Skip to content
CAI
Software that uses CAICheck a score

cocoyes/zhizhi-agent-runtime

66.4

Adequate · 17 November 2026

13k

lines of production code

Go

primary language

1

measurement over time

CAI band scale
CAI lens gauges

What this system is

Behavioural changes

1 commit (0 fixes) modifying adapter/speech, speech

A change to existing behaviour in adapter/speech, speech — 1 commit, 6 files: “support doubao speech”.

adapter/speech, speech · medium confidence · unverified

11 commits (1 fix) modifying github.com/cocoyes/zhizhi-agent-runtime

A change to existing behaviour in github.com/cocoyes/zhizhi-agent-runtime — 11 commits (1 fix), 3 files: “Add lazy multi-server MCP capability selection”; “Update agent runtime implementation”; “support skill load”; and 7 more.

github.com/cocoyes/zhizhi-agent-runtime · medium confidence · unverified

12 commits (2 fixes) modifying examples

A change to existing behaviour in examples — 12 commits (2 fixs), 27 files: “Add lazy multi-server MCP capability selection”; “Update agent runtime implementation”; “support skill load”; and 9 more.

examples · medium confidence · unverified

2 commits (0 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 2 commits, 35 files: “support skill load”; “Release v1.1.1 with Docker Skill execution and usage guides”.

skill · low confidence · unverified

2 commits (0 fixes) modifying .agents

A change to existing behaviour in .agents — 2 commits, 36 files: “Update agent runtime implementation”; “Improve agent runtime workflows and tooling”.

.agents · medium confidence · unverified

2 commits (0 fixes) modifying .gocache

A change to existing behaviour in .gocache — 2 commits, 4807 files: “delete cache”; “init,v1.0”.

.gocache · medium confidence · unverified

2 commits (0 fixes) modifying adapter/otel

A change to existing behaviour in adapter/otel — 2 commits, 1 file: “Update agent runtime implementation”; “update package”.

adapter/otel · medium confidence · unverified

2 commits (0 fixes) modifying eval, replay

A change to existing behaviour in eval, replay — 2 commits, 3 files: “update package”; “init,v1.0”.

eval, replay · medium confidence · unverified

25 commits (3 fixes) modifying (repo-wide)

A change to existing behaviour in (repo-wide) — 25 commits (3 fixs), 26 files: “add star history”; “Add lazy multi-server MCP capability selection”; “Update agent runtime implementation”; and 19 more.

(repo-wide) · low confidence · unverified

3 commits (0 fixes) modifying capability

A change to existing behaviour in capability — 3 commits, 2 files: “update package”; “init,v1.0”.

capability · medium confidence · unverified

3 commits (0 fixes) modifying checkpoint

A change to existing behaviour in checkpoint — 3 commits, 2 files: “Update agent runtime implementation”; “support skill load”; “Improve agent runtime workflows and tooling”.

checkpoint · medium confidence · unverified

3 commits (0 fixes) modifying contract

A change to existing behaviour in contract — 3 commits, 1 file: “Update agent runtime implementation”; “Release v1.0.5”; “init,v1.0”.

contract · medium confidence · unverified

3 commits (0 fixes) modifying middleware

A change to existing behaviour in middleware — 3 commits, 2 files: “Update agent runtime implementation”; “update package”; “Improve agent runtime workflows and tooling”.

middleware · medium confidence · unverified

3 commits (0 fixes) modifying observe

A change to existing behaviour in observe — 3 commits, 3 files: “Improve agent runtime workflows and task handling”; “update package”; “init,v1.0”.

observe · medium confidence · unverified

3 commits (0 fixes) modifying resolve, route

A change to existing behaviour in resolve, route — 3 commits, 4 files: “Improve agent runtime workflows and task handling”; “update package”; “init,v1.0”.

resolve, route · medium confidence · unverified

3 commits (0 fixes) modifying runtimeerr, security

A change to existing behaviour in runtimeerr, security — 3 commits, 3 files: “Update agent runtime implementation”; “update package”; “init,v1.0”.

runtimeerr, security · medium confidence · unverified

4 commits (0 fixes) modifying exec, planner, replan

A change to existing behaviour in exec, planner, replan — 4 commits, 9 files: “Update agent runtime implementation”; “Improve agent runtime workflows and task handling”; “update package”; and 1 more.

exec, planner, replan · medium confidence · unverified

4 commits (0 fixes) modifying internal/structuredoutput

A change to existing behaviour in internal/structuredoutput — 4 commits, 2 files: “Update agent runtime implementation”; “Improve agent runtime workflows and task handling”; “update package”; and 1 more.

internal/structuredoutput · medium confidence · unverified

5 commits (0 fixes) modifying internal/runtime

A change to existing behaviour in internal/runtime — 5 commits, 11 files: “support skill load”; “Release v1.1.1 with Docker Skill execution and usage guides”; “Release v1.0.5”; and 2 more.

internal/runtime · medium confidence · unverified

5 commits (0 fixes) modifying model

A change to existing behaviour in model — 5 commits, 3 files: “Update agent runtime implementation”; “Release v1.0.5”; “Improve agent runtime workflows and task handling”; and 2 more.

model · medium confidence · unverified

5 commits (0 fixes) modifying policy

A change to existing behaviour in policy — 5 commits, 3 files: “support skill load”; “Release v1.0.5”; “update package”; and 2 more.

policy · medium confidence · unverified

6 commits (0 fixes) modifying mcp

A change to existing behaviour in mcp — 6 commits, 7 files: “Add lazy multi-server MCP capability selection”; “Update agent runtime implementation”; “Improve agent runtime workflows and task handling”; and 2 more.

mcp · medium confidence · unverified

6 commits (2 fixes) modifying adapter/model

A change to existing behaviour in adapter/model — 6 commits (2 fixs), 2 files: “Update agent runtime implementation”; “fix reasoning\_effort param”; “fix default bug”; and 3 more.

adapter/model · medium confidence · unverified

8 commits (0 fixes) modifying tool

A change to existing behaviour in tool — 8 commits, 7 files: “Update agent runtime implementation”; “support skill load”; “Release v1.0.5”; and 4 more.

tool · medium confidence · unverified

8 commits (2 fixes) modifying plan

A change to existing behaviour in plan — 8 commits (2 fixs), 13 files: “Update agent runtime implementation”; “fix plan bug”; “Release v1.0.5”; and 5 more.

plan · medium confidence · unverified

Test coverage

2 commits adding/updating tests in tests

Test coverage in tests — 2 commits, 1 file: “update package”; “init,v1.0”.

tests · high confidence · unverified

Dependencies

6 commits updating dependencies (2 manifests)

A dependency / build maintenance change in (dependencies) — 6 commits, 2 files: “Update agent runtime implementation”; “Release v1.1.1 with Docker Skill execution and usage guides”; “support doubao speech”; and 3 more.

(dependencies) · medium confidence · unverified

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Baseline

  • First survey — no prior run to compare against. CAI 66.4.

Lenses

  • Code Health 76.5
  • Architecture 93.2
  • Maturity 63.3
  • Readiness 59.4
  • Security 86.0

Changes since last survey

  • 29 commits — 25 feature/other, 4 fixes

By area

  • (root) — 18 commits
  • .agents/skills — 2 commits
  • .gocache/64 — 2 commits
  • (repo) — 1 commit
  • adapter/speech — 1 commit
  • docs/zhizhi-agent-runtime-improvement-plan.md — 1 commit
  • examples/13-parallel-search — 1 commit
  • internal/runtime — 1 commit
  • plan/planner.go — 1 commit
  • skill/script — 1 commit

Notable commits

  • fix: fix bugs
  • fix: fix default bug
  • fix: fix plan bug
  • fix: fix reasoning_effort param
  • change: 1.0.8
  • change: 1.0.9
  • change: Add lazy multi-server MCP capability selection
  • change: Add opt-in Parallel Search MCP example
  • change: Improve agent runtime workflows and task handling
  • change: Improve agent runtime workflows and tooling
  • change: Merge pull request #1 from georgeatparallel/parallel-search-6de5a954-2835-4f0a-bfc8-c1c46f9f0287
  • change: Release v1.0.4
  • change: Release v1.0.5
  • change: Release v1.1.1 with Docker Skill execution and usage guides
  • change: Update agent runtime implementation
  • change: add star history
  • change: commit ignore
  • change: delete cache
  • change: init,v1.0
  • change: remove version
  • …and 9 more

Architecture

  • 0 containers · 1 bounded contexts · 0 dependency edges (baseline)

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

cocoyes/zhizhi-agent-runtime was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 17 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 480007470440d896436e78c609ab33fcd24ec73f — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.85+preprod-eba6548ac50f.