collection crosses a callback boundary unsynchronised adapter/speech/doubao/client.go:328
Minor — 10 finding(s)
- Fat interface: Session (16 methods) speech/speech.go:177
- REDACTED
- REDACTED
- Tests reach code only in some runs: adapter/speech/doubao/client.go adapter/speech/doubao/client.go:358
- No ADRs
- No SAST REDACTED:6
- No dependency-update automation REDACTED:5
- Duplicated predicate adapter/model/openaicompat/openaicompat.go:535
- Silent fallback default on error mcp/security.go:24
- Subsumed condition operand plan/fixes.go:157
Minor — 8 finding(s)
- Outdated: github.com/go-openapi/jsonpointer
- Outdated: github.com/invopop/jsonschema
- Outdated: github.com/moby/moby/api
- Outdated: github.com/moby/moby/client
- Outdated: github.com/modelcontextprotocol/go-sdk
- Outdated: github.com/santhosh-tekuri/jsonschema/v6
- Outdated: go.opentelemetry.io/otel
- Outdated: go.opentelemetry.io/otel/trace
Appendix B — Reproduction & audit trail
| Dimension | Tool | Version | Command | Findings | Raw output |
|---|---|---|---|---|---|
| D28 · Secrets (history) | gitleaks | — | gitleaks detect --no-banner --config /opt/gitleaks-rules/canine-gitleaks.toml --report-format json --report-path /tmp/watchdog-gitleaks-cbed258e423747b0807a619fcac0d1c5/history.json --exit-code 0 --source . | 0 | artifacts/raw/gitleaks-history.json |
| D28 · Secrets (history) | gitleaks | — | gitleaks detect --no-git --no-banner --config /opt/gitleaks-rules/canine-gitleaks.toml --report-format json --report-path /tmp/watchdog-gitleaks-cbed258e423747b0807a619fcac0d1c5/tree.json --exit-code 0 --source . | 0 | artifacts/raw/gitleaks-tree.json |
| D29 · Static Analysis (SAST) | semgrep | — | semgrep --config /opt/semgrep-rules/security-audit.yml --config /opt/semgrep-rules/owasp-top-ten.yml --config /opt/semgrep-rules/canine-sast.yml --json --quiet --timeout 10 --timeout-threshold 3 --metrics off --exclude *.arrow --exclude *.avro --exclude *.csv --exclude *.dat --exclude *.db --exclude *.feather --exclude *.geojson --exclude *.h5 --exclude *.hdf5 --exclude *.jsonl --exclude *.log --exclude *.ndjson --exclude *.npy --exclude *.npz --exclude *.orc --exclude *.parquet --exclude *.pickle --exclude *.pkl --exclude *.psv --exclude *.sqlite --exclude *.sqlite3 --exclude *.tfrecord --exclude *.tsv --exclude *.txt --exclude .agents . | 6 | artifacts/raw/semgrep.json |
| D30 · Dependency Vulnerabilities | osv-scanner | — | osv-scanner --format json --recursive --experimental-disable-plugins transitivedependency/requirements --experimental-disable-plugins dotnet/csproj --experimental-disable-plugins dotnet/nugetcpm . /tmp/codehealth-osv-sbom-ce1fe580f0ca449ca9138c62a2fb74e7 | 5 | artifacts/raw/osv-scanner.json |
| D31 · IaC & Container Security | trivy | — | trivy config --format json --quiet . | 0 | artifacts/raw/trivy-config.json |
| D32 · Data Compliance (PII/GDPR) | semgrep | — | semgrep: not applicable — No personal data was found crossing a boundary the PII/GDPR ruleset checks — nothing written to a log or console sink, placed in a URL or query string, or persisted to browser storage. That is a clean result for the LEAK surface only: this ruleset detects personal data escaping, it does not inventory the personal data a repository holds, so it is not evidence that this repository has no personal-data surface. The personal-data map (Appendix C) and the C1-C5 compliance cards are what speak to that. | 0 | — |
| D40 · Network Egress Confinement | runtime-hardening | — | runtime-hardening: not applicable — No Kubernetes/orchestration workloads found in the repository manifests; network egress policy is a cluster-native control that may live at the platform/firewall layer, so there is nothing to assess here. | 0 | — |
| D41 · Kernel & Syscall Confinement | runtime-hardening | — | runtime-hardening: not applicable — No Kubernetes/orchestration workloads found in the repository manifests; seccomp/AppArmor/SELinux confinement is a workload-level control, so there is nothing to assess here. | 0 | — |
| D42 · Runtime Threat Enforcement | runtime-hardening | — | runtime-hardening: not applicable — No Kubernetes/orchestration workloads found in the repository manifests; runtime threat-detection and admission-control policy are cluster-level controls, so there is nothing to assess here. | 0 | — |
| D43 · Malicious Dependencies | osv-scanner | — | osv-scanner --format json --recursive --experimental-disable-plugins transitivedependency/requirements --experimental-disable-plugins dotnet/csproj --experimental-disable-plugins dotnet/nugetcpm . /tmp/codehealth-osv-sbom-ce1fe580f0ca449ca9138c62a2fb74e7 | 0 | artifacts/raw/osv-scanner.json |