Public report of FoundationAgents/MetaGPT, published 25 October 2026. It has the same score, grades and number of
findings as the full report. The details of security findings (where they are in the code, which known
vulnerabilities and which passwords or keys were found) are left out, so nobody can use them against the project.
Public
Executive reportMeasured under the Code Assurance Index, an open standard for code quality, using its published scoring rules (rubric version 2026.10.5). Watchdog signed this survey and filed it in the standard's public register, where anyone can look it up by its survey ID. Check this survey →
Signed and filed in the standard's public register, 25 October 2026, 02:01 UTC · Survey ID cd_7cdab9bdc3614e4b85a898ff13ab6b21
FoundationAgents/MetaGPT
Measured 25 October 2026, 01:59 UTC, at code version 11cdf46
Regression: 1 dimension fell since the last survey
A regression is a drop of 0.5 points or more in the score, or of 2.5 or more out of 10 in a dimension, since the last survey.
CAI scoreAt riskDown 11 since the last survey
The score is built from these lenses. Each lens grades one area of the code, such as how easy it is to change or how well it is protected. The weakest lens counts most, so one weak area pulls the score down instead of being averaged away.
A medium codebase: 55,624 lines of product code in 4 projects, tests not counted · Estimated rebuild effort: about 0.4 person-years · Weakest lens: Security and Compliance, 23
Findings by how serious they are
49 critical339 serious353 minor
10 dimensions are left out of the score. For each one, Watchdog either couldn't measure it in this code, or found no evidence of the safeguard it looks for, such as a tested backup restore. They count neither for nor against the score, and Limitations lists each one with its reason.
This survey was produced by
Watchdog
Producer
Canine Development
Analyzer
Watchdog engine 1.0.0
Measured
25 October 2026, 01:59 UTC
A measurement, not a certificate. The Code Assurance Index records a number
together with the evidence it was worked out from, so anyone can recalculate it, but it doesn't certify or guarantee
the code. The standard was written by Canine Development, which also builds Watchdog. It is open to any tool that
implements it, and today Watchdog is the only one that does.
A critical security finding is open, such as a library with a known critical vulnerability or a password or key found in the code. The score itself is unchanged, but its band shows At risk until the finding is fixed. See the Security and Compliance lens.
The score is deterministic, which means the same code always gets the same score. Watchdog works it out with tools that follow published rules, and an AI model never decides it, so anyone who applies the same rules to the same code gets the same number. How it is done is explained under Methodology ▸
71of 75 dimensions measured by tools. The other 4 are advisory notes from an AI model, which explain the code but don't count towards the score.
676of 741 findings point to an exact file and line, so you can open each one in the code. The other 65 concern the repository as a whole, such as missing documentation.
75dimensions across 6 lenses, read from 55,624 lines of product code in 4 projects.
FoundationAgents/MetaGPT scores 38 out of 100, but it is rated At risk while a critical security finding is open; the score itself is unchanged. The project hasn't declared a stable release yet, so its lenses are rated against a lower bar than a released product's, while the score itself is worked out as for any repository.
The weakest lens counts most in the score, and here that is Security and Compliance, which scores 23 and is rated Weak. Its Secrets (history) dimension scores 0 out of 10, and until that reaches 4, Security and Compliance can't be rated higher than Adequate. The first actions are to protect endpoints by default-deny: a global authentication guard or middleware with explicit public opt-outs, or a guard on every route, plus named role/permission rules for what an authenticated caller may do and to resolve the 9 REDACTED finding(s) in Secrets (history), and if Security and Compliance rose to 70, the score would rise from 38 to about 51.
49 findings are critical: 30 in Static Analysis (SAST), nine in Secrets (history), six in Dependency Vulnerabilities, two in Supply-chain Provenance & Signing, one in IaC & Container Security and one in License Compliance.
Watchdog couldn't measure 9 dimensions in this code, among them Code Coverage, Test Reliability and Navigability, so they are left out of the score. The product code is 55,624 lines, which would take an estimated 0.4 person-years, around €63,000, to rebuild.
A lens is capped at Adequate while one of its dimensions scores below 4 out of 10, however well the rest of the lens does. That way a serious problem in one place always shows in the lens's rating.
How the score is built: what each lens counts forThe lenses don't count equally. The weakest lens counts most, the next weakest a little less, and so on, so a weak area pulls the score down instead of being averaged away. In the bar below, each part's width shows how much that lens counts and its colour shows its rating. Improving the widest part moves the score most, and as that lens improves, it counts for less, because another lens becomes the weakest.
Watchdog compares every finding with the previous survey's. A finding that has only moved to another line in the same file counts as the same finding, so only new findings appear here. Advisory notes from the AI model are left out, because the model words them afresh in every survey.
Fixed since the last survey: 5 findings
These 5 critical or serious findings were in the previous survey, on 11 October 2026, and are gone from this one.
Dependency Vulnerabilities · High CVE: [GHSA redacted] REDACTED
€21,000 to €110,000, for 349 to 1,107 hours of work, about 0.4 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
×0.7 at a score of 38. 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
Medium: 55,624 lines of product code
How the estimate is made: Watchdog prices the hours a team would need to write this code again, at €60 to €95 an hour. Declarations and boilerplate are priced at a fast rate and logic at a slower one, and the logic is then multiplied by the difficulty of the problem and by the quality factor. The estimate can be about 30% off either way, and it moves most with the hourly rate and the difficulty. For this code, every line is priced as straight logic, which keeps the estimate on the low side.
Top priorities
The three actions that raise the score most for the work they take. The full ranked list is in the Roadmap.
1
Protect endpoints by default-deny: a global authentication guard or middleware with explicit public opt-outs, or a guard on every route, plus named role/permission rules for what an authenticated caller may do.
Raises the score by about 13 points · Medium effort · Access Controls
2
Resolve the 9 REDACTED finding(s) in Secrets (history) — start with REDACTED (2), REDACTED (2), REDACTED (2).
Each conclusion below combines several dimensions into one point that no single dimension shows, and lists the measurements it rests on.
Where the investment is most exposed · Value at risk
This code would cost about €63,000 to build again, about 0.4 person-years of work. Its weakest lens is Security and Compliance, at 23 (Critical). Security and Compliance is about how well the product is protected, and how it handles personal data. Because the weakest lens counts most in the score, work on Security and Compliance also moves the score most.
Based on: the rebuild estimate · the Security and Compliance grade · how much each lens counts
What to do: Start with the Security and Compliance actions in Top priorities.
If you do one thing first · First action
Protect endpoints by default-deny: a global authentication guard or middleware with explicit public opt-outs, or a guard on every route, plus named role/permission rules for what an authenticated caller may do. Of all the actions in this report, it raises the score most for the work it takes: about 13 points for medium effort. The next survey will show the change in the score.
Based on: the ranked actions in Top priorities, by score gain and effort
Architecture — module dependency graph
Project dependencies, layered top-to-bottom; arrows show direction. Any dashed red edge points upward or sideways — a layering smell or cycle. A clean layered graph has none.
Architecture: which parts of the code depend on which
The code is divided into modules, groups of code that each handle one part of the product, and a module depends on another when it uses code from it. The table lists the modules both down the side and across the top, in an order where each module should only use modules listed above it. A number in a cell means the module on that row uses the module in that column, and it counts the pairs of building blocks (types) that connect them. The one thing to look for is a mark above the diagonal line. It means two or more modules use each other in a loop (a dependency cycle), so none of them can be changed, tested or released on its own.
419 modules, with 436 dependencies between them. Every module uses only modules listed above it, so there are no loops.
The table shows the 40 modules with the most connections; 379 more are left out to keep it readable.
Which modules use which. The module on each row uses the module in each column, and the number counts the pairs of types that connect them. A cell above the diagonal is part of a loop.
metagpt.base.base_env uses metagpt.base.base_env_space, so a change to metagpt.base.base_env_space can break metagpt.base.base_env, while a change to metagpt.base.base_env can't break metagpt.base.base_env_space.
Position
Below the diagonal: metagpt.base.base_env uses a module listed above it, which is the healthy direction.
metagpt.configs.embedding_config uses metagpt.utils.yaml_model, so a change to metagpt.utils.yaml_model can break metagpt.configs.embedding_config, while a change to metagpt.configs.embedding_config can't break metagpt.utils.yaml_model.
Position
Below the diagonal: metagpt.configs.embedding_config uses a module listed above it, which is the healthy direction.
metagpt.configs.llm_config uses metagpt.utils.yaml_model, so a change to metagpt.utils.yaml_model can break metagpt.configs.llm_config, while a change to metagpt.configs.llm_config can't break metagpt.utils.yaml_model.
Position
Below the diagonal: metagpt.configs.llm_config uses a module listed above it, which is the healthy direction.
metagpt.memory.memory uses metagpt.schema, so a change to metagpt.schema can break metagpt.memory.memory, while a change to metagpt.memory.memory can't break metagpt.schema.
Position
Below the diagonal: metagpt.memory.memory uses a module listed above it, which is the healthy direction.
metagpt.rag.factories.retriever uses metagpt.rag.factories.base, so a change to metagpt.rag.factories.base can break metagpt.rag.factories.retriever, while a change to metagpt.rag.factories.retriever can't break metagpt.rag.factories.base.
Position
Below the diagonal: metagpt.rag.factories.retriever uses a module listed above it, which is the healthy direction.
metagpt.rag.factories.retriever uses metagpt.rag.schema, so a change to metagpt.rag.schema can break metagpt.rag.factories.retriever, while a change to metagpt.rag.factories.retriever can't break metagpt.rag.schema.
Position
Below the diagonal: metagpt.rag.factories.retriever uses a module listed above it, which is the healthy direction.
metagpt.config2 uses metagpt.utils.yaml_model, so a change to metagpt.utils.yaml_model can break metagpt.config2, while a change to metagpt.config2 can't break metagpt.utils.yaml_model.
Position
Below the diagonal: metagpt.config2 uses a module listed above it, which is the healthy direction.
metagpt.config2 uses metagpt.configs.embedding_config, so a change to metagpt.configs.embedding_config can break metagpt.config2, while a change to metagpt.config2 can't break metagpt.configs.embedding_config.
Position
Below the diagonal: metagpt.config2 uses a module listed above it, which is the healthy direction.
metagpt.config2 uses metagpt.configs.llm_config, so a change to metagpt.configs.llm_config can break metagpt.config2, while a change to metagpt.config2 can't break metagpt.configs.llm_config.
Position
Below the diagonal: metagpt.config2 uses a module listed above it, which is the healthy direction.
metagpt.provider.base_llm uses metagpt.configs.llm_config, so a change to metagpt.configs.llm_config can break metagpt.provider.base_llm, while a change to metagpt.provider.base_llm can't break metagpt.configs.llm_config.
Position
Below the diagonal: metagpt.provider.base_llm uses a module listed above it, which is the healthy direction.
metagpt.actions.action_node uses metagpt.provider.base_llm, so a change to metagpt.provider.base_llm can break metagpt.actions.action_node, while a change to metagpt.actions.action_node can't break metagpt.provider.base_llm.
Position
Below the diagonal: metagpt.actions.action_node uses a module listed above it, which is the healthy direction.
metagpt.context uses metagpt.configs.llm_config, so a change to metagpt.configs.llm_config can break metagpt.context, while a change to metagpt.context can't break metagpt.configs.llm_config.
Position
Below the diagonal: metagpt.context uses a module listed above it, which is the healthy direction.
1 pair of types, where a type in metagpt.context uses a type in metagpt.config2.
The types involved
metagpt.context.Context → metagpt.config2.Config
Direction
metagpt.context uses metagpt.config2, so a change to metagpt.config2 can break metagpt.context, while a change to metagpt.context can't break metagpt.config2.
Position
Below the diagonal: metagpt.context uses a module listed above it, which is the healthy direction.
metagpt.context uses metagpt.provider.base_llm, so a change to metagpt.provider.base_llm can break metagpt.context, while a change to metagpt.context can't break metagpt.provider.base_llm.
Position
Below the diagonal: metagpt.context uses a module listed above it, which is the healthy direction.
metagpt.provider.openai_api uses metagpt.configs.llm_config, so a change to metagpt.configs.llm_config can break metagpt.provider.openai_api, while a change to metagpt.provider.openai_api can't break metagpt.configs.llm_config.
Position
Below the diagonal: metagpt.provider.openai_api uses a module listed above it, which is the healthy direction.
metagpt.provider.openai_api uses metagpt.provider.base_llm, so a change to metagpt.provider.base_llm can break metagpt.provider.openai_api, while a change to metagpt.provider.openai_api can't break metagpt.provider.base_llm.
Position
Below the diagonal: metagpt.provider.openai_api uses a module listed above it, which is the healthy direction.
metagpt.context_mixin uses metagpt.config2, so a change to metagpt.config2 can break metagpt.context_mixin, while a change to metagpt.context_mixin can't break metagpt.config2.
Position
Below the diagonal: metagpt.context_mixin uses a module listed above it, which is the healthy direction.
metagpt.context_mixin uses metagpt.provider.base_llm, so a change to metagpt.provider.base_llm can break metagpt.context_mixin, while a change to metagpt.context_mixin can't break metagpt.provider.base_llm.
Position
Below the diagonal: metagpt.context_mixin uses a module listed above it, which is the healthy direction.
metagpt.context_mixin uses metagpt.context, so a change to metagpt.context can break metagpt.context_mixin, while a change to metagpt.context_mixin can't break metagpt.context.
Position
Below the diagonal: metagpt.context_mixin uses a module listed above it, which is the healthy direction.
metagpt.environment.base_env uses metagpt.base.base_env_space, so a change to metagpt.base.base_env_space can break metagpt.environment.base_env, while a change to metagpt.environment.base_env can't break metagpt.base.base_env_space.
Position
Below the diagonal: metagpt.environment.base_env uses a module listed above it, which is the healthy direction.
metagpt.environment.base_env uses metagpt.schema, so a change to metagpt.schema can break metagpt.environment.base_env, while a change to metagpt.environment.base_env can't break metagpt.schema.
Position
Below the diagonal: metagpt.environment.base_env uses a module listed above it, which is the healthy direction.
metagpt.environment.base_env uses metagpt.base.base_env, so a change to metagpt.base.base_env can break metagpt.environment.base_env, while a change to metagpt.environment.base_env can't break metagpt.base.base_env.
Position
Below the diagonal: metagpt.environment.base_env uses a module listed above it, which is the healthy direction.
metagpt.environment.base_env uses metagpt.memory.memory, so a change to metagpt.memory.memory can break metagpt.environment.base_env, while a change to metagpt.environment.base_env can't break metagpt.memory.memory.
Position
Below the diagonal: metagpt.environment.base_env uses a module listed above it, which is the healthy direction.
metagpt.environment.base_env uses metagpt.context, so a change to metagpt.context can break metagpt.environment.base_env, while a change to metagpt.environment.base_env can't break metagpt.context.
Position
Below the diagonal: metagpt.environment.base_env uses a module listed above it, which is the healthy direction.
metagpt.actions.action uses metagpt.schema, so a change to metagpt.schema can break metagpt.actions.action, while a change to metagpt.actions.action can't break metagpt.schema.
Position
Below the diagonal: metagpt.actions.action uses a module listed above it, which is the healthy direction.
metagpt.actions.action uses metagpt.actions.action_node, so a change to metagpt.actions.action_node can break metagpt.actions.action, while a change to metagpt.actions.action can't break metagpt.actions.action_node.
Position
Below the diagonal: metagpt.actions.action uses a module listed above it, which is the healthy direction.
metagpt.actions.action uses metagpt.context_mixin, so a change to metagpt.context_mixin can break metagpt.actions.action, while a change to metagpt.actions.action can't break metagpt.context_mixin.
Position
Below the diagonal: metagpt.actions.action uses a module listed above it, which is the healthy direction.
metagpt.environment.android.android_env uses metagpt.environment.base_env, so a change to metagpt.environment.base_env can break metagpt.environment.android.android_env, while a change to metagpt.environment.android.android_env can't break metagpt.environment.base_env.
Position
Below the diagonal: metagpt.environment.android.android_env uses a module listed above it, which is the healthy direction.
metagpt.environment.werewolf.werewolf_ext_env uses metagpt.environment.base_env, so a change to metagpt.environment.base_env can break metagpt.environment.werewolf.werewolf_ext_env, while a change to metagpt.environment.werewolf.werewolf_ext_env can't break metagpt.environment.base_env.
Position
Below the diagonal: metagpt.environment.werewolf.werewolf_ext_env uses a module listed above it, which is the healthy direction.
metagpt.actions.write_prd uses metagpt.schema, so a change to metagpt.schema can break metagpt.actions.write_prd, while a change to metagpt.actions.write_prd can't break metagpt.schema.
Position
Below the diagonal: metagpt.actions.write_prd uses a module listed above it, which is the healthy direction.
metagpt.actions.write_prd uses metagpt.actions.action_node, so a change to metagpt.actions.action_node can break metagpt.actions.write_prd, while a change to metagpt.actions.write_prd can't break metagpt.actions.action_node.
Position
Below the diagonal: metagpt.actions.write_prd uses a module listed above it, which is the healthy direction.
metagpt.actions.write_prd uses metagpt.actions.action, so a change to metagpt.actions.action can break metagpt.actions.write_prd, while a change to metagpt.actions.write_prd can't break metagpt.actions.action.
Position
Below the diagonal: metagpt.actions.write_prd uses a module listed above it, which is the healthy direction.
metagpt.ext.stanford_town.actions.st_action uses metagpt.actions.action, so a change to metagpt.actions.action can break metagpt.ext.stanford_town.actions.st_action, while a change to metagpt.ext.stanford_town.actions.st_action can't break metagpt.actions.action.
Position
Below the diagonal: metagpt.ext.stanford_town.actions.st_action uses a module listed above it, which is the healthy direction.
metagpt.ext.werewolf.actions.common_actions uses metagpt.actions.action, so a change to metagpt.actions.action can break metagpt.ext.werewolf.actions.common_actions, while a change to metagpt.ext.werewolf.actions.common_actions can't break metagpt.actions.action.
Position
Below the diagonal: metagpt.ext.werewolf.actions.common_actions uses a module listed above it, which is the healthy direction.
metagpt.roles.role uses metagpt.schema, so a change to metagpt.schema can break metagpt.roles.role, while a change to metagpt.roles.role can't break metagpt.schema.
Position
Below the diagonal: metagpt.roles.role uses a module listed above it, which is the healthy direction.
metagpt.roles.role uses metagpt.base.base_env, so a change to metagpt.base.base_env can break metagpt.roles.role, while a change to metagpt.roles.role can't break metagpt.base.base_env.
Position
Below the diagonal: metagpt.roles.role uses a module listed above it, which is the healthy direction.
metagpt.roles.role uses metagpt.memory.memory, so a change to metagpt.memory.memory can break metagpt.roles.role, while a change to metagpt.roles.role can't break metagpt.memory.memory.
Position
Below the diagonal: metagpt.roles.role uses a module listed above it, which is the healthy direction.
metagpt.roles.role uses metagpt.context_mixin, so a change to metagpt.context_mixin can break metagpt.roles.role, while a change to metagpt.roles.role can't break metagpt.context_mixin.
Position
Below the diagonal: metagpt.roles.role uses a module listed above it, which is the healthy direction.
metagpt.roles.role uses metagpt.actions.action, so a change to metagpt.actions.action can break metagpt.roles.role, while a change to metagpt.roles.role can't break metagpt.actions.action.
Position
Below the diagonal: metagpt.roles.role uses a module listed above it, which is the healthy direction.
examples.agent_creator uses metagpt.schema, so a change to metagpt.schema can break examples.agent_creator, while a change to examples.agent_creator can't break metagpt.schema.
Position
Below the diagonal: examples.agent_creator uses a module listed above it, which is the healthy direction.
examples.agent_creator uses metagpt.actions.action, so a change to metagpt.actions.action can break examples.agent_creator, while a change to examples.agent_creator can't break metagpt.actions.action.
Position
Below the diagonal: examples.agent_creator uses a module listed above it, which is the healthy direction.
examples.agent_creator uses metagpt.roles.role, so a change to metagpt.roles.role can break examples.agent_creator, while a change to examples.agent_creator can't break metagpt.roles.role.
Position
Below the diagonal: examples.agent_creator uses a module listed above it, which is the healthy direction.
examples.build_customized_agent uses metagpt.schema, so a change to metagpt.schema can break examples.build_customized_agent, while a change to examples.build_customized_agent can't break metagpt.schema.
Position
Below the diagonal: examples.build_customized_agent uses a module listed above it, which is the healthy direction.
examples.build_customized_agent uses metagpt.actions.action, so a change to metagpt.actions.action can break examples.build_customized_agent, while a change to examples.build_customized_agent can't break metagpt.actions.action.
Position
Below the diagonal: examples.build_customized_agent uses a module listed above it, which is the healthy direction.
examples.build_customized_agent uses metagpt.roles.role, so a change to metagpt.roles.role can break examples.build_customized_agent, while a change to examples.build_customized_agent can't break metagpt.roles.role.
Position
Below the diagonal: examples.build_customized_agent uses a module listed above it, which is the healthy direction.
examples.build_customized_multi_agents uses metagpt.schema, so a change to metagpt.schema can break examples.build_customized_multi_agents, while a change to examples.build_customized_multi_agents can't break metagpt.schema.
Position
Below the diagonal: examples.build_customized_multi_agents uses a module listed above it, which is the healthy direction.
examples.build_customized_multi_agents uses metagpt.actions.action, so a change to metagpt.actions.action can break examples.build_customized_multi_agents, while a change to examples.build_customized_multi_agents can't break metagpt.actions.action.
Position
Below the diagonal: examples.build_customized_multi_agents uses a module listed above it, which is the healthy direction.
examples.build_customized_multi_agents uses metagpt.roles.role, so a change to metagpt.roles.role can break examples.build_customized_multi_agents, while a change to examples.build_customized_multi_agents can't break metagpt.roles.role.
Position
Below the diagonal: examples.build_customized_multi_agents uses a module listed above it, which is the healthy direction.
metagpt.ext.stanford_town.roles.st_role uses metagpt.schema, so a change to metagpt.schema can break metagpt.ext.stanford_town.roles.st_role, while a change to metagpt.ext.stanford_town.roles.st_role can't break metagpt.schema.
Position
Below the diagonal: metagpt.ext.stanford_town.roles.st_role uses a module listed above it, which is the healthy direction.
metagpt.ext.stanford_town.roles.st_role uses metagpt.roles.role, so a change to metagpt.roles.role can break metagpt.ext.stanford_town.roles.st_role, while a change to metagpt.ext.stanford_town.roles.st_role can't break metagpt.roles.role.
Position
Below the diagonal: metagpt.ext.stanford_town.roles.st_role uses a module listed above it, which is the healthy direction.
metagpt.ext.werewolf.roles.base_player uses metagpt.roles.role, so a change to metagpt.roles.role can break metagpt.ext.werewolf.roles.base_player, while a change to metagpt.ext.werewolf.roles.base_player can't break metagpt.roles.role.
Position
Below the diagonal: metagpt.ext.werewolf.roles.base_player uses a module listed above it, which is the healthy direction.
metagpt.memory.longterm_memory uses metagpt.schema, so a change to metagpt.schema can break metagpt.memory.longterm_memory, while a change to metagpt.memory.longterm_memory can't break metagpt.schema.
Position
Below the diagonal: metagpt.memory.longterm_memory uses a module listed above it, which is the healthy direction.
metagpt.memory.longterm_memory uses metagpt.memory.memory, so a change to metagpt.memory.memory can break metagpt.memory.longterm_memory, while a change to metagpt.memory.longterm_memory can't break metagpt.memory.memory.
Position
Below the diagonal: metagpt.memory.longterm_memory uses a module listed above it, which is the healthy direction.
metagpt.memory.longterm_memory uses metagpt.roles.role, so a change to metagpt.roles.role can break metagpt.memory.longterm_memory, while a change to metagpt.memory.longterm_memory can't break metagpt.roles.role.
Position
Below the diagonal: metagpt.memory.longterm_memory uses a module listed above it, which is the healthy direction.
metagpt.roles.di.data_interpreter uses metagpt.schema, so a change to metagpt.schema can break metagpt.roles.di.data_interpreter, while a change to metagpt.roles.di.data_interpreter can't break metagpt.schema.
Position
Below the diagonal: metagpt.roles.di.data_interpreter uses a module listed above it, which is the healthy direction.
metagpt.roles.di.data_interpreter uses metagpt.roles.role, so a change to metagpt.roles.role can break metagpt.roles.di.data_interpreter, while a change to metagpt.roles.di.data_interpreter can't break metagpt.roles.role.
Position
Below the diagonal: metagpt.roles.di.data_interpreter uses a module listed above it, which is the healthy direction.
metagpt.roles.di.role_zero uses metagpt.schema, so a change to metagpt.schema can break metagpt.roles.di.role_zero, while a change to metagpt.roles.di.role_zero can't break metagpt.schema.
Position
Below the diagonal: metagpt.roles.di.role_zero uses a module listed above it, which is the healthy direction.
metagpt.roles.di.role_zero uses metagpt.roles.role, so a change to metagpt.roles.role can break metagpt.roles.di.role_zero, while a change to metagpt.roles.di.role_zero can't break metagpt.roles.role.
Position
Below the diagonal: metagpt.roles.di.role_zero uses a module listed above it, which is the healthy direction.
metagpt.roles.di.data_analyst uses metagpt.roles.di.role_zero, so a change to metagpt.roles.di.role_zero can break metagpt.roles.di.data_analyst, while a change to metagpt.roles.di.data_analyst can't break metagpt.roles.di.role_zero.
Position
Below the diagonal: metagpt.roles.di.data_analyst uses a module listed above it, which is the healthy direction.
Findings mapped to OWASP categories; the specific CVEs/secrets are in the Security dimension cards below and findings.md (redacted only on the public version of this report).
OWASP category
Findings
Severity
A05:2025 — Injection
44
High / Critical
A03:2025 — Software Supply Chain Failures
20
High / Critical
A07:2025 — Authentication Failures
10
High / Critical
A02:2025 — Security Misconfiguration
4
High / Critical
Roadmap
First, secure the application by implementing a global authentication guard with explicit public opt-outs and defining named role permissions. Next, immediately remediate the nine secret findings in configuration and source files, and resolve the single banned license violation. Finally, integrate a SAST step into the CI pipeline to prevent security regressions and document the system architecture by creating the missing architecture decision records.
Ranked by impact ÷ effort. "Helps" is the estimated gain on the 0–100 health score.
Do this
Helps
Effort
Dimension
Protect endpoints by default-deny: a global authentication guard or middleware with explicit public opt-outs, or a guard on every route, plus named role/permission rules for what an authenticated caller may do.
Add a SAST step to CI running what this repository's stack ships: bandit, `semgrep --config=p/python`, or CodeQL's python pack — so a security regression fails the build instead of landing.
Every finding carries one of four grades. Three say how serious it is. The fourth says this
survey could not settle it — and it is a grade, not a gap.
Critical — 49
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.
Serious — 339
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.
Minor — 353
Recorded, with no effect on how the codebase functions.
Present so the survey is complete, not because it needs doing.
Could not be resolved — 10
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
Watchdog 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. 71 of 75 evaluated dimensions are computed purely by tools and static analysis (confidence 1.0); 4 documentation/naming judgement(s) are LLM-assisted and labelled advisory. Overall confidence is 0.9 — the weighted average across measured dimensions; it falls as more of the score leans on LLM-assisted judgement and rises when it's fully tool-backed.
Every figure here is one of three kinds, and we label which: ✓ Measured — a deterministic fact (LoC, complexity, coverage); ~ Modeled — an estimate from a stated model (cost, effort, value-at-risk), always a range with its assumptions, never a precise fact; ◐ Advisory — an LLM prose judgement. We never present a modelled estimate as if it were measured. Perfect or absent scores carry their provenance too (ADR-0011): ✓ Tool-verified means the property itself was measured across the surface; ○ Nothing flagged means the probes came back clean — a claim bounded by what a repository can show; ⊘ Not evidenced means a working control (a tested restore, an automated rollback) showed no positive evidence — absence of evidence is not evidence of a control, so it's excluded from the score rather than awarded a spurious 10; ◐ Sampled · advisory marks an LLM verdict over a bounded sample — advisory, never a deterministic measurement.
What we checked — 75 dimensions across the health lenses
Each chip is a dimension scored from real signals across architecture, testing, dependencies, security & compliance, documentation, git-history and code quality — in one coherent pass. A surface report typically covers a handful.
How to trust any code-health report — three questions
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, 676 of 741 do; the remainder are repo-wide signals — a dimension-level measurement, not a single line. (Every path in this report is repo-relative by construction: paths are normalized at the producer and the report is rejected if any rooted path leaks through.)
Is there a tool behind the number? Every score below names the method that produced it — Roslyn, git, a scanner, or (for a handful of documentation/naming dimensions) an LLM labelled sampled · advisory — 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.
This report answers yes to all three. That's the bar to hold any assessment to.
Tools & methods
The actual versions used this run (captured at analysis time) — re-run on the same commit for the identical score.
Method
Backs
Version
Evaluator
Roslyn static analysis
Complexity, cohesion, coupling, dead code, API surface, layering
What ran differently this time — a tool absent, degraded, or that fell back to an estimate. Named openly, not folded silently into the scores. A degraded run also records its exact cause in diagnostics.md.
D8 Code Coverage — not measured this run — Watchdog 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. Coverage NOT READ here — but this repository measures it: a coverage step in CI (`pytest tests/ --doctest-modules --cov=./metagpt/ --cov-repor…`) shows that coverage is collected and tracked in your own CI. The built-in collector has no runner for this ecosystem (.py), so the analyzer could not read the number — a gap in the analyzer's language coverage, not an unmeasured repo. Not scored. To have the real number read, produce a coverage report in a standard format (`coverage run -m pytest` then `coverage xml`) and commit it — a hosted scan measures a clone of the repository, so a report that exists only in a working tree, a CI runner's or your own, never reaches it; the artefact is commonly gitignored, so `git add -f` that one file (or un-ignore its path) and commit it alongside the code it measures. You can widen what we reach: optional: produce a coverage report in a standard format (`coverage run -m pytest` then `coverage xml`) and commit it — a hosted scan measures a clone of the repository, so a report that exists only in a working tree, a CI runner's or your own, never reaches it; the artefact is commonly gitignored, so `git add -f` that one file (or un-ignore its path) and commit it alongside the code it measures — then the real number is read on the next scan.
D11 Test Reliability — not measured this run — Watchdog 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. Test source is present (.py) and this repository declares a Python test suite (repository root, 249 test files), but it was not re-run: no test result was produced. Not scored — this is a gap in the analyzer's language coverage, not a finding about this repository.
D27 Navigability — not measured this run — Watchdog 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. Navigability is taken over call sites whose callee resolved. For C# that population includes calls into referenced assemblies; for this language only calls declared inside the repository count, so the abstention threshold reads the repository's use of its standard library as a resolution failure. That is a limit of this analyzer, not a build problem in this repository.
AXR1 Runtime accessibility — not measured this run — Watchdog 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 DockerCompose (.devcontainer/docker-compose.yaml). compose up failed (exit 17 — an image could not be built) — failed to solve: nikolaik/python-nodejs:python3.9-nodejs20-slim: failed to resolve source metadata for docker.io/nikolaik/python-nodejs:python3.9-nodejs20-slim: failed to do request: Head "https://registry-1.docker.io/v2/nikolaik/python-nodejs/manifests/python3.9-nodejs20-slim": Forbidden; runtime evidence skipped.
C1 Data Protection — not measured this run — Watchdog 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.
GD1 Unfinished & placeholder code — not measured this run — Watchdog 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 and Scala source only, and this repository's Python is most of its product and 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 — Watchdog 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 and Scala source only, and this repository's Python is most of its product and 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.
P8 Schema migrations — not measured this run — Watchdog 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. The schema may be created by a runner, a deploy script or a config file outside what this check reads, so an absence here is our blind spot rather than a missing migration strategy. The card abstains instead of scoring. You can widen what we reach: if the schema is created and evolved by a tool this check does not name, naming it lets us teach the detector to read it.
S1 Web-Security Posture — not measured this run — Watchdog 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.
Repo exclusion declarations: 4 pattern(s) declared (.gitattributes linguist-generated/vendored, .editorconfig generated_code) excluded 0 source file(s) from code-quality scoring. Declarations are the repo's own visible statement that a tree is machine-written or vendored — auditable in any diff, honored by GitHub the same way.
Limitations & what we did not check
Watchdog assesses the repository exactly as committed, and only the repository. By design it does 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
For each dimension that was measured, what a static, repo-only scan structurally cannot see — the honest edge of the measurement, not a failure of it.
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.
D5 Coupling: Coupling is measured between projects/assemblies — runtime coupling through DI, reflection, messaging or shared databases is invisible to a static reference graph.
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.
D9 Test Distribution: The test-pyramid shape is inferred from project/folder naming and references, with a single test host bucketed per-file by its path tier and content signals — a suite that names tiers unconventionally and gives no per-file signal can still be mis-bucketed.
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 REDACTED Scanning: REDACTED 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.
D16 Bus Factor: Bus-factor is a time-decayed model of commit attribution (who has recently, repeatedly worked a file), not comprehension — pairing, review and reading-without-committing spread knowledge it can't see; bot commits and shared accounts still distort it.
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 is judged by an LLM over a bounded sample of docs — it reads what is written, not whether the docs match the running system, and it is advisory, not a measurement. Its critique rows are drawn from a closed category vocabulary and each row means the same thing in every run, so two scans can be compared row by row; the SET that fires is still a sample, and does not repeat exactly. Measured on one frozen input, six scans at one engine SHA: 2-5 critique rows per scan, 8 distinct rows across the six, 3 of those 8 seen in only one scan. So a D19 row is evidence about the documentation, but a COUNT of D19 rows is not a quantity — never read a change in it as an improvement or a regression.
D20 ADR Quality: ADR quality is an LLM read of the decision records present — it cannot know about decisions made and never recorded, and its verdict is sampled and advisory.
D21 Naming Consistency: Naming quality is an LLM judgement over a bounded sample — it assesses clarity/consistency of the names it sees, not domain-correctness, and is advisory.
D22 Internal API Consistency: API-surface coherence is an LLM judgement over a sample of the public surface — consistency of intent across the whole API is approximated, not exhaustively verified.
D26 Project Cohesion: Project focus is sized from members/namespaces per project — a project that is broad by deliberate design reads the same as one that has sprawled.
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 REDACTED, 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.
D34 Knowledge Freshness: Freshness is decayed commit RECENCY, not comprehension — code read often but rarely committed reads as orphaned, and stable code that genuinely needs no changes is penalised the same as forgotten code; bot/squash commits distort it like the bus factor.
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 REDACTED (D31's subject), in a CI workflow (D29's), or in a file this pass does not parse (go.mod, 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: Onboarding quality is an LLM read of the docs/setup present — it cannot run the onboarding or measure how long a real new joiner takes; the verdict is sampled and advisory.
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.
The LLM boundary
LLM-set scores this run (4): D19, D21, D22, M4 (model: Local LLM). For these, a model reads a bounded sample and sets the numeric score; each names its own sample and method on its card. They are sampled and advisory by design: they vary at the margins between runs and are never a deterministic measurement. Every other score in this report is tool-computed at confidence 1.0.
What it measures: How tangled the control flow is — methods with many branches are hard to test and change.
Method: Cyclomatic complexity per method (1 + decision points), computed exhaustively across production source; test projects separated by convention. Deterministic.
+ 18 more group(s) — more in Appendix A; the complete list is findings.md.
What to do
Bring the 1 body over 30 down to 30 or less in Cyclomatic Complexity — start with Editor._edit_file_impl (cyclomatic 36). — Refactoring it lifts Cyclomatic Complexity from 7.2 to about 7.4/10.
Enforce Cyclomatic Complexity in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Prevented — provenance only; does not change the score.
Detailed fixes: d1_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: How hard the code is for a person to follow, beyond raw branching.
Method: Cognitive complexity per method (Sonar-style nesting-penalized score), computed exhaustively over production code, excluding test projects. Deterministic.
+ 44 more group(s) — more in Appendix A; the complete list is findings.md.
What to do
Bring the 49 bodies over 15 down to 15 or less in Cognitive Complexity — start with StanfordTownExtEnv._init_maze (cognitive 52), STRole.observe (cognitive 44), Editor._edit_file_impl (cognitive 44). — 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 49 together lifts Cognitive Complexity from 6.7 to about 10.0/10, projected with the scoring formula itself and assuming each lands exactly at 15.
Enforce Cognitive Complexity in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Prevented — provenance only; does not change the score.
Detailed fixes: d2_recommendation.md · top locations in Appendix A, every location in findings.md.
Do you agree with this assessment?
D3 · God Classes9.4 / 10Stronggated by 7 serious findings✓ Tool-verified
What it measures: Over-large classes that try to do too much ("god classes").
Method: God-class detection by line and method-count thresholds per logical type (partial classes unified), filtered for generated code and registration/contract false positives. Deterministic.
Resolve the 5 FileTooLong finding(s) in God Classes — start with experience_retriever.py, common.py, editor.py. — One of this dimension's main actionable groups (5 warning-level).
Resolve the 1 FunctionTooLong finding(s) in God Classes — start with REDACTED. — One of this dimension's main actionable groups (1 warning-level).
Resolve the 1 TooManyMethods finding(s) in God Classes — start with REDACTED. — One of this dimension's main actionable groups (1 warning-level).
Enforce God Classes in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Prevented — provenance only; does not change the score.
Detailed fixes: d3_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Copy-pasted code that should be shared instead.
Method: Code duplication via token-stream sliding windows with type-aware normalization (locals masked, type names preserved), density-scored per KLoC of production code. Deterministic.
39 duplicated block group(s) detected. 1 of the 39 are in trees this repository does not ship — vendored, example/demo, 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.
+ 18 more group(s) — more in Appendix A; the complete list is findings.md.
What to do
Resolve the 6 Duplicated block (5 lines × 2) finding(s) in Code Duplication — start with screenshot_parse.py (2), design_api.py (2), browser.py. — One of this dimension's main actionable groups (6 warning-level).
Resolve the 5 Duplicated block (10 lines × 2) finding(s) in Code Duplication — start with REDACTED, agent_chat_sum_rel.py, decide_to_talk.py. — One of this dimension's main actionable groups (5 warning-level).
Resolve the 5 Duplicated block (9 lines × 2) finding(s) in Code Duplication — start with rebuild_sequence_view.py, write_code.py, ollama_api.py. — One of this dimension's main actionable groups (5 warning-level).
Enforce Code Duplication in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Verified — provenance only; does not change the score.
Detailed fixes: d4_recommendation.md · top locations in Appendix A, every location in findings.md.
Do you agree with this assessment?
D5 · Coupling10.0 / 10Exemplary✓ Tool-verified
What it measures: Whether volatile projects sit underneath others that depend on them (so their churn ripples upward), and whether project dependencies form cycles. A widely-depended-on but stable shared/kernel project is healthy, not penalised.
Method: Dependency cycles via elementary-DFS over real .csproj references, plus Martin instability (afferent/efferent) per project. Exhaustive over the reference graph, deterministic.
Coverage: Exhaustive · type-level: afferent/efferent coupling + cycles computed over every production type — the population is all types, not a name convention.
3 production modules (npm+Python), 0 dependency cycle(s), 0 unstable depended-on module(s). Read from the build's own module declarations; 0 module(s) off the main sequence, with abstractness counted on 1 of the 3 (the rest declare no modelled class or interface, export only macros, declare types in source no model reads, or have no source directory of their own).
What it measures: Whether a class's methods are focused on a single responsibility.
Method: LCOM4 cohesion per production class with at least two methods: connected components of methods sharing state or calls, computed syntactically. Deterministic, not a proxy.
Coverage: Exhaustive · type-level: LCOM4 cohesion computed over every production class — the population is all types, not a name convention.
Resolve the 1 Low cohesion finding(s) in Cohesion (LCOM4) — start with engineer2.py. — One of this dimension's main actionable groups (1 warning-level).
Enforce Cohesion (LCOM4) in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Verified — provenance only; does not change the score.
Detailed fixes: d6_recommendation.md · top locations in Appendix A, every location in findings.md.
Do you agree with this assessment?
D9 · Test Distribution10.0 / 10Exemplary✓ Tool-verified
What it measures: Whether the test suite has a healthy mix of unit / integration / end-to-end tests.
Method: Test projects classified (Unit/Integration/BDD/E2E) from compiled metadata; test methods counted exhaustively across projects with placement-agnostic disk fallback. Deterministic.
753 test methods: 753 unit, 0 integration, 0 BDD, 0 e2e. The Python suite contributes 753 test function(s) across 243 file(s) declaring at least one — every `def test…` in a file pytest or unittest would collect, which is those frameworks' own definition of a case; a parametrize table counts once, so this is a floor. Its tier split is read from file names and paths only.
What it measures: Whether dependencies are current, secure, and not bloated.
Method: Manifest scan via dotnet list package across all projects; worst-signal-per-package deduction (saturating for vulnerabilities, capped-linear for deprecation/outdated) per KLoC. Exhaustive, deterministic.
38 outdated, 0 yanked pinned Python distributions. 41 of 75 shipped distributions were graded against pypi.org (0 not published there, 34 declared without an exact pin, which installs the newest release the declaration admits and so cannot be behind one). Only EXACT pins are graded for currency: a floor or a range already installs the newest release it admits, so reporting one would report this repository for being current. Whether a deliberate upper cap has itself gone stale is a different and weaker question, and is not asked. Whether any distribution is UNMAINTAINED is not graded — PyPI publishes no maintenance status, and release age does not stand in for one. Lockfiles are not read (poetry.lock, uv.lock, Pipfile.lock, pdm.lock), so a lock-resolved install is outside this verdict. Known CVEs in this dependency graph are D30's question.
Outdated: aiofiles · ×38
What to do
Enforce Dependency Hygiene in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Verified — provenance only; does not change the score.
Detailed fixes: d12_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether any secrets (keys, tokens, passwords) have leaked into the code.
Method: In-process native secret scanner (entropy plus signature patterns) across all tracked files; no external tool. A clean result is a measured 10, not no-data zero. Deterministic.
What it measures: Whether the licenses of third-party packages are compatible with your policy.
Method: Third-party package licenses resolved from declared package metadata and checked against the configured policy (allow/deny/copyleft). Deterministic; clean = no incompatible license found at metadata depth.
1 of 415 shipped Python distribution(s) use a banned license. Licences were resolved from PyPI over the distributions a consumer installs — this repository's 75 declared runtime requirement(s) closed transitively over each distribution's published `requires_dist` (340 reached that way). Requirements it states ONLY under an extra, a PEP 735 dependency group, a Poetry dev group or a dev-named requirements file are excluded: pip does not install any of them for a consumer. ★ This repository commits no dependency lockfile that this pass reads, so each licence is the one PyPI publishes for the distribution's CURRENT release rather than for a pinned version. 176 of them publish no licence on PyPI this pass can read; that is missing data, not a violation, and none of them is charged.
Banned license: pylint
What to do
Resolve the 1 Banned license finding(s) in License Compliance. — One of this dimension's main actionable groups (1 issue-level).
Enforce License Compliance in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Verified — provenance only; does not change the score.
Detailed fixes: d14_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Files that change often and are also complex — the riskiest hotspots.
Method: Per production file churn times cyclomatic complexity over a rolling window, computed from git and Roslyn/JS/Razor analysis. Exhaustive, deterministic per commit date.
What it measures: Whether knowledge is concentrated in too few people (the "bus factor").
Method: Living knowledge per author via time-decayed commit attribution (6-month half-life, focus weighting) across largest source files. Deterministic, avoids blame's mechanical-refactor false positives.
17 source file(s) have their living knowledge concentrated in one author (≥90% of recent, decayed contribution). The largest is metagpt/tools/libs/index_repo.py. Counted over 266 of the 516 production source files in this repository: 243 are under the ~2,400-byte size floor this dimension measures over, and the remaining 7 have no attributable history left to measure.
Off-boarding risk: anonymized user #1 · ×3
Further sole-owners (lower concentration)
✓ On the Gold path — maintain.
Detailed fixes: d16_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Acknowledged debt left in the code — TODOs, dead code, suppressed warnings.
Method: Roslyn syntactic debt markers (suppressions/TODO/FIXME/HACK/empty-catch/commented-code/Obsolete) plus SymbolFinder dead-code analysis; weighted-debt-per-KLoC density deducted 2.0x per unit. Deterministic, exhaustive.
91 deducted task-comment markers across 55624 LoC (0.2/KLoC) → score 9.7. 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.
Resolve the 66 TodoComment finding(s) in Explicit Debt — start with st_role.py (6), self_learn_and_reflect.py (4), env_space.py (3). — One of this dimension's main actionable groups (66 warning-level).
Resolve the 22 FixmeComment finding(s) in Explicit Debt — start with document.py (2), REDACTED (2), test_prompt.py (2). — One of this dimension's main actionable groups (22 warning-level).
Resolve the 3 HackComment finding(s) in Explicit Debt — start with moderator.py (2), role_zero.py. — One of this dimension's main actionable groups (3 warning-level).
Enforce Explicit Debt in CI to reach Verified (currently Documented). — Hardens enforcement from Documented toward Prevented — provenance only; does not change the score.
Detailed fixes: d17_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether the project's documentation is clear, complete, and useful.
Method: Judged by language model at low temperature (0.0-0.1) on a deterministic doc sample (READMEs plus first 25 architecture docs), with two-pass stability filtering. Advisory, sampled.
The repository is well documented: the READMEs of each directory (e.g. metagpt/ext/sela/README.md, metagpt/ext/stanford_town/README.md) describe what that directory does and how to use its contents; architecture/design docs are present (32 markdown files); the academic papers referenced in ACADEMIC_WORK.md are cited; a comprehensive FAQ document covers installation, roadmap, contributor guidance, and links to all MetaGPT documentation; and a NEWS.md chronicles major releases. The READMEs of each directory are judged only against their own scope. This repository is a well-structured documentation set: the root README (MetaGPT: Architecture Multi-Agent) gives an overview of what the project does and its main features with a strong callout to the Japanese roadmap, while architecture/roadmap markdown files cover the scope in detail. The READMEs for each language pair are consistent in describing their own directory's purpose and provide installation, usage, and contribution guidance (Discord/Follow links). There is no single unshown document that would make any of these sections missing; all visible content is complete and well-organized. (11 of 25 sampled documents could not be assessed: 1 of 3 evaluation groups failed.)
Documentation: no project overviewdocs/README_CN.md
✓ On the Gold path — maintain.
Detailed fixes: d19_recommendation.md · top locations in Appendix A, every location in findings.md.
Do you agree with this assessment?
D20 · ADR Quality0.0 / 10Critical✓ Tool-verified
What it measures: Whether architecture decisions are recorded well (context, decision, consequences).
Method: Per-ADR judgment by language model at low temperature with two-pass stability; confidence is share of ADRs evaluated; enforcement-field presence detected deterministically. Advisory.
What it measures: Whether names — types, methods, variables — are clear and consistent.
Method: Judged by language model at low temperature (0.0-0.1) on a deterministic random symbol sample (fixed size, not exhaustive), with disclosed confidence band. Advisory, sampled.
0 naming inconsistencies across 0 sampled symbols.
✓ On the Gold path — maintain.
Detailed fixes: d21_recommendation.md.
Do you agree with this assessment?
D22 · Internal API ConsistencyExemplary◐ Sampled · advisory
What it measures: Whether the internal API surface is consistent and coherent.
Method: Judged by language model at low temperature over a sample of the public API surface (IsPackable or .Contracts types). Sampled, advisory; confidence discounted by model uncertainty.
1 of 4 build units (Python, npm) flagged as possibly oversized/incoherent.
Projects may be oversized for their cohesion
What to do
Resolve the 1 Projects may be oversized for their cohesion finding(s) in Project Cohesion. — One of this dimension's main actionable groups (1 recommendation-level).
Detailed fixes: d26_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether any secrets were ever committed — scanned across the full git history, not just now.
Method: REDACTED scan via TWO gitleaks detect passes in an isolated checkout — the full git history, then a second --no-git pass over the working tree as it stands — merged and de-duplicated by (rule, file, line); each match flagged High. Both invocations are recorded in the audit trail. Exhaustive; when the tool is absent, or when its output cannot be parsed into the expected shape, the dimension is WITHHELD as an explicit measurement gap on our side — unscored and excluded from the lens, never a hedged middling score.
12 finding(s): 0 critical, 12 high, 0 medium, 0 low. Remediation for historically-committed secrets is credential rotation — they remain in history regardless of later deletion.
REDACTED
REDACTED
What to do
Resolve the 9 REDACTED finding(s) in Secrets (history) — start with REDACTED (2), REDACTED (2), REDACTED (2). — One of this dimension's main actionable groups (9 issue-level).
Resolve the 1 Rotate the exposed credentials finding(s) in Secrets (history). — One of this dimension's main actionable groups (1 recommendation-level).
Detailed fixes: d28_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Real static-analysis (SAST) findings — likely security bugs in the code, any language.
Method: Polyglot static analysis via semgrep across the repo using the pinned, image-baked p/security-audit + p/owasp-top-ten rulesets (no scan-time registry fetch); severity rules (ERROR/WARNING/INFO) map to a full-band severity-weighted score. Exhaustive, deterministic; degrades on parse failure.
Coverage: semgrep pattern rules over all files — exhaustive for the rule set, blind to classes of bug without a rule (clean = no rule matched).
44 finding(s): 0 critical, 30 high, 12 medium, 2 low. 11 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. semgrep hit a parse error in 3 file(s) — `metagpt/tools/swe_agent_commands/defaults.sh` (line 9), `metagpt/tools/swe_agent_commands/edit_linting.sh`, `metagpt/tools/swe_agent_commands/search.sh` (line 31, line 36, line 37, …) — so no absence of findings in the named regions is evidence of anything; rows reported elsewhere in those files are real. Fix the syntax error (or exclude the file deliberately) and re-scan to cover them. Separately, one or more rules could not re-parse an embedded snippet in 1 file(s) (e.g. a workflow `run:` block read as shell). Those files WERE scanned and their other rows are unaffected; only those rules' view of those snippets is missing.
REDACTED
REDACTED
REDACTED
REDACTED
REDACTED
+ 9 more group(s) — more in Appendix A; the complete list is findings.md.
What to do
Resolve the 5 REDACTED finding(s) in Static Analysis (SAST) — start with REDACTED (2), REDACTED (2), REDACTED. — One of this dimension's main actionable groups (5 issue-level).
Resolve the 4 REDACTED finding(s) in Static Analysis (SAST) — start with REDACTED, REDACTED, REDACTED. — One of this dimension's main actionable groups (4 issue-level).
No action in Static Analysis (SAST) — all 11 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 (11 issue-level, 0 of them charged here).
Detailed fixes: d29_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether any dependency has a known published vulnerability (CVE), direct or transitive, in ANY ecosystem the repository declares — Dart pub, Elixir and Erlang via Hex, Go modules, Java and Kotlin via Maven/Gradle, JavaScript/npm, .NET/NuGet, PHP/Composer, Python/PyPI, RubyGems, Rust/Cargo and Swift.
Method: Dependency-CVE scan across every ecosystem the repository declares, scored ONCE. Three sources are unioned and deduplicated by advisory identity (rule id + alias closure, CVE<->GHSA) scoped to package+version, keeping the worst severity: `osv-scanner --recursive` over osv.dev for Dart pub, Elixir/Hex (and Erlang, whose `rebar.lock` syft first converts to a CycloneDX SBOM the scanner reads, with rows attributed back to the lock), Go, Java and Kotlin via Maven/Gradle (and Scala, whose sbt build's pinned direct declarations are written into a CycloneDX SBOM the scanner reads, with rows attributed back to the build file), npm, PHP/Composer, Python/PyPI, RubyGems, Rust/Cargo and Swift; `trivy fs --scanners vuln` for npm lockfiles; and `dotnet list package --vulnerable --include-transitive` for NuGet (with per-advisory collapse of the project x target-framework fan-out), plus a DECLARED-dependency arm that resolves a published gem's gemspec against rubygems.org where no Gemfile.lock is committed. `SeverityScore(c,h,m,l, normalizer 8.0)`. NotApplicable only when NO ecosystem is readable; if any applicable ecosystem could not be scanned the findings are REPORTED and the score is withheld. Supersedes the npm and OSV arms, retired 2026-09-05.
Resolve the 3 Critical CVE finding(s) in Dependency Vulnerabilities — start with REDACTED (3). — One of this dimension's main actionable groups (3 issue-level).
Resolve the 2 High CVE finding(s) in Dependency Vulnerabilities — start with REDACTED (2). — One of this dimension's main actionable groups (2 issue-level).
Resolve the 1 High vulnerability finding(s) in Dependency Vulnerabilities — start with REDACTED. — One of this dimension's main actionable groups (1 issue-level).
Detailed fixes: d30_recommendation.md · top locations in Appendix A, every location in findings.md.
Resolve the 1 High IaC finding(s) in IaC & Container Security — start with REDACTED. — One of this dimension's main actionable groups (1 issue-level).
Resolve the 3 Medium IaC finding(s) in IaC & Container Security — start with REDACTED (3). — One of this dimension's main actionable groups (3 warning-level).
Detailed fixes: d31_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether anyone still has living knowledge of each file, or it has been orphaned — last understood long ago by someone now gone quiet. The sibling of the bus factor: D16 asks who owns it, D34 asks whether anyone still knows it.
Method: File orphaning as total living-knowledge decay below one focused-commit's worth within a year, computed per-file from the D16 decay model. Exhaustive, deterministic over fixed history.
273 of 273 significant source file(s) are orphaned — their living knowledge has decayed to nothing, so no one currently understands them. The largest is metagpt/strategy/experience_retriever.py. Counted over 273 of the 516 production source files in this repository: the rest are under the ~2,400-byte size floor this dimension measures over.
Orphaned file · ×270REDACTED:1
Most significant orphaned file · ×3metagpt/strategy/experience_retriever.py:1
Dormant codebase
What to do
Resolve the 270 Orphaned file finding(s) in Knowledge Freshness — start with REDACTED (5), schema.py (3), role_zero.py (2). — One of this dimension's main actionable groups (270 recommendation-level).
Resolve the 3 Most significant orphaned file finding(s) in Knowledge Freshness — start with experience_retriever.py, editor.py, common.py. — One of this dimension's main actionable groups (3 recommendation-level).
Resolve the 1 Dormant codebase finding(s) in Knowledge Freshness. — One of this dimension's main actionable groups (1 recommendation-level).
Detailed fixes: d34_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether files that change together actually belong together — pairs that repeatedly co-change in git history despite having no explicit code dependency, surfacing the hidden/logical coupling (and boundaries in the wrong place) a static scan can't see.
Method: Pairwise co-occurrence over the per-commit file sets in git history (production source only — tests and generated dropped): Degree-of-Coupling = shared ÷ min individual revisions, reported above noise floors (each file ≥10 revisions, ≥5 shared commits, ≥50% strength); sweeping commits excluded. Deterministic over fixed history.
Coverage: Population: PRODUCTION source files only — test and generated files are dropped before pairing, so a class co-changing with its own test (trivially ~100%) can't drown the real production↔production coupling. Pairs ranked by Degree-of-Coupling. A non-source file is never a coupling PARTICIPANT either: documentation, schemas, config and data files are dropped with the rest, so a code↔docs pair — a command and the reference page that restates it — is not reported however strongly the two co-change; nor is coupling that runs THROUGH a build step or config file.
Resolve the 14 Change coupling finding(s) in Change Coupling — start with architect.py, base_provider.py, search_engine_serpapi.py. — One of this dimension's main actionable groups (14 warning-level).
Resolve the 1 Change-coupling hub finding(s) in Change Coupling — start with prompt.py. — One of this dimension's main actionable groups (1 warning-level).
Detailed fixes: d35_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether the build pipeline provides supply-chain integrity — generated provenance/attestation, signed artifacts (cosign/sigstore), an SBOM, and pinned build actions. Presence of the configuration, not a runtime guarantee.
Method: Supply-chain provenance/signing read deterministically from CI/build config (.github/workflows, .gitlab-ci.yml, azure-pipelines, Jenkinsfile, .circleci) + the release surface: four signals — generated provenance/attestation (SLSA/in-toto/actions-attest), artifact signing (cosign/sigstore/gitsign), an SBOM (syft/sbom-action/*.spdx.json/*.cdx.json), and SHA-pinned build actions — scored 10·present/denom. NotApplicable without a build pipeline. Detects configuration presence, not runtime enforcement.
+ 6 more group(s) — more in Appendix A; the complete list is findings.md.
What to do
Resolve the 2 REDACTED finding(s) in Supply-chain Provenance & Signing — start with REDACTED, REDACTED. — One of this dimension's main actionable groups (2 issue-level).
Resolve the 1 REDACTED finding(s) in Supply-chain Provenance & Signing. — One of this dimension's main actionable groups (1 warning-level).
Resolve the 1 REDACTED finding(s) in Supply-chain Provenance & Signing — start with REDACTED. — One of this dimension's main actionable groups (1 warning-level).
Detailed fixes: d36_recommendation.md · top locations in Appendix A, every location in findings.md.
What it measures: Whether the repository publishes a coordinated-vulnerability-disclosure policy (SECURITY.md or security.txt) with a reporting contact, so finders know how to report a vulnerability. Presence of a policy file with a contact, not whether the policy is adequate or honoured.
Method: Vulnerability-disclosure policy read deterministically from the repo: a SECURITY.md (root/.github/docs) or .well-known/security.txt / security.txt, regex-checked for a reporting contact (email / URL / mailto). Present + contact → 10; present without a contact → 4; NotApplicable when no policy file exists (it may live off-repo). Detects the policy file's presence + contact, not its adequacy.
What it measures: Whether any dependency the repository declares is published as MALICIOUS rather than merely vulnerable — a package that is an attacker's work, in any ecosystem osv-scanner reads. Scored apart from D30 because the answer is binary: there is no safe version to upgrade to, and the fix is to remove the package and rotate every credential it could have read.
Method: The same dependency scan D30 reads, partitioned on the scanner's own classification rather than rescanned: a row is MALICIOUS when its id is in the `MAL-` space (the ossf/malicious-packages feed) OR its `database_specific.cwe_ids` carries `CWE-506` ("Embedded Malicious Code"). Both channels are structural; the summary text is deliberately NOT read, because a malicious-package record whose summary says only "Critical severity vulnerability" is a real shape ([GHSA redacted]) and a text matcher misses it. Scored BINARY: any surviving row is 0, whatever its severity and however many CVEs sit beside it — a hostile dependency is not a quantity. Applicability and degradation are D30's: NotApplicable only when no ecosystem is readable, and an unscannable ecosystem degrades rather than reading clean. SCORED, not informational.
What it measures: Whether anyone still ships security patches for the platform this repository RUNS ON — the runtime it pins and the framework majors its own constraints hold it to. Separate from D12 because the question differs: a current Django on an end-of-life Python is perfectly up to date and completely unsupported, and the fix is a migration rather than a version bump. What the repository says it merely SUPPORTS is never charged.
Method: End-of-life PLATFORM read from the repository's own declarations and graded against a FROZEN, dated table of vendor support dates — no network, no feed, no API, so this dimension answers identically inside a closed scan fence. Two subjects: a RUNTIME the project pins (a single or all-end-of-life TargetFramework, a .nvmrc or .python-version, a requires-python CAP) and a FRAMEWORK major a dependency constraint cannot move off (a caret, tilde or exact version; `vue@^2.7.16` pins Vue 2). A FLOOR is deliberately never charged — `requires-python = ">=3.8"` states what a package SUPPORTS, not what it runs on — and a multi-target project is charged only when EVERY target is out of support. Runtime 4.0/product capped 8.0, framework 1.5 capped 4.5. The table is safe to freeze because a statement about support that ended in the past cannot become false: it loses recall as it ages, never precision, and a test asserts every entry predates the freeze date. Disjoint from D31 (a container image's OS layer) and D29 (the toolchain a CI workflow installs). Abstains when the repository declares no platform this pass reads — never scores it clean.
0 end-of-life runtime(s) and 0 end-of-life framework(s), read from 0 platform declaration(s) and 75 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.
Other · Architecture — How the codebase splits by code ROLE — domain, application, infrastructure, test, generated. The significance map behind the knowledge/coupling weighting, and a DDD signal in its own right: a thin domain core under fat infrastructure is the anemic-domain smell, quantified. How each file's role is decided, because the split is only as good as that: a generated name or a build-output tree makes it Generated, a test project makes it Test, and otherwise the file's NAMESPACE and PATH words are matched against fixed vocabularies in a fixed ORDER — domain, then infrastructure, then application — so a file whose words hit two layers is counted under the earlier one. A production file matching none of them counts as application, so that share reads 'application or unclassified' rather than a measured application layer. Roles come from naming convention, never from what the code does. On this repository the split was taken from the source tree on disk rather than from a loaded .NET workspace, so a file's role is decided by its PATH segments alone — no declared namespace was available to add to the evidence — and generated output is excluded from the census entirely rather than counted as a generated share.
Method: Roslyn line-count by code ROLE: every source file classified Domain/Application/Infrastructure/Test/Generated by namespace + path convention (the shared CodeRoleClassifier), then significant lines summed per role. Deterministic; the advisory score is the business-logic (domain+application) share of production code.
Coverage: Population: ALL source files, each bucketed into ONE of five roles (Domain/Application/Infrastructure/Test/Generated) by namespace + path convention — a file whose layer isn't named in the convention falls to Application (the neutral default), and the split is line-count, not semantic depth or business value.
What to do
The domain core is a small share of production code, but most of the rest matched no layer vocabulary at all — so this is not yet an anemic-domain finding. The namespace/path convention could not place that code, which makes the composition above a statement about the naming, not about the design. Name the layers (or check that the repository's conventions differ from the ones this check knows) before reading a thin domain into it.
Other · Architecture — Whether singleton services avoid mutable shared instance state that concurrent callers would race on.
Method: Roslyn scan: singleton field mutations unguarded by lock or Interlocked, per type; syntax-based guard detection. Deterministic, traceable per field.
Other · Architecture — Whether the project-reference graph is acyclic (cycles block independent build/deploy and signal eroding boundaries).
Method: Project reference cycles via elementary-DFS over real .csproj references, using the engine shared with D5/D7; cyclic versus acyclic. Exhaustive, deterministic.
Other · Architecture — Whether dependencies point inward (Domain ← Application ← Infrastructure/Web) — the clean-architecture dependency rule, checked across the project graph.
Method: Layer violations by name-segment inference (Domain/Core to Application to Infrastructure/Web) over the project-reference graph. Exhaustive over all projects, deterministic.
Other · Security — Whether access is authorized by default — a framework authorization attribute/decorator or policy, or imperative guard methods (throw-on-violation) called from handlers.
Method: Roslyn scan: [Authorize] usage and authorization policies, plus imperative throw-on-violation guard methods detected via syntax. Deterministic.
This repository serves requests — a request handler (app.run() (metagpt/tools/openapi_v3_hello.py:29) — and no route guard, auth-gate middleware, global guard or imperative check that refuses a caller (401/403, an Unauthorized/Forbidden error) was found: its endpoints may be unprotected. — metagpt/tools/openapi_v3_hello.py:29
What to do
Protect endpoints by default-deny: a global authentication guard or middleware with explicit public opt-outs, or a guard on every route, plus named role/permission rules for what an authenticated caller may do.
Maturity · Maturity — Whether the repo and its projects have a README, and whether it's substantive and current.
Method: Filesystem scan: README presence, word count, and headings for depth; git history for staleness. Exhaustive across root and project dirs, deterministic.
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.
Add an 'Architecture' / 'How it works' section to the root README — the high-level shape.
Add a README to the 1 of 2 project(s) that lack one — worth up to 1 pts.
Maturity · Maturity — Whether key decisions (ADRs) and the high-level shape (C4/diagrams) are written down.
Method: Filesystem scan: ADR folder/naming conventions or content, plus Mermaid/PlantUML/C4/architecture.md discovery. Exhaustive, deterministic.
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.
Maturity · Maturity — Whether the repo is organised deliberately — src/test separation and consistent project naming.
Method: Filesystem scan: src/test folder separation and namespace-prefix consistency (majority RootNamespace agreement). Exhaustive across projects, deterministic.
Production code isn't grouped under a src/ folder — it's spread across several top-level directories, so there's no one place that says 'this is the product'.
What to do
Group production code under src/ (or split deliberately, e.g. backend/ + frontend/) so production and tooling code aren't mixed at the root.
Maturity · Maturity — Whether the README actually describes the code that exists (LLM-judged, advisory).
Method: Judged by language model at low temperature: README accuracy versus actual projects, within a disclosed tolerance. Advisory, not a measured number.
docs/README_FR.md links to `docs/ROADMAP.md`, but `docs/docs/ROADMAP.md` does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong. — docs/README_FR.md:138
docs/README_JA.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong. — docs/README_JA.md:78
docs/install/cli_install.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong. — docs/install/cli_install.md:45
docs/install/cli_install_cn.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong. — docs/install/cli_install_cn.md:45
What to do
Reconcile the README with reality: docs/README_FR.md links to `docs/ROADMAP.md`, but `docs/docs/ROADMAP.md` does not exist; docs/README_JA.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it; docs/install/cli_install.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it; docs/install/cli_install_cn.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it.
Readiness · Readiness — Whether an automated pipeline builds and tests every change.
Method: Filesystem scan: CI workflow files (.github/workflows, .gitlab-ci.yml, etc.) for build and test stages. Exhaustive, deterministic.
Do you agree with this assessment?
P10 · Library API & versioning10.0 / 10Exemplary○ Nothing flagged
Readiness · Readiness — For a library: a deliberate (small) public API surface and explicit semantic versioning so consumers can depend on it safely.
Method: Roslyn scan: public API surface area and semantic-versioning markers (SemVer attributes, changelog entries) for libraries; off .NET, a library is the ecosystem's publication act (an npm package that is not private and names an entry point, a PyPI distribution with a build system, a Rust library crate, a Maven/Gradle module that publishes, a Go module with no package main, a gemspec, a Composer library, a SwiftPM library product, a pub.dev or Hex package), its surface is the share of types the language model records as public (Rust, Swift, Java, Kotlin, Go, Dart; not measured where the model records no type visibility or, as in TypeScript, only module-level export), and its version is read from the manifest, a semver CHANGELOG, release tooling or semver git tags. Exhaustive, deterministic.
Do you agree with this assessment?
P2 · Observability6.0 / 10Adequate✓ Tool-verified
Readiness · Readiness — Whether the code is diagnosable in production — structured logging, tracing/metrics, health checks.
Only 2/3 runnable modules use logging (modules with no entry point or server are excluded — they are libraries a runnable module hosts). Silent: `metagpt/environment/minecraft/mineflayer`.
What to do
Extend structured logging to the remaining runnable modules so everything you run is diagnosable in production.
Consider OpenTelemetry tracing/metrics (opentelemetry-sdk) and a health-check endpoint (a /health route) for operability.
Readiness · Readiness — Whether SAST, secret/dependency scanning and performance benchmarking are wired in (presence, not runtime).
Method: Filesystem scan: SAST configuration, dependency-update automation, secret scanning, and a benchmark harness or benchmark step — in this repository's own ecosystem. Exhaustive, deterministic.
No static application security testing detected. For this repository's stack, add bandit, `semgrep --config=p/python`, or CodeQL's python pack as a CI step. What was searched, so you can tell an absence from a miss: the 7064 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.
What to do
Add a SAST step to CI running what this repository's stack ships: bandit, `semgrep --config=p/python`, or CodeQL's python pack — 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.
Readiness · Readiness — Whether releases are automated and safely reversible (probes, rolling updates, approval gates) — from manifests/pipeline files, not the live environment.
Method: Filesystem scan: deployment manifests/IaC (K8s YAML, Helm, Terraform) for rolling updates, probes, approval gates, migration hooks. Exhaustive, deterministic.
What to do
Make sure a person approves each release. The release job names an environment, but its approval rules live in the code host's settings, where Watchdog can't see them. Check that a reviewer must approve each release, or publish releases as drafts first, so a bad build can be stopped before anyone downloads it.
Readiness · Readiness — Whether releases are traceable — a maintained changelog and explicit version stamping.
Method: Filesystem scan: changelog file presence and version tags in csproj or git tags. Exhaustive, deterministic.
No CHANGELOG/HISTORY/RELEASES file — what shipped when isn't easy to reconstruct for support or audit. (Versioning/tagging makes releases traceable, but a changelog records the what.)
What to do
Keep a changelog (e.g. Keep-a-Changelog) recording what shipped in each release.
Readiness · Readiness — Whether outbound HTTP calls are wrapped in resilience (retry/timeout/circuit-breaker) so a failing dependency doesn't cascade.
Method: Source scan: outbound HTTP clients and what bounds them — resilience handlers (Polly, AddStandardResilienceHandler) on .NET; on Go, the JVM, Python, JavaScript/TypeScript, Ruby, PHP, Rust, Elixir, Swift, Dart and Erlang, a timeout, deadline, retry or breaker beside each call, or a process-wide client default (a framework-wide deadline such as Drupal core's, Laravel's or actix's awc counts). Exhaustive, deterministic.
`requests.post(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout. (×4) — metagpt/environment/minecraft/minecraft_ext_env.py:101, metagpt/environment/minecraft/minecraft_ext_env.py:182, metagpt/environment/minecraft/minecraft_ext_env.py:190, …
`requests.get(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout. (×3) — metagpt/ext/aflow/data/download_data.py:18, metagpt/utils/common.py:863, metagpt/utils/common.py:1234
`aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout. (×6) — metagpt/tools/metagpt_text_to_image.py:72, metagpt/tools/openai_text_to_embedding.py:65, metagpt/tools/openai_text_to_image.py:45, …
What to do
Pass `timeout=` on every `requests`/`httpx` call (requests has no default and will wait forever), mount an `HTTPAdapter(max_retries=Retry(...))` on shared sessions, and wrap calls to flaky dependencies in `tenacity` retries or a `pybreaker` circuit breaker.
Readiness · Performance — Whether asynchronous code stays responsive — it avoids sync-over-async blocking (a .NET .Wait()/.GetAwaiter().GetResult(), a time.sleep or blocking HTTP call inside a Python coroutine, a *Sync call inside an async JavaScript function, block_on inside a Rust async fn, runBlocking inside a Kotlin suspend function, block() inside a Reactor publisher) that stalls a thread or event loop and risks deadlock, and, where the code is a reusable library on .NET, awaits with ConfigureAwait(false) so it never captures and stalls its caller's context.
Method: Production-source scan: sync-over-async blocking counted everywhere — .Wait()/.GetAwaiter().GetResult() in .NET; off .NET, read from the language model, a blocking call inside an async function (Python, TS/JS, Rust, Kotlin, Swift, Dart) or inside a Java method returning a Reactor Mono/Flux or a Scala method returning a Future or effect — and, for a .NET library with ≥5 awaits, the share of awaits using ConfigureAwait(false). Deterministic, syntax/text detection.
`run` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — examples/build_customized_agent.py:47
`on_event_retrieve` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/environment/minecraft/minecraft_env.py:315
`on_event_execute` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/environment/minecraft/minecraft_env.py:354
`get_graph_optimize_response` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/aflow/scripts/optimizer_utils/graph_utils.py:97
`run` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/android_assistant/actions/manual_record.py:44
`_run_gpt35_max_tokens` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/actions/st_action.py:61
`_run_gpt35` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/actions/st_action.py:79
`_run_gpt35_wo_extra_prompt` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/actions/st_action.py:103
`run_reflect` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/reflect/reflect.py:94
`update_role_env` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/roles/st_role.py:534
`_react` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/ext/stanford_town/roles/st_role.py:581
`rebuild_class_views` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — REDACTED:713
`shell_execute` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs. — metagpt/tools/libs/shell.py:10
`fs.existsSync` in `handleError` blocks the event loop until it finishes — a blocking call inside async code stalls the event loop — every other request waits for as long as it runs. — REDACTED:365
`fs.readFileSync` in `handleError` blocks the event loop until it finishes — a blocking call inside async code stalls the event loop — every other request waits for as long as it runs. — REDACTED:367
What to do
Python: await the async equivalent (asyncio.sleep, an async HTTP client such as httpx.AsyncClient or aiohttp, asyncio.create_subprocess_exec), or move the blocking call off the loop with `await asyncio.to_thread(...)`; never call asyncio.run inside a coroutine — await the coroutine.
TypeScript/JavaScript: use the promise APIs (fs/promises, a promisified child_process.execFile, the async zlib/crypto functions) and await them instead of the *Sync variants.
Do you agree with this assessment?
R1 · Type Safety10.0 / 10Exemplary✓ Tool-verified
React / JS · Code Health — How much of the frontend is typed TypeScript vs untyped JavaScript.
Method: Frontend file inventory: the share of typed TypeScript vs untyped JavaScript across the source tree. Deterministic, exhaustive over frontend files.
React / JS · Code Health — Near-exact copy-pasted blocks of substantial extent across the frontend (the D4 clone algorithm over JS/TS tokens, D-386): a block is reported only where its copies still agree on most of their own identifiers and literals, or were renamed as they were pasted but kept most of their constants, and where the copies carry enough code to stand on their own or the copied extent reaches 30 lines — so a re-implementation sharing neither names nor values, and a small pasted declaration, are both found and deliberately not reported, and a clean R10 is not a claim that nothing was copied.
Method: Near-exact copy-pasted blocks of substantial extent across the frontend (the D4 clone algorithm run over JS/TS tokens). Masking finds the candidates; a block is reported when its copies still agree on most of their own identifiers and literals, or when a renamed copy still agrees on most of its constants, AND the copies carry enough code to stand on their own — or when the copied extent reaches 30 lines. So a re-implementation sharing neither names nor values, and a small pasted declaration, are deliberately not counted. Deterministic.
REDACTED:302 · REDACTED:312 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. — REDACTED:302
metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:38 · metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:48 — all 2 copies are in the same file, and the CITED SPAN is not a self-contained block — it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead — the whole function, component or branch these lines sit in — and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported. — metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:38
REDACTED:365 · REDACTED:376 — the two spans are one implementation copied and then locally edited — 60 tokens are still identical, in the same order in both spans, with only local edits between them. The copies have already begun to drift, which is this row's finding: an edit made to one and not the other changes behaviour silently. Diff the two spans first to learn what genuinely differs, then extract the shared core into one module both sites use, passing the differences in as parameters — or, if one copy exists only because the other could not be imported from its context, make one of them the single source the other is generated or re-exported from. If one copy is no longer reachable, delete it rather than letting it shadow the live one. — REDACTED:365
What to do
Act on each finding's own remediation rather than one rule: the move depends on what recurs. Where the copies are executable blocks, give the shared part one home and call it from each site; where they are declarations, a listing, a specialisation already delegating to its base, or one shape repeated per entity, there is no call site and the move is a shared type, a generated set or a factory — sometimes there is nothing to extract.
React / JS · Code Health — Per-function cyclomatic/cognitive complexity from the token-level function scanner (D-386) — real branching, not a regex heuristic.
Method: Per-function cyclomatic/cognitive complexity from a token-level function scanner (real branching, not a regex heuristic), computed over every frontend function. Deterministic.
collectAll has cyclomatic complexity 21 and cognitive complexity 55; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:18
collect has cyclomatic complexity 15 and cognitive complexity 16; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:350
handleError has cyclomatic complexity 13 and cognitive complexity 14; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — REDACTED:338
findFromVein has cyclomatic complexity 11 and cognitive complexity 33; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/BlockVeins.ts:4
(anonymous) has cyclomatic complexity 11 and cognitive complexity 18; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — REDACTED:52
ItemFilter has cyclomatic complexity 11 and cognitive complexity 10; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive sits below cyclomatic here, so much of the count is breadth — arms side by side rather than stacked — and splitting per arm would leave a function per arm; group the work between the checks into named steps instead. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes. — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:310
What to do
Break down the listed branch-heavy functions; aim P95 cyclomatic ≤ 5.
Do you agree with this assessment?
R3 · Large Files7.9 / 10Strong✓ Tool-verified
React / JS · Code Health — How many source files exceed the large-file threshold.
Method: Components/modules exceeding the large-file threshold, counted exhaustively across the frontend source tree. Deterministic.
metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts has 423 significant lines (blank lines excluded), over the 400-line bar, and contains logic — a file this long is usually several responsibilities in one module. — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:1
What to do
Split each oversized file along the responsibilities already in it, into smaller focused modules in the same package.
Do you agree with this assessment?
R6 · Tooling6.7 / 10Strong✓ Tool-verified
React / JS · Readiness — Whether the project wires up test, lint and typecheck — detected from each package.json script's COMMAND (eslint / tsc / vitest / jest / playwright), not just its name, and corroborated against CI-workflow invocations so a tool run only in CI still counts.
Method: package.json scanned for test/lint/typecheck script wiring. Deterministic presence check.
test ✓ · lint ✗ · typecheck ✓ — read from this repository's package.json scripts and corroborated against its CI workflows. A script counts when its name or command matches the step: `test` for the suite, `lint` or `prettier` for linting, `typecheck`/`type-check`/`tsc` for type checking. ✗ therefore means no script or CI step under those names was found, NOT that the step is absent from your pipeline — a task invoked by a runner this check does not read, or named something else entirely, is not seen and is worth confirming before acting on a cross. A ✓ means the wiring is DECLARED — a script or CI step under those names exists. It is not a statement that the step passes, or that it runs at all: nothing here installs a dependency or executes a suite.
What to do
Add eslint as package.json scripts and run them in CI.
Do you agree with this assessment?
R7 · Dead Code8.2 / 10Strong✓ Tool-verified
React / JS · Code Health — Files unreachable from every application/tooling/test entry point, and exports nothing imports (module-graph reachability, D-386).
Method: Dead code: files unreachable from every application/tooling/test entry point plus exports nothing imports, via module-graph reachability. Deterministic, exhaustive over the import graph.
Unreachable from the 2 application, 0 tooling and 0 test entry point(s) detected in this repo. Gate removals on `npm run build` — an undetected custom entry would make these reachable.
no import path from any entry point (2 application, 0 tooling, 0 test roots considered), and no other file in the scanned tree imports it — nothing in-repo names this module at all, which is the strongest form of this claim the import graph can make — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/TaskQueue.ts
What to do
Delete the dead files and unused exports — every line is maintenance cost and rebuild-estimate inflation with zero runtime value.
React / JS · Readiness — npm dependency truthfulness (D-386): unused dependencies, imports not declared anywhere, and type-/test-only packages shipped as production deps.
Method: npm dependency truthfulness: unused dependencies, imports declared nowhere, and type-/test-only packages shipped as production deps — from the manifest + import graph. Deterministic.
Declared in metagpt/environment/minecraft/mineflayer/package.json but never imported anywhere in that package or its workspace members — no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it. (×3)
What to do
Remove unused dependencies, declare unlisted imports explicitly, and demote type-/test-only packages to devDependencies.
React / JS · Architecture — Import cycles in the module graph (D-386) — files that can only be understood and changed together.
Method: Import cycles in the module graph, detected exhaustively over JS/TS imports (the same cycle detection as the .NET coupling dimension). Deterministic.
Other · Code Health — Whether the code avoids sync-over-async (deadlock-prone blocking on tasks) and async void.
Method: Roslyn syntax scan: async methods scanned for .Wait()/.GetAwaiter().GetResult() and async-void outside event handlers. Deterministic, hard fact per invocation.
This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`). (×10) — metagpt/environment/minecraft/minecraft_env.py:339, metagpt/environment/minecraft/minecraft_env.py:375, metagpt/ext/aflow/scripts/optimizer_utils/graph_utils.py:112, …
The task this creates is not kept anywhere. The event loop holds only a weak reference to its tasks, so a task nobody references can be garbage-collected before it finishes (Python's documentation for `asyncio.create_task`: save a reference to the result); and nothing ever awaits it, so an exception it raises is never handled — it surfaces, if at all, as "Task exception was never retrieved" in a log. Keep the task: `await` it, gather it, start it in an `asyncio.TaskGroup` (`async with asyncio.TaskGroup() as tg: tg.create_task(…)`), or, for genuine fire-and-forget, add it to a set and `task.add_done_callback(tasks.discard)` with a callback that also reads its exception. — metagpt/tools/libs/terminal.py:103
Other · Code Health — Whether any branch is dead by construction — a switch arm whose label can never equal a case-normalised subject, or an `else if` whose predicate the arm above has already swallowed.
Method: Roslyn syntax + semantics: switch labels compared against the subject's own case normaliser, and if/else-if chains checked for a literal an earlier arm's containment test already swallows. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X13 · Undrained process stream10.0 / 10Exemplary○ Nothing flagged
Other · Code Health — Whether a child process that has BOTH standard streams redirected drains both — reading one to the end while the other is never read deadlocks once the child fills the unread pipe.
Method: Roslyn syntax + semantics: ProcessStartInfo launches with both streams redirected, checked for a drain of each stream across the enclosing type. On a repository with no .NET source it reads JavaScript/TypeScript off the engine’s own token stream (test, vendored and minified paths not) with the same rule: a `spawn` imported from `child_process` whose stdout and stderr are both pipes (no options, no `stdio`, or `stdio` of `'pipe'`), bound to a local that never leaves its scope, where exactly one of the two streams is read, the other never, and the child’s `close`/`exit` (or the read stream’s end) is awaited; a shell redirect in the call’s arguments or a `kill` of the child suppresses it. The same rule reads Python’s `subprocess.Popen`, Dart’s `Process.start`, Ruby’s `Open3.popen3`, and Scala’s JDK process starts (`new ProcessBuilder(…).start()` with no `redirectErrorStream`/`redirectError`/`redirectOutput`/`inheritIO`, `Runtime.getRuntime.exec`) where one of `getInputStream`/`getErrorStream` is read and the other never while `waitFor()` is called or the read stream is read to its end. Deterministic, provable per finding. Advisory.
Other · Security — Whether a hand-rolled public/private IP check can be walked past — a method that unwraps IPv4-mapped IPv6 but returns the opposite verdict for the same host written as IPv4-compatible, 6to4 or NAT64.
Method: Roslyn syntax + semantics: methods that unwrap IPv4-mapped IPv6 and hand-roll IPv4 range carve-outs, checked for whether the IPv6 branch also accounts for the IPv4-compatible, 6to4 and NAT64 embeddings. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X15 · Unvalidated length from an untrusted reader10.0 / 10Exemplary○ Nothing flagged
Other · Security — Whether a length read out of the stream being parsed is bounded before it is allocated or read — an unchecked count taken from the input lets the input choose the allocation.
Method: Roslyn syntax + semantics: integer lengths read from a BinaryReader and spent on a bulk read or an array allocation, checked for any comparison or bounding call on the value anywhere in the method. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a loop that shortens a string until it fits a length budget has a floor — one with none grinds the value down to the empty string, or past it into a negative-length `Substring`.
Method: Roslyn syntax + semantics: while/do loops whose body's only effect on a string is to drop its last character, checked for whether anything — a direct comparison on the length, a body guard, a break — bounds that length below. On a repository with no .NET source it reads JavaScript/TypeScript off the engine’s own token stream (test, vendored and minified paths not) with the same rule: a `while`/`do` loop whose body’s one assignment to a value is `x = x.slice(0, -1)` or `x = x.slice|substring|substr(0, x.length - 1)`, driven by a condition that reads `x.length` only as a term of a larger expression — never compared directly, never tested for truthiness, and with no other read of `x` — and whose body has no `break`, `return`, `throw` or `if` naming `x`. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X17 · Uncapped recursion over a caller-supplied document10.0 / 10Exemplary○ Nothing flagged
Other · Security — Whether a walk that recurses through a JSON/XML tree handed in by its caller bounds how deep it will go — an uncapped walk lets the document's nesting choose the stack depth, and the resulting StackOverflowException cannot be caught.
Method: Roslyn syntax + semantics: methods that take a JSON/XML document node and call themselves with a child of it, reachable from an externally-callable member of the same type that accepts a document, checked for any depth parameter, descent counter or threaded arithmetic anywhere in the walk. On a repository with no .NET source it reads TypeScript off the engine’s own token stream (test, vendored, generated and minified paths and `.d.ts` not) with the same rule: a function or method with a parameter typed as a document value — `unknown`, `any`, `object`, `Record<string, unknown|any>`, a JSON alias (`JsonValue`, `JSONObject`, …) or a DOM node global the file does not rebind — that calls itself (bare, or through `this` for a method, or hands itself to a call over the value as in `value.map(walk)`) with something it took out of that value and never through an ancestor accessor such as `closest()` or `parentElement`, that is exported or reached from an exported function (a public method of the same exported class) taking such a value, and that names no depth, level, nesting, recursion, remaining or budget anywhere and threads no `+`/`-` arithmetic through a self-call. Plain JavaScript is not read: with no annotation nothing tells a parsed document from a tree the code built itself. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a type's disposal matches what it OWNS — releasing what it created, leaving alone what it was handed, and not declaring a finalizer for state that has nothing unmanaged to finalize.
Method: Roslyn syntax + semantics: every assignment to a disposable field is read to decide whether the type CREATED the value or was handed it, and the type's disposal is checked against that answer — an injected interface it disposes, a value it constructed and never releases, a finalizer on a type holding nothing unmanaged, and a disposable local whose every reference is a plain member read. A value handed to a container that disposes its contents (a parent control's `Controls` collection, a component `IContainer`) is released by that container and is not reported; generated code is out of population. On a repository with no .NET source the same ownership questions are read in JavaScript/TypeScript off the engine’s own token stream (test, vendored, generated and minified paths not): a class declaring `dispose()`, `[Symbol.dispose]()` or `[Symbol.asyncDispose]()` that disposes a field it was handed through a constructor parameter typed as a repository interface or resolved by a dependency-injection container; that assigns a field only ever from `new X(…)` of a disposable class and neither releases it anywhere in the class nor names it in its disposal member or a method that member calls, nor hands it to anything else; and a `const`/`let` local built from literals only whose every reference opens a statement operating on a non-release member of it. A class is disposable when every repository declaration of its name declares or inherits a disposal member, or when it is a documented library disposable (`vscode` EventEmitter, CancellationTokenSource and Disposable; three.js geometries, materials, textures, render targets, renderers, controls and composers). The finalizer arm has no JavaScript counterpart: a class cannot declare one. Dart is read for the owned-and-never-released arm: a Flutter `State` (or a class declaring `dispose()`/`close()`) whose library-private field is written only with direct creations of a framework controller, `FocusNode`, `StreamController` or periodic `Timer` (or a `.listen(…)` into a field declared `StreamSubscription`), which nothing in the class or its library releases (`dispose`/`close`/`cancel`) and which is never handed on except as a named argument. Ruby is read for the owned-and-never-released arm and the abandoned-local arm: a class declaring an instance `close`, `dispose`, `shutdown`, `stop`, `disconnect` or `terminate` whose instance variable is written only with a blockless core descriptor creation (`File.open`/`new`, `Tempfile`, `Dir.open`, `IO.popen`, the `socket` and `openssl` socket classes) that no method of the class closes and that is never handed on (passed, returned, stored, exposed by `attr_reader`, delegated) — a class whose superclass or mixin lies outside the repository is not judged — and a blockless creation read through and dropped (`File.open(path).read`) or held in a local that is never closed, returned, passed or stored (a `&:read` block-pass, an `autoclose: false` borrow and a `fileno` hand-over are not abandonment). PHP is read for the same two arms: a class (not a trait, and not one using a trait) declaring an instance `close`, `dispose`, `shutdown`, `stop`, `disconnect` or `terminate` whose `private` property (or a `final` class's `protected` one) is written only with a direct core `fopen`, `tmpfile`, `popen`, `proc_open`, `fsockopen`, `stream_socket_client`/`server` or `opendir` that nothing in the class closes (`fclose`, `pclose`, `closedir`, `unset`, a reset to `null`) and that is never handed on, and a handle held in a function's local, or read through as the argument of a reader, that is never closed, returned, passed, captured or stored; a `php://` stream, `curl_init`, `SplFileObject`, `PDO` and a function the repository declares under the core name are not read. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a method that temporarily changes state belonging to the whole process — the working directory, an environment variable — puts it back on EVERY path: a restore reached only when nothing throws leaks the change to the rest of the process.
Method: Roslyn syntax + semantics: method bodies that write the process working directory or an environment variable and write it back in the same body, checked for whether that restore sits in a `finally`/`catch` or only on the straight-line path. On a repository with no .NET source the same rule reads production JavaScript/TypeScript off the engine’s own token stream (test, vendored and minified paths not): `process.chdir`, `process.env.NAME =`/`["NAME"] =` and `delete process.env.NAME`, and Deno’s `Deno.chdir`/`Deno.env.set`/`Deno.env.delete`, paired per function body (a nested function or arrow is its own body, and module top-level code is none), where the last write puts back a local the body captured from the same global or deletes a variable the first write set, with at least one statement between them; a write in a `catch`/`finally` of that body silences it. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a `when` guard is free of side effects — a guard that increments a counter or assigns while deciding whether its arm matches applies that change during PATTERN MATCHING, on an arm that may not be selected, and skips it entirely when a short-circuit to its left answers first.
Method: Roslyn syntax: `when` guards on case labels and switch-expression arms, read for a mutation (`++`/`--`/assignment) sitting in a position the guard's own `&&`/`||`/`??`/`?:`/`?.` can skip. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a method that TAKES a lock or semaphore and gives it back from a flag-guarded `finally` returns the value that flag implies — reporting success while the guard hands the primitive back admits a second caller the exclusion was there to keep out, and reporting failure while the guard keeps it leaves nothing to ever give it back.
Method: Roslyn syntax: `try` statements whose `finally` releases a synchronisation primitive under a bare local-bool guard, where the method also TOOK that same primitive before the `try`, checked for a `return` of a bool literal whose value disagrees with the flag state the method's own straight-line assignments put it in. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether the work a diagnostic log line costs is paid only when that line is wanted — C# evaluates a call's arguments BEFORE the call, so a trace/debug message joined or projected out of a collection is built in full on every pass, and then discarded by a sink the shipped configuration leaves switched off.
Method: Roslyn syntax: log calls at a diagnostic level (a `Log`-prefixed method naming Trace/Debug/Verbose, or a bare `Debug`/`Trace`/`Verbose` on a receiver named for a logger), whose argument list is read for a call whose cost scales with a sequence — a LINQ operator, a materialisation, `string.Join`, a serializer — with no enclosing level check or conditional-compilation region. On a repository with no .NET source it reads JavaScript/TypeScript off the engine’s own token stream (test, vendored and minified paths not) with the same rule: a `debug`/`trace`/`verbose` call on a receiver named for a logger, or a `log`-prefixed method naming the level, whose argument calls an array operator (`map`/`filter`/`reduce`/`sort`/…), `Array.from`, `Object.keys/values/entries`, `JSON.stringify`/`util.inspect` over anything but a literal, or an array `join` — outside any arrow or function passed as an argument, which the logger calls only when the level is on — with no enclosing `if`, `&&` or `?:` whose condition names a level, a level string, or the `NODE_ENV`/`__DEV__`/`DEV` build switch. Deterministic, provable per finding. Advisory.
`debug` at line 277 is called with an argument built by `msg.model_dump_json()` (line 277), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on. — metagpt/roles/engineer.py:277
`debug` at line 281 is called with an argument built by `msg.model_dump_json()` (line 281), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on. — metagpt/roles/engineer.py:281
`debug` at line 285 is called with an argument built by `msg.model_dump_json()` (line 285), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on. — metagpt/roles/engineer.py:285
What to do
In Python, put the construction behind the logger's own check (`if logger.isEnabledFor(logging.DEBUG):`), or pass the collection itself with a `%s` placeholder (`logger.debug("Items %s", items)`) so the logging module renders it only when the record is emitted. The placeholder alone is not the fix when the argument is still built first: it defers the formatting, not a `json.dumps`, a `join` or a comprehension in the argument, and an f-string defers nothing at all.
Do you agree with this assessment?
X24 · Document value interpolated into markup unescaped10.0 / 10Exemplary○ Nothing flagged
Other · Security — Whether text read out of the document being converted is escaped before it is written into generated markup — a value the document's author chose, interpolated into an attribute the surrounding literal delimits, can close that attribute and open another.
Method: Roslyn semantic model over the whole compilation: a string-typed `Value`/`InnerText`/`InnerXml`/`Text` member declared inside `DocumentFormat.OpenXml` or `System.Xml` is a taint SOURCE, propagated through assignments, returns, arguments, tuple elements and string composition to its transitive closure, then read at interpolated-string holes that sit in a markup position the surrounding literal itself delimits. Escaper/encoder calls and enclosing validator conditions cut the flow. Flow- and container-insensitive by construction. A second arm needs no provenance at all and reports a type that CONTRADICTS ITSELF — the same expression escaped at one delimited markup hole and interpolated raw at another hole in the same markup position of the same type, which the type's own escaping proves is a defect without knowing where the value came from. On a repository with no .NET source it reads JavaScript/TypeScript off the token stream with the same rule: a DOM read of raw document text (`getAttribute`, `textContent`, `innerText`, `nodeValue`) is the source, propagated through local bindings and string composition, and judged at template-literal and concatenation holes in the same two delimited markup positions; escapers and validating conditions cut it, and documentation-site, test, vendored and minified scripts are not read. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a value the caller is invited to supply is the value the type actually uses — a constructor parameter stored in a private field that nothing ever reads while the default it was given is spelled out a second time at the site that should have read it, a keyed lookup that falls back to a different setting than the one its key names while the same type falls back to the matching one for that same key, or a culture-sensitive parse given no format provider by a type that feeds its own settable culture to the same kind of parse elsewhere, or a number an entry point writes to standard output under the host's culture while the same entry point formats with the invariant culture elsewhere. Either way, every caller who supplies a value silently gets something else.
Method: Roslyn syntax: private instance fields of a non-partial type assigned in a constructor from one of its own parameters with a `??` fallback, checked for whether anything in the type body reads the field and whether that same fallback expression is spelled out again outside the constructor; and `??` fallbacks onto a member access from a lookup call carrying exactly one string literal, grouped by that key across the type and checked for a fallback member whose folded name disagrees with the key while a sibling site for the same key agrees with it. On a repository with no .NET source the first two arms read JavaScript/TypeScript off the engine’s own token stream (tests included, bundles and vendored paths not): a `#x`, `private` or `private` parameter-property instance field filled in the constructor from a parameter (or one member of one) through `??`/`||` or a parameter default, never read anywhere in the file by name, whose constructed default is spelled again in the class body; and `lookup("key") ?? s.member` grouped by key per class, or per module outside every class. The culture arm has no JavaScript counterpart: its parses take no locale. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether a value handed from a callback to the body that waits on it crosses on something built to be crossed — a `Queue<T>`/`List<T>`/`Dictionary<K,V>` written inside an event handler and read back outside it is mutated by two flows at once, and the semaphore or completion source beside it orders how MANY items exist while leaving the collection's own head, tail and backing array unprotected.
Method: Roslyn syntax: method, accessor, local-function and lambda bodies that declare BOTH a non-thread-safe generic collection (`Queue`/`Stack`/`List`/`Dictionary`/`HashSet`/`Sorted*`/`LinkedList`) and a synchronisation primitive (`SemaphoreSlim`/`TaskCompletionSource`/`ManualResetEvent(Slim)`/`AutoResetEvent`/`CountdownEvent`) as locals, then read for a `+=`-registered lambda that raises that primitive while the body outside every lambda waits on it — and, in that scope, a mutating call on the collection inside the lambda paired with a mention of it outside. Any `lock` in the scope abstains it. On a repository with no .NET source the same handoff is read in Java off the engine’s own token stream (test source sets, vendored and demonstration paths not): an `ArrayList`/`LinkedList`/`ArrayDeque`/`PriorityQueue`/`Hash*`/`LinkedHash*`/`Tree*` local and a `CountDownLatch`/`Semaphore`/`CompletableFuture` local, a lambda or anonymous class that raises the primitive and mutates the collection, and a wait outside it; any `synchronized` or `lock()` abstains the body. Because each of those primitives orders what the callback wrote before raising it, only a touch that provably overlaps the callback is convicted: one after the registration and before the next wait, or one in a loop registered-before, waiting on every pass and not declaring the collection. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X27 · Collection changed while being enumerated10.0 / 10Exemplary○ Nothing flagged
Other · Code Health — Whether a `for` loop leaves the `dict`, `set` or `deque` it is walking alone — CPython's iterators over those check that the collection has not changed size since the loop began, so a body that removes from (or empties) the very collection the loop is walking makes the next step raise `RuntimeError: dictionary changed size during iteration` and the remaining items are never seen.
Method: Roslyn syntax + semantics: `foreach` statements whose body calls a structural mutator (`Add`/`Remove`/`Clear`/`Insert`/…) on the very expression the loop is enumerating. Two arms. ARM A — the source is a concrete fragile BCL collection, or a live `Keys`/`Values` view over one, and the mutator resolves to that same collection's own member; concurrent and immutable collections and arrays are outside the population by construction, since their enumerators survive a structural change. ARM B — the source is an argument-less accessor CALL on a receiver whose body is in source: the accessor must return a stored field VERBATIM and a sibling member must structurally change that same field, both read off the implementations rather than from the members' names. A mutation the loop provably exits immediately after (`break`/`return`/`throw`/`goto`), or one written inside a nested loop or a lambda, is counted and never reported. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X28 · Index access outside its own emptiness guard10.0 / 10Exemplary○ Nothing flagged
Other · Code Health — Whether a condition that tests a value for emptiness indexes that same value only where the test holds — an `||` written one parenthesis too far to the left leaves an index access outside the guard beside it, so the empty case the guard exists to anticipate reaches the index and throws.
Method: Roslyn syntax only, no semantic model: the OUTERMOST `&&`/`||` of every boolean condition, read for a symbol the condition tests for emptiness (`string.IsNullOrEmpty`/`IsNullOrWhiteSpace`, a `Length`/`Count` comparison against a literal, `Any()`, a `Length`/`Count` pattern, or a comparison against `""`) and ALSO indexes. Each `symbol[...]` access is placed by a boolean-reachability walk from the access up to the outermost connective: an access is COVERED when some enclosing step has it in the right operand and the left operand, under the truth value that step forces, proves the symbol non-empty — a recursion over `&&`/`||` whose true- and false-directions are asymmetric. A finding needs BOTH an uncovered access and a covered one on the same symbol in the same condition, which is the agreeing twin that separates a misplaced parenthesis from an unrelated length test. Bare index accesses with no emptiness test in the condition are neither counted nor reported; a non-identifier receiver and a lambda nested inside the condition are outside the population. Deterministic, provable per finding. Advisory.
Do you agree with this assessment?
X29 · Per-element action decided by a fixed element10.0 / 10Exemplary○ Nothing flagged
Other · Code Health — Whether a decision taken once per element is taken ABOUT that element — a test inside a counted loop that reads a fixed subscript of the very collection its guarded statement indexes by the loop variable applies element zero's answer to all of them, so the elements that differ from it are all handled wrongly, and in the same direction.
Method: Roslyn syntax only, no semantic model: every `for` statement declaring exactly ONE loop variable, and every `if` inside its body that is not under a nested loop or a lambda. A site enters the population when the `if`’s condition never mentions the loop variable while the statement it guards indexes some collection by that variable ALONE (`c[i]`; `c[i + 1]` and `c[i, j]` are outside it). A finding additionally needs the AGREEING TWIN at the same-collection grain: the condition must read THAT SAME collection at a subscript that does not move — written into the condition, or reached through a local declared BEFORE the loop, so an alias bound inside the body is not followed. Both collection expressions must be simple identifiers. On a repository with no .NET source the same rule reads JavaScript/TypeScript off the engine’s own token stream (tests included, bundles and vendored paths not): a `for (let|var|const x = …; …; …)` with one declarator and a braced body, an alias followed only when it is declared before the loop in a block that encloses it and never assigned inside the loop. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether exceptions are handled rather than silently swallowed or rethrown with lost stack traces.
Method: Roslyn syntax scan: every catch clause counted; empty catches and bare rethrows flagged. Population is all catch clauses, not estimated. Deterministic, hard fact.
`except` 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. (×2) — metagpt/document_store/qdrant_store.py:70, metagpt/memory/brain_memory.py:122
An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it. (×12) — metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:56, metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:145, metagpt/ext/cr/actions/code_review.py:126, …
`except Exception` 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. (×21) — metagpt/environment/stanford_town/stanford_town_ext_env.py:257, metagpt/ext/stanford_town/actions/wake_up.py:16, metagpt/ext/stanford_town/actions/task_decomp.py:74, …
What to do
Swallowed exception (caught, then discarded)
Do you agree with this assessment?
X30 · Support guard that admits what it rejects10.0 / 10Exemplary○ Nothing flagged
Other · Code Health — Whether a guard written as a NEGATED `||` says what its author meant — `!(a || b || x != k)` is `!a && !b && x == k` by De Morgan, so a bail-out that mixes capabilities the code needs with a fault it refuses turns inside out: it fires only where the capabilities are ABSENT, and lets every value the fault term names walk straight into the body that cannot handle it.
Method: Roslyn syntax only, no semantic model: every logical-not whose operand is a parenthesised `||` chain of two or more disjuncts, flattened (a left-nested `a || b || c` read once would see `(a || b)` as one disjunct). A site enters the population on that shape alone. A finding additionally needs the disjuncts to DISAGREE in polarity: at least one bare boolean read — an identifier or member access, never an invocation, which is a predicate rather than a capability flag — and at least one `x != <constant>`, the only form that negates into an exact-value pin (`== null` negates into a looser requirement and is outside the fault set). Consistently-polarised disjunctions, all-fault or all-capability, are counted and never reported; a negated `&&` is outside the population entirely. No same-receiver gate: it was measured to cost a real defect and remove no false positive. Deterministic, provable per finding. Advisory.
Other · Code Health — Whether log calls use message templates (queryable) rather than interpolated strings.
Method: Roslyn syntax scan: every log call-site counted; interpolated-string first-argument violations flagged. Population is all log calls, not estimated. On a repository with no .NET source it reads JavaScript/TypeScript off the engine’s own token stream (test, vendored and minified paths not) with the same rule: a `trace`/`debug`/`info`/`warn`/`error`/`fatal`/`verbose`/`silly`/`http`/`log` call on a receiver named for a logger, in a package whose own or an enclosing `package.json` declares a logger that carries values as fields (pino, pino-http, nestjs-pino, Fastify, winston, bunyan, tslog, LogTape, roarr), whose first deciding argument is a template literal with substitutions; an object-literal fields argument is stepped over, a plain string message clears the call. Python is read the same way: a `debug`/`info`/`warning`/`error`/`exception`/`critical`/`log` call on a logger in a file that imports the standard library’s `logging` or structlog (loguru, which formats at the call, is not judged), whose message is a whole f-string with a non-constant field; a `%`-formatted, `.format()`-ed or concatenated message is not convicted, as in C#. PHP is read the same way: a PSR-3 level call (`emergency`…`debug`, `log`) on a logger (`$logger`, `$this->logger`, Laravel’s `Log::`, `logger()`, `\Drupal::logger()`) in a package whose `composer.json` requires a PSR-3 logger or a framework that hands one out (psr/log, Monolog, Laravel, Symfony, Drupal, CakePHP), or a file that imports one, whose message is a double-quoted string interpolating a variable; a single-quoted message clears the call, and `sprintf` or `.` concatenation is not convicted, as in C#. Dart is read the same way: a `trace`/`debug`/`info`/`warn`/`error`/`fatal` call on Sentry’s structured logger (`Sentry.logger`) whose message is a whole string literal interpolating a value (`$name`, `${…}`); the `Sentry.logger.fmt` template API clears the call. Dart that logs only through loggers with one message and no fields (package:logging, package:logger, talker, dart:developer) is not applicable rather than a reach gap. Ruby is read the same way: a `trace`/`debug`/`info`/`warn`/`error`/`fatal` call on the console gem’s `Console` (declared by a Gemfile, gemspec or Gemfile.lock, or required) or, where SemanticLogger, Ougai or dry-logger is declared or required, on a receiver named for a logger (`logger`, `@logger`, `Rails.logger`, `log`), whose first deciding argument is, as the whole argument, a double-quoted string interpolating a non-constant value (`#{…}`, `#@ivar`); a plain literal clears the call, keyword arguments are the fields, and a block, `%`-format or `+` concatenation is not convicted. Ruby that logs only through the standard Logger (Rails.logger) is not applicable rather than a reach gap. Deterministic.
Other · Code Health — Whether strict null checking is enabled and not undermined by heavy `!` assertion — TypeScript's `strictNullChecks` (which `strict` turns on) is what makes `string` exclude `null` and `undefined`, and the postfix `!` is the operator that silences it.
Method: Roslyn compiler-options scan: NullableContextOptions per project; null-forgiving (!) suppression density per 1k syntax nodes. Deterministic, adoption plus suppression penalty.
Do you agree with this assessment?
Reference — by lens
The score is the rank-weighted fold of these lenses (worst-heaviest), each including its meta-dimensions; a lens with a Critical contributor is capped at Fair (its band reads "gated by …") and is never the strongest area however high its average.
Unscored — 4 check(s) recorded observations but carry no score
These checks ran and found something, but they do not carry a score — either by design (an advisory check reports evidence rather than grading it) or because they could not be scored here. They are excluded from the score for that reason, not because there was nothing to see.
P12 CI test-gate honesty — 1 observation(s) recorded · Reported, not scored — this card publishes what the CI gate does with the test inventory rather than grading it. The findings above are its output.
SC1 Supply-chain hygiene — 1 observation(s) recorded · Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
X10 Duplicated predicate — 12 observation(s) recorded · Advisory — this card reports evidence and never carries a score.
X7 Silent fallback defaults — 2 observation(s) recorded · Advisory — this card reports evidence and never carries a score.
Not evidenced — 1 control(s) we could not find positive evidence for
These checks grade a working control, and the repository shows no evidence of one. That is deliberately not scored as a zero: a repository cannot show an ops runbook, a database TTL or an infrastructure-side audit log, so absence of evidence here is not evidence the control is missing. It is also not a statement that the check is irrelevant to this codebase — the thing it grades applies; we just could not see it. Excluded from the score either way.
P5 DR & Backup — not evidenced — repo shows no backup/RTO/RPO controls; absence of evidence is not evidence of a working control
Not included — 52 check(s) not relevant to this codebase
These checks had nothing to measure here (no tests, no git history, the codebase is small, or the architecture style doesn't apply), so they're omitted above rather than scored low.
AC1 Text alternatives — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC2 Forms & labels — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC3 Page structure — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC4 Keyboard semantics — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC5 ARIA correctness — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC6 Visual & motion safety — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AC7 A11y enforcement — Frontend below the scale floor (6 DOM element(s) < 25) — too little surface to assess accessibility.
AX1 Captive dependencies — Not applicable: this repository's JavaScript 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; this repository's Python 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; this repository's TypeScript 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.
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
AX6 Interface segregation — no exported interface declares behaviour
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 — compose up failed (exit 17 — an image could not be built) — failed to solve: nikolaik/python-nodejs:python3.9-nodejs20-slim: failed to resolve source metadata for docker.io/nikolaik/python-nodejs:python3.9-nodejs20-slim: failed to do request: Head "https://registry-1.docker.io/v2/nikolaik/python-nodejs/manifests/python3.9-nodejs20-slim": Forbidden; runtime evidence skipped 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.
C3 Audit Trail — No personal data detected in a persisted data model — no PII-named field (email, first_name, date_of_birth, phone, …) or stored credential in a Django, SQLAlchemy, SQLModel, Peewee, Tortoise or MongoEngine model, a migration or a SQL schema — and no database or data-store client (Django ORM, SQLAlchemy, psycopg, PyMongo, …) in the source either, so this repository keeps no sensitive data whose changes an audit trail would record. If it does (through a store configured outside this repository, for instance), the trail belongs to wherever that data is stored.
C4 Data Retention — No personal data detected in a persisted data model — no PII-named field (email, first_name, date_of_birth, phone, …) or stored credential on a Django, SQLAlchemy, SQLModel, Peewee, Tortoise or mongoengine model, in a migration or in a SQL schema — and no database or data-store client (django.db, sqlalchemy, psycopg2, pymongo, sqlite3, …) imported either, so this repository keeps no personal data whose lifetime a retention limit would bound.
C5 Data-Subject Rights — No personal data detected in a persisted data model — no PII-named field (email, first_name, date_of_birth, phone, …) or stored credential on a Django, SQLAlchemy, SQLModel, Peewee, Tortoise or mongoengine model, in a migration or in a SQL schema — and no database or data-store client (django.db, sqlalchemy, psycopg2, pymongo, sqlite3, …) imported either, so this repository keeps no personal data for a data subject to erase, export or consent over.
D10 Test Quality — ~18401 lines of test source are present (.py) 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.
D11 Test Reliability — Test reliability not included — the .py suite was found but not re-run
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.
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+ projects each declaring an entity of their own. 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 — No inline comments to assess — comment value is not applicable here.
D25 ADR Conformance — no ADRs to check
D27 Navigability — D27 counts a call into the standard library or a dependency as unresolved for this repository's language (.py), so too few call sites counted as resolved to assess navigability. 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.
D39 IL Efficiency — D39 measures the IL emitted by a .NET build; this repository has no .NET solution or project files, so the dimension does not apply.
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.
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
D8 Code Coverage — Coverage not included — suite not readable by the collector
DM1 Domain Modelling — not scored — this repository shows only 1 of the 3 signals this lens looks for (110 value object(s))
ED1 Event-Driven — not scored — this repository shows none of the 3 signals this lens looks for
ED5 Idempotency — no mutating command handlers or message consumers detected — idempotency check not applicable
ES1 Event Sourcing — not scored — this repository shows none of the 3 signals this lens looks for
GD1 Unfinished & placeholder code — no source files were read — this check reads C#, F#, JavaScript/TypeScript, Dart, Ruby and Scala, 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
P8 Schema migrations — Django is declared, but the schema-migration mechanism could not be identified. Our limit, not a verdict on this repository.
P9 Domain vs controller coverage — no coverage report found on disk — produce a coverage report in a standard format (`coverage run -m pytest` then `coverage xml`) and commit it — a hosted scan measures a clone of the repository, so a report that exists only in a working tree, a CI runner's or your own, never reaches it; the artefact is commonly gitignored, so `git add -f` that one file (or un-ignore its path) and commit it alongside the code it measures, or wire coverage collection into CI, to enable this cross-layer check
PF1 Benchmark discipline — Not applicable: no benchmark suite was found. This check searched for a pytest-benchmark or pytest-codspeed dependency with tests taking the `benchmark` fixture, an asv.conf.json with its `time_`/`mem_`/`peakmem_` benchmarks, or a pyperf Runner, 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 applicable: Python runs on a garbage-collected runtime that gives a program no allocation-control idiom to choose on a hot path — no pools, stack allocation or value types — so allocation awareness is not something this code can be rated on.
R11 Import Boundaries — No recognizable feature-sliced/layered src layout — boundary rules not applicable.
R4 Test Coverage — the JS/TS workspace (19 production file(s)) has no JavaScript/TypeScript test, but it is 2.99% of this repository's production source and the other 97.01% carries 18,401 line(s) of test code this pass cannot read — an incidental frontend's reachability is not the repository's test posture, so it is not scored as one
R5 Dependency Freshness — no package-lock.json — dependency freshness not measured (would require an npm lockfile); JS/npm CVEs are scored in D30 (Dependency Vulnerabilities), which answers every ecosystem
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.
X2 Cancellation propagation — no C# was loaded; this repository's Python was read, and no request in it can be cancelled by a caller — a Python request takes no token: asyncio cancels the task and trio or anyio the scope that made it, from outside the call, and requests, httpx, aiohttp and gRPC take a timeout, not a cancellation
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.
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.
X6 Hand-rolled structured-format parsing — Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
X9 Subsumed condition operand — Advisory — this card reports evidence and never carries a score, so there is nothing missing here.
Appendix A — Findings (grouped)
The findings behind the scores, grouped by severity, then by dimension and kind. The high-severity issues are enumerated in full below; items per group are capped at 25 with any overflow stated explicitly per group, never silently truncated. The complete machine-readable list of every finding (all severities) is the companion findings.md in this report's bundle.
Banned license: pylint — `pylint` 4.1.3 is published on PyPI under `GPL-2.0-or-later`, which this policy bans, and it is in the SHIPPED closure of this repository — so it is installed by everything that depends on this repository, not just by its test environment. A distribution offering SEVERAL licences is a choice and is only charged when every one of them is banned. Replace the package, or record an accepted exception.
TodoComment examples/build_customized_agent.py:64— # todo will be SimpleWriteCode() — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment examples/build_customized_agent.py:85— # todo will be first SimpleWriteCode() then SimpleRunCode() — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/document.py:101— # TODO: excel, csv, json, etc. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/const.py:58— # TODO to store `storage` under the individual generated project — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/actions/write_code_plan_and_change_an.py:102— # TODO: Implement subtraction, multiplication, and division operations — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/base/base_serialization.py:59— # TODO could try dynamic import — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/minecraft/minecraft_env.py:63— # TODO: maybe fix 10054 now, a better way is isolating env.step() like voyager — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/minecraft/minecraft_env.py:66— # TODO add skills_dir — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/werewolf/werewolf_ext_env.py:180— # TODO — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/sela/evaluation/evaluation.py:37— # TODO — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment tests/metagpt/test_schema.py:110— # TODO — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/werewolf/werewolf_ext_env.py:255— # TODO in case of tie vote, check who was voted first — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/werewolf/env_space.py:37— # TODO should be tuple of variable length — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/werewolf/env_space.py:40— # TODO should be tuple of variable length — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/environment/werewolf/env_space.py:44— # TODO should be tuple of variable length — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/exp_pool/manager.py:112— # TODO: filter by metadata — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:112— # TODO Modify Op_param. When op_param.action is FINISH, how to solve this ? — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:168— # TODO Test for assignment, This error is eupiped with the next. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:200— # TODO here will cause `IndexError: list index out of range`. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:205— # TODO global — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/sela/runner/custom.py:15— # todo — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment REDACTED:176— # TODO: Check if this is correct or +1 — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment REDACTED:208— # TODO: Check this — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment REDACTED:355— # TODO: add new insights — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
TodoComment metagpt/ext/stanford_town/actions/task_decomp.py:15— # TODO SOMETHING HERE sometimes fails... See screenshot — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
Swallowed exception (caught, then discarded) metagpt/document_store/qdrant_store.py:70— `except` 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.
Swallowed exception (caught, then discarded) metagpt/environment/stanford_town/stanford_town_ext_env.py:257— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/wake_up.py:16— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/task_decomp.py:74— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:19— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:57— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:105— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:146— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:182— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:218— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/run_reflect_action.py:251— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/inner_voice_action.py:16— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_hourly_schedule.py:35— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_daily_schedule.py:16— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_action_details.py:213— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_action_details.py:252— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_action_details.py:289— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_action_details.py:326— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/ext/stanford_town/actions/gen_action_details.py:359— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/memory/brain_memory.py:122— `except` 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.
Swallowed exception (caught, then discarded) metagpt/utils/human_interaction.py:37— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/utils/human_interaction.py:45— `except Exception` 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.
Swallowed exception (caught, then discarded) metagpt/utils/a11y_tree.py:278— `except Exception` 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.
FixmeComment metagpt/schema.py:582— # FIXME: if LLM generates cyclic tasks, this will result in infinite recursion — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/document.py:189— # FIXME: These judgments are difficult to support multiple programming languages and need to be more general — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/document.py:208— # FIXME: These judgments are difficult to support multiple programming languages and need to be more general — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment REDACTED:407— # FIXME: json instruction会带来格式问题，如："Project name": "web_2048 # 项目名称使用下划线", — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment REDACTED:369— # FIXME: device=device — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/ext/werewolf/actions/experience_operation.py:16— # FIXME: some hard code for now — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/ext/werewolf/roles/witch.py:20— # FIXME: hard code to split, restricted为"Moderator"或"Moderator,角色profile" — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/ext/werewolf/roles/moderator.py:70— # FIXME: hard code truncation — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/ext/werewolf/roles/base_player.py:86— # FIXME: hard code to split, restricted为"Moderator"或"Moderator, 角色profile" — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/provider/openai_api.py:285— # FIXME — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/roles/qa_engineer.py:56— # FIXME: a bit hack here, only init one action to circumvent _think() logic, — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/roles/project_manager.py:33— # FIXME: Read and edit files requires more steps, consider later — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/roles/di/role_zero.py:367— # an actual TASK intent misclassified as QUICK, correct it here, FIXME: a better way is to classify it correctly in the first place — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment REDACTED:67— # fixme 避免不跟随，生成过多nodes — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment REDACTED:222— # fixme: 需要产生回退，当前节点不可用时回退到父节点，产生新的节点继续探索 — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/tools/tool_recommend.py:214— # FIXME: needs more sophisticated tokenization — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/tools/libs/editor.py:873— # FIXME: support replacing *all* occurrences — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment metagpt/utils/common.py:363— # FIXME: use ActionNode instead. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment tests/metagpt/test_software_company.py:20— # FIXME: we're now using "metagpt" cli, so the entrance should be replaced instead. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment tests/metagpt/test_prompt.py:170— # fixme: 添加icon lora — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment tests/metagpt/test_prompt.py:188— # fixme: update prompt (根据需求细化prompt） — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
FixmeComment tests/metagpt/actions/test_action_node.py:93— # FIXME: ADD MARKDOWN SUPPORT. NEED TO TUNE MARKDOWN SYMBOL FIRST. — source code is not a task system: move the work to your tracker and leave a reference instead (e.g. `# REF: #123`), so the task is planned where tasks live and the ticket links back to the code.
Sync-over-async blocking examples/build_customized_agent.py:47— `run` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/environment/minecraft/minecraft_env.py:315— `on_event_retrieve` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/environment/minecraft/minecraft_env.py:354— `on_event_execute` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/aflow/scripts/optimizer_utils/graph_utils.py:97— `get_graph_optimize_response` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/android_assistant/actions/manual_record.py:44— `run` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/actions/st_action.py:61— `_run_gpt35_max_tokens` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/actions/st_action.py:79— `_run_gpt35` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/actions/st_action.py:103— `_run_gpt35_wo_extra_prompt` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/reflect/reflect.py:94— `run_reflect` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/roles/st_role.py:534— `update_role_env` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/ext/stanford_town/roles/st_role.py:581— `_react` is async and calls time.sleep — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking REDACTED:713— `rebuild_class_views` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking metagpt/tools/libs/shell.py:10— `shell_execute` is async and calls subprocess.run — a blocking call inside async code stalls the event loop — every other task on it waits for as long as it runs.
Sync-over-async blocking REDACTED:365— `fs.existsSync` in `handleError` blocks the event loop until it finishes — a blocking call inside async code stalls the event loop — every other request waits for as long as it runs.
Sync-over-async blocking REDACTED:367— `fs.readFileSync` in `handleError` blocks the event loop until it finishes — a blocking call inside async code stalls the event loop — every other request waits for as long as it runs.
Change coupling: architect.py ↔ project_manager.py metagpt/roles/architect.py:1— `metagpt/roles/architect.py` and `metagpt/roles/project_manager.py` change together 88% of the time (21 of the 24 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 21 shared commits counted here, the most recent 3 are `ff79389d` refactor_the_architect; `513d1317` feat: +similarity_search; `9685c910` bugfix: 解决单测耗时超长问题: 1)移除agentops装饰器 2)屏蔽所有单测报错文件 3)减少单测时的无用信息输出 — run `git show` on any of them.
Change coupling: base_provider.py ↔ bedrock_api.py metagpt/provider/bedrock/base_provider.py:1— `metagpt/provider/bedrock/base_provider.py` and `metagpt/provider/bedrock_api.py` change together 84% of the time (16 of the 19 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 16 shared commits counted here, the most recent 3 are `1b8df6ff` update bedrock claude usage; `ff477066` add openrouter reasoning; `8c84de74` update bedrock — run `git show` on any of them.
Change coupling: search_engine_serpapi.py ↔ search_engine_serper.py metagpt/tools/search_engine_serpapi.py:1— `metagpt/tools/search_engine_serpapi.py` and `metagpt/tools/search_engine_serper.py` change together 83% of the time (10 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 10 shared commits counted here, the most recent 3 are `f1d102e7` add url params for SERPAPI/SERPER search engine; `9deb9f35` add url params for SERPAPI/SERPER search engine; `fc412e55` fix tests/metagpt/learn/test_google_search.py error — run `git show` on any of them.
Change coupling: index.py ↔ retriever.py metagpt/rag/factories/index.py:1— `metagpt/rag/factories/index.py` and `metagpt/rag/factories/retriever.py` change together 76% of the time (13 of the 17 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 13 shared commits counted here, the most recent 3 are `2fdfd703` remove milvus from RAG; `ceccd660` Update pre-commit's error; `ac4eb309` 删除codecov — run `git show` on any of them.
Change coupling: operator_an.py ↔ workflow.py metagpt/ext/aflow/scripts/operator_an.py:1— `metagpt/ext/aflow/scripts/operator_an.py` and `metagpt/ext/aflow/scripts/workflow.py` change together 71% of the time (12 of the 17 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 12 shared commits counted here, the most recent 3 are `c3903412` Update Operator Optimize Method. (at that commit the files were still `examples/ags/w_action_node/operator_an.py` and `examples/ags/w_action_node/graph.py`); `02c7c4ea` Update 混乱版本 (at that commit the files were still `examples/ags/w_action_node/operator_an.py` and `examples/ags/w_action_node/graph.py`); `2937d9a1` Update 粗糙版本 优化 (at that commit the files were still `examples/ags/w_action_node/operator_an.py` and `examples/ags/w_action_node/graph.py`) — run `git show` on any of them.
Change coupling: random_search.py ↔ REDACTED metagpt/ext/sela/runner/random_search.py:1— `metagpt/ext/sela/runner/random_search.py` and `REDACTED` change together 67% of the time (10 of the 15 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 10 shared commits counted here, the most recent 3 are `25299e1f` change research assistant to experimenter; `61492d9f` add data type; fix instruction generation (at that commit the file was still `metagpt/ext/sela/experimenter/random_search.py`); `eb460d3e` make timeout as argument (at that commit the files were still `expo/experimenter/aug.py` and `expo/MCTS.py`) — run `git show` on any of them.
Change coupling: REDACTED ↔ workflow.py REDACTED:1— `REDACTED` and `metagpt/ext/aflow/scripts/workflow.py` change together 59% of the time (10 of the 17 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 10 shared commits counted here, the most recent 3 are `2937d9a1` Update 粗糙版本 优化 (at that commit the files were still `examples/ags/benchmark/humaneval.py` and `examples/ags/w_action_node/graph.py`); `bdfa6eb5` Update (at that commit the files were still `examples/ags/benchmark/humaneval.py` and `examples/ags/w_action_node/graph.py`); `3fc3d217` Update (at that commit the files were still `examples/ags/benchmark/humaneval.py` and `examples/ags/w_action_node/graph.py`) — run `git show` on any of them.
Change coupling: product_manager.py ↔ project_manager.py metagpt/roles/product_manager.py:1— `metagpt/roles/product_manager.py` and `metagpt/roles/project_manager.py` change together 58% of the time (14 of the 24 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 14 shared commits counted here, the most recent 3 are `9685c910` bugfix: 解决单测耗时超长问题: 1)移除agentops装饰器 2)屏蔽所有单测报错文件 3)减少单测时的无用信息输出; `bbb65c96` feature: 主流程支持配置agentops; `8f745335` feature: 主流程支持配置agentops — run `git show` on any of them.
Change coupling: azure_tts.py ↔ metagpt_oas3_api_svc.py metagpt/tools/azure_tts.py:1— `metagpt/tools/azure_tts.py` and `metagpt/tools/metagpt_oas3_api_svc.py` change together 55% of the time (6 of the 11 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 6 shared commits counted here, the most recent 3 are `71b4922f` feat: fix coding; `6794645f` feat: 改异步; `8aa30c35` feat: +hello.py oas3 — run `git show` on any of them.
Change coupling: run_experiment.py ↔ REDACTED metagpt/ext/sela/run_experiment.py:1— `metagpt/ext/sela/run_experiment.py` and `REDACTED` change together 52% of the time (14 of the 27 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 14 shared commits counted here, the most recent 3 are `4c541c2e` reorder import; `a46f5753` clean up input argument (at that commit the files were still `expo/run_experiment.py` and `expo/MCTS.py`); `989a3b42` allow max depth passing in (at that commit the files were still `expo/run_experiment.py` and `expo/MCTS.py`) — run `git show` on any of them.
Change coupling: summarize_code.py ↔ write_code_review.py metagpt/actions/summarize_code.py:1— `metagpt/actions/summarize_code.py` and `metagpt/actions/write_code_review.py` change together 50% of the time (8 of the 16 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 8 shared commits counted here, the most recent 3 are `ee0b9d20` feat: new/inc/patch pass; `431e5361` changed tasks to task; `8baa6d09` refine writeprd code — run `git show` on any of them.
Change coupling: web_browser_engine_playwright.py ↔ web_browser_engine_selenium.py metagpt/tools/web_browser_engine_playwright.py:1— `metagpt/tools/web_browser_engine_playwright.py` and `metagpt/tools/web_browser_engine_selenium.py` change together 50% of the time (6 of the 12 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency between them. They sit in the same directory, but in this ecosystem each file is its own module — a sibling reference still needs an import — so the missing import edge is real: the coupling runs through shared behaviour, not a declared dependency. If they duplicate structure, extract the common part into one unit; otherwise the coupling is hidden and worth breaking. You can check this without leaving the row: of the 6 shared commits counted here, the most recent 3 are `033211eb` update timeout; `d150cc35` refine code; `ede23b2f` Unified WebPage object return for the WebBrowserEngine API — run `git show` on any of them.
Change coupling: manager.py ↔ reflection.py metagpt/exp_pool/manager.py:1— `metagpt/exp_pool/manager.py` and `metagpt/utils/reflection.py` change together 50% of the time (5 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 5 shared commits counted here, the most recent 3 are `6052d8b9` update exp_pool decorator; `4650b7bd` change req in exp; `29c61a7f` experience pool — run `git show` on any of them.
Change coupling: decorator.py ↔ reflection.py metagpt/exp_pool/decorator.py:1— `metagpt/exp_pool/decorator.py` and `metagpt/utils/reflection.py` change together 50% of the time (5 of the 10 commits that touched whichever of the two files changed less often, counting a file under its earlier names as well — a repo-wide or module-wide sweep is evidence about the sweep rather than about any pair inside it and is left out of BOTH sides of this ratio, while a dependency bump, a formatter/rename sweep, or a commit whose edit to one of the two files was a tool directive such as //go:generate or whitespace only is left out of the shared count ONLY, so the two sides are not taken over identical commit sets) with no explicit dependency — the edge is real but nothing declares it. Read the pair before acting: if one registers itself into the other through a hook or an initialiser, the missing dependency is DELIBERATE — the registration is the link, and it is meant not to be an import — and the thing to add is a comment on each side naming the other, not a merge; if they simply belong together, co-locate them; if neither holds, the coupling is hidden and worth breaking. You can check this without leaving the row: of the 5 shared commits counted here, the most recent 3 are `6052d8b9` update exp_pool decorator; `4650b7bd` change req in exp; `29c61a7f` experience pool — run `git show` on any of them.
Outbound HTTP without resilience metagpt/environment/minecraft/minecraft_ext_env.py:101— `requests.post(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/environment/minecraft/minecraft_ext_env.py:182— `requests.post(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/environment/minecraft/minecraft_ext_env.py:190— `requests.post(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/ext/aflow/data/download_data.py:18— `requests.get(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/metagpt_text_to_image.py:72— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/openai_text_to_embedding.py:65— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/openai_text_to_image.py:45— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/search_engine_bing.py:73— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/search_engine_serpapi.py:59— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/tools/search_engine_serper.py:55— `aiohttp.ClientSession(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/utils/common.py:863— `requests.get(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/utils/common.py:1234— `requests.get(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Outbound HTTP without resilience metagpt/utils/report.py:108— `requests.post(` makes an outbound HTTP call, and nothing bounds it: no timeout, deadline, retry or circuit breaker is set for it here, and the client has no process-wide default. A slow or failing dependency will hold this service's request, thread or connection until the call gives up on its own — or never, for a client with no default timeout.
Swallowed exception (empty catch) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:56— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:145— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/ext/cr/actions/code_review.py:126— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/ext/stanford_town/actions/summarize_conv.py:17— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/ext/stanford_town/actions/new_decomp_schedule.py:31— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/ext/stanford_town/actions/gen_iter_chat_utt.py:19— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/ext/stanford_town/actions/agent_chat_sum_rel.py:17— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/tools/tool_registry.py:57— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/utils/human_interaction.py:70— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/utils/common.py:153— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/utils/common.py:178— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Swallowed exception (empty catch) metagpt/utils/common.py:189— An empty catch block silently discards the error — failures vanish with no log and no rethrow. Log it, handle it, or don't catch it.
Blocking `time.sleep` inside an `async def` metagpt/environment/minecraft/minecraft_env.py:339— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/environment/minecraft/minecraft_env.py:375— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/aflow/scripts/optimizer_utils/graph_utils.py:112— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/android_assistant/actions/manual_record.py:166— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/actions/st_action.py:76— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/actions/st_action.py:100— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/actions/st_action.py:113— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/reflect/reflect.py:131— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/roles/st_role.py:575— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Blocking `time.sleep` inside an `async def` metagpt/ext/stanford_town/roles/st_role.py:624— This `async def` runs on the event loop's thread, and `time.sleep` blocks that thread: for the whole delay no other coroutine, request or callback on the loop makes progress — the Python form of blocking on a task. Use `await asyncio.sleep(…)`, which suspends only this coroutine. Where the blocking work is not a sleep but a synchronous call that cannot be made async, move it off the loop with `await asyncio.to_thread(…)` (or `loop.run_in_executor(…)`).
Duplicated block (5 lines × 2) metagpt/ext/android_assistant/actions/screenshot_parse.py:148— metagpt/ext/android_assistant/actions/screenshot_parse.py:148-152 | metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:106-110 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (5 lines × 2) metagpt/tools/libs/browser.py:83— metagpt/tools/libs/browser.py:83-87 | metagpt/tools/libs/image_getter.py:52-56 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once.
Duplicated block (5 lines × 2) metagpt/actions/design_api.py:232— metagpt/actions/design_api.py:232-236 | metagpt/actions/write_prd.py:279-283 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once.
Duplicated block (5 lines × 2) metagpt/actions/design_api.py:268— metagpt/actions/design_api.py:268-272 | metagpt/actions/write_prd.py:316-320 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/actions/design_api.py:268` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (5 lines × 2) metagpt/ext/android_assistant/actions/screenshot_parse.py:163— metagpt/ext/android_assistant/actions/screenshot_parse.py:163-167 | metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:120-124 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once.
Duplicated block (5 lines × 2) examples/build_customized_agent.py:64— examples/build_customized_agent.py:64-68 | examples/build_customized_agent.py:86-91 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
FileTooLong: strategy/experience_retriever.py metagpt/strategy/experience_retriever.py— FileTooLong — 738 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 238 over it, 1.48× the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them.
FileTooLong: utils/common.py metagpt/utils/common.py— FileTooLong — 717 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 217 over it, 1.43× the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them.
FileTooLong: libs/editor.py metagpt/tools/libs/editor.py— FileTooLong — 621 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 121 over it, 1.24× the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them.
FileTooLong: metagpt/schema.py metagpt/schema.py— FileTooLong — 582 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 82 over it, 1.16× the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them.
FileTooLong: REDACTED REDACTED— FileTooLong — 559 significant lines (blank, comment-only and punctuation-only lines excluded). The bar is 500 significant lines; this is 59 over it, 1.12× the bar. To reduce it, split the file along the responsibilities already in it: move each cohesive group of declarations into its own sibling file in the same module or package, so no one file has to be read whole to change one of them.
Duplicated block (10 lines × 2) REDACTED:134— REDACTED:134-143 | REDACTED:150-159 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at `REDACTED:134` it does not close everything it opens, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (10 lines × 2) metagpt/ext/stanford_town/actions/agent_chat_sum_rel.py:30— metagpt/ext/stanford_town/actions/agent_chat_sum_rel.py:30-39 | metagpt/ext/stanford_town/actions/run_reflect_action.py:37-46 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (10 lines × 2) metagpt/ext/stanford_town/actions/decide_to_talk.py:51— metagpt/ext/stanford_town/actions/decide_to_talk.py:51-60 | metagpt/ext/stanford_town/actions/decide_to_talk.py:62-71 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (10 lines × 2) metagpt/ext/stanford_town/plan/converse.py:22— metagpt/ext/stanford_town/plan/converse.py:22-31 | metagpt/ext/stanford_town/plan/converse.py:40-49 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (10 lines × 2) metagpt/tools/search_engine_serpapi.py:34— metagpt/tools/search_engine_serpapi.py:34-43 | metagpt/tools/search_engine_serper.py:28-38 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The `return` at the foot of the matched lines is the enclosing body's own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that `return` occupied — no decision has to be handed back and re-acted on.
Duplicated block (9 lines × 2) metagpt/actions/rebuild_sequence_view.py:175— metagpt/actions/rebuild_sequence_view.py:175-183 | metagpt/actions/rebuild_sequence_view.py:566-574 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (9 lines × 2) metagpt/actions/write_code.py:134— metagpt/actions/write_code.py:134-142 | metagpt/actions/write_code.py:145-153 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/actions/write_code.py:134` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (9 lines × 2) metagpt/provider/ollama_api.py:153— metagpt/provider/ollama_api.py:153-161 | metagpt/provider/ollama_api.py:175-183 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (9 lines × 2) metagpt/roles/di/data_analyst.py:133— metagpt/roles/di/data_analyst.py:133-141 | metagpt/roles/di/data_interpreter.py:181-189 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (9 lines × 2) metagpt/environment/base_env.py:165— metagpt/environment/base_env.py:165-173 | metagpt/environment/werewolf/werewolf_env.py:18-26 — the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach — a location they all depend on today, or a new shared one if there is none — and call it from each site; until then, every change has to be made twice. Note first that the copies are not typed on the same thing: the declarations holding them bind `roles` to `Iterable[BaseRole]` in one and `Iterable["Role"]` in another, and the duplicated lines use it. The extracted unit therefore needs a parameter type that fits BOTH — their common supertype where they have one, or a new abstraction over them where they do not — and settling that is the step that comes BEFORE the extraction above. Where the two types are deliberately unrelated, the duplication is the price of that separation and the honest resolution is to record the decision rather than to extract.
HackComment metagpt/ext/werewolf/roles/moderator.py:215— # msg_content = f"Step {self.step_idx}: {msg_content}" # HACK: 加一个unique的step_idx避免记忆的自动去重 — a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there.
HackComment metagpt/ext/werewolf/roles/moderator.py:229— # msg_content = f"Step {self.step_idx}: {msg_content}" # HACK: 加一个unique的step_idx避免记忆的自动去重 — a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there.
HackComment metagpt/roles/di/role_zero.py:113— # HACK: Init Planner, control it through dynamic thinking; Consider formalizing as a react mode — a workaround marked in source: record what it is compensating for and what would allow its removal (the upstream fix, the API it is waiting on, the invariant it restores), so the next reader can judge whether it is still needed rather than rediscovering why it is there.
Duplicated block (12 lines × 2) metagpt/provider/ollama_api.py:84— metagpt/provider/ollama_api.py:84-95 | metagpt/provider/ollama_api.py:122-133 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (12 lines × 2) metagpt/rag/engines/simple.py:275— metagpt/rag/engines/simple.py:275-286 | metagpt/rag/engines/simple.py:298-309 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (8 lines × 2) metagpt/ext/android_assistant/actions/screenshot_parse.py:107— metagpt/ext/android_assistant/actions/screenshot_parse.py:107-114 | metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:84-91 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The `return` at the foot of the matched lines is the enclosing body's own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that `return` occupied — no decision has to be handed back and re-acted on.
Duplicated block (8 lines × 2) metagpt/ext/cr/actions/code_review.py:147— metagpt/ext/cr/actions/code_review.py:147-154 | metagpt/ext/cr/actions/modify_code.py:63-70 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once.
Duplicated block (7 lines × 2) metagpt/ext/stanford_town/actions/st_action.py:71— metagpt/ext/stanford_town/actions/st_action.py:71-77 | metagpt/ext/stanford_town/actions/st_action.py:108-114 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (7 lines × 2) metagpt/ext/stanford_town/plan/converse.py:32— metagpt/ext/stanford_town/plan/converse.py:32-38 | metagpt/ext/stanford_town/plan/converse.py:50-56 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
No authorization metagpt/tools/openapi_v3_hello.py:29— This repository serves requests — a request handler (app.run() (metagpt/tools/openapi_v3_hello.py:29) — and no route guard, auth-gate middleware, global guard or imperative check that refuses a caller (401/403, an Unauthorized/Forbidden error) was found: its endpoints may be unprotected.
Editor._edit_file_impl (cyclomatic 36) metagpt/tools/libs/editor.py:509— Editor._edit_file_impl has cyclomatic complexity 36 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
index.app.post("/step") (cyclomatic 28) REDACTED:152— index.app.post("/step") has cyclomatic complexity 28 (threshold 15). Most of this is not in the body itself: 3 of the 28 points are its own statements and the rest belongs to 7 function items inside it that branch (handleError, returnItems, onTick, …). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
(anonymous) (cyclomatic 28) REDACTED:152— (anonymous) has cyclomatic complexity 28 (threshold 15). Most of this is not in the body itself: 3 of the 28 points are its own statements and the rest belongs to 11 function items inside it that branch (handleError, returnItems, onTick, …). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
a11y_tree.execute_step (cyclomatic 27) metagpt/utils/a11y_tree.py:23— a11y_tree.execute_step has cyclomatic complexity 27 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
ScreenshotParse.run (cyclomatic 25) metagpt/ext/android_assistant/actions/screenshot_parse.py:94— ScreenshotParse.run has cyclomatic complexity 25 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages.
custom_decoder.JSONObject (cyclomatic 25) metagpt/utils/custom_decoder.py:91— custom_decoder.JSONObject has cyclomatic complexity 25 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
StanfordTownExtEnv._init_maze (cyclomatic 24) metagpt/environment/stanford_town/stanford_town_ext_env.py:41— StanfordTownExtEnv._init_maze has cyclomatic complexity 24 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
ManualRecord.run (cyclomatic 24) metagpt/ext/android_assistant/actions/manual_record.py:44— ManualRecord.run has cyclomatic complexity 24 (threshold 15). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline.
WriteCode.run (cyclomatic 21) metagpt/actions/write_code.py:100— WriteCode.run has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
Engineer._new_code_actions (cyclomatic 21) metagpt/roles/engineer.py:328— Engineer._new_code_actions has cyclomatic complexity 21 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
SelfLearnAndReflect.run_reflect (cyclomatic 20) metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:145— SelfLearnAndReflect.run_reflect has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
STRole.execute (cyclomatic 20) metagpt/ext/stanford_town/roles/st_role.py:393— STRole.execute has cyclomatic complexity 20 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
app.main (cyclomatic 19) metagpt/ext/spo/app.py:75— app.main has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
sanitize.sanitize (cyclomatic 19) metagpt/utils/sanitize.py:124— sanitize.sanitize has cyclomatic complexity 19 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
STRole.observe (cyclomatic 18) metagpt/ext/stanford_town/roles/st_role.py:213— STRole.observe has cyclomatic complexity 18 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
SerpAPIWrapper._process_response (cyclomatic 18) metagpt/tools/search_engine_serpapi.py:80— SerpAPIWrapper._process_response has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages.
repair_llm_raw_output.repair_invalid_json (cyclomatic 18) metagpt/utils/repair_llm_raw_output.py:184— repair_llm_raw_output.repair_invalid_json has cyclomatic complexity 18 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages.
utils.path_finder_v2 (cyclomatic 17) metagpt/ext/stanford_town/utils/utils.py:89— utils.path_finder_v2 has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
OpenAILLM._achat_completion_stream (cyclomatic 17) metagpt/provider/openai_api.py:92— OpenAILLM._achat_completion_stream has cyclomatic complexity 17 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
SerperWrapper._process_response (cyclomatic 17) metagpt/tools/search_engine_serper.py:82— SerperWrapper._process_response has cyclomatic complexity 17 (threshold 15). To reduce it, split the body: these branches sit side by side rather than nested inside one another, so extracting each one on its own would leave a function per branch. Group the statements between the checks into named steps and move each step into its own function, so the body reads as a short sequence of named stages.
ParseRecord.run (cyclomatic 16) metagpt/ext/android_assistant/actions/parse_record.py:38— ParseRecord.run has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
custom_decoder.py_scanstring (cyclomatic 16) metagpt/utils/custom_decoder.py:195— custom_decoder.py_scanstring has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
mermaid.mermaid_to_file (cyclomatic 16) metagpt/utils/mermaid.py:19— mermaid.mermaid_to_file has cyclomatic complexity 16 (threshold 15). To reduce it, separate the cases: extract each independent branch into its own named function, and where the body has guards that only reject input, fold those into early returns at the top.
StanfordTownExtEnv._init_maze (cognitive 52) metagpt/environment/stanford_town/stanford_town_ext_env.py:41— StanfordTownExtEnv._init_maze has cognitive complexity 52 (threshold 15). Drivers by points: if/else 12 (35 pts), loops 12 (17 pts) (nesting depth added 28). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
STRole.observe (cognitive 44) metagpt/ext/stanford_town/roles/st_role.py:213— STRole.observe has cognitive complexity 44 (threshold 15). Drivers by points: if/else 13 (35 pts), loops 5 (8 pts), boolean chains 1 (nesting depth added 25). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
Editor._edit_file_impl (cognitive 44) metagpt/tools/libs/editor.py:509— Editor._edit_file_impl has cognitive complexity 44 (threshold 15). Drivers by points: if/else 18 (25 pts), boolean chains 11, error handling 6 (8 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
Engineer._new_code_actions (cognitive 43) metagpt/roles/engineer.py:328— Engineer._new_code_actions has cognitive complexity 43 (threshold 15). Drivers by points: if/else 18 (34 pts), loops 5 (8 pts), boolean chains 1 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
STRole.execute (cognitive 42) metagpt/ext/stanford_town/roles/st_role.py:393— STRole.execute has cognitive complexity 42 (threshold 15). Drivers by points: if/else 17 (34 pts), loops 3 (7 pts), boolean chains 1 (nesting depth added 21). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
custom_decoder.JSONObject (cognitive 42) metagpt/utils/custom_decoder.py:91— custom_decoder.JSONObject has cognitive complexity 42 (threshold 15). Drivers by points: if/else 17 (33 pts), error handling 3 (6 pts), boolean chains 2, loops 1 (nesting depth added 19). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
app.main (cognitive 37) metagpt/ext/spo/app.py:75— app.main has cognitive complexity 37 (threshold 15). Drivers by points: if/else 14 (25 pts), error handling 2 (7 pts), boolean chains 3, loops 1 (2 pts) (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ManualRecord.run (cognitive 36) metagpt/ext/android_assistant/actions/manual_record.py:44— ManualRecord.run has cognitive complexity 36 (threshold 15). Drivers by points: loops 9 (22 pts), boolean chains 7, if/else 4 (7 pts) (nesting depth added 16). To reduce it, break up the iteration: give each loop body a named function, and split a multi-phase loop into one function per phase so no single body carries the whole pipeline.
utils.traverse_xml_tree (cognitive 34) REDACTED:49— utils.traverse_xml_tree has cognitive complexity 34 (threshold 15). Drivers by points: if/else 8 (28 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 23). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
index.app.post("/step") (cognitive 33) REDACTED:152— index.app.post("/step") has cognitive complexity 33 (threshold 15). Drivers by points: if/else 21 (28 pts), boolean chains 3, error handling 1, loops 1 (nesting depth added 7). Most of this is not in the body itself: 2 of the 33 points are its own statements and the rest belongs to 7 function items inside it that branch (handleError, returnItems, onTick, …). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
(anonymous) (cognitive 33) REDACTED:152— (anonymous) has cognitive complexity 33 (threshold 15). Drivers by points: if/else 21 (28 pts), boolean chains 3, error handling 1, loops 1 (nesting depth added 7). Most of this is not in the body itself: 2 of the 33 points are its own statements and the rest belongs to 11 function items inside it that branch (handleError, returnItems, onTick, …). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
WriteCode.run (cognitive 32) metagpt/actions/write_code.py:100— WriteCode.run has cognitive complexity 32 (threshold 15). Drivers by points: ternaries 10 (20 pts), if/else 9, boolean chains 3 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
text_icon_localization.ocr (cognitive 32) metagpt/environment/android/text_icon_localization.py:97— text_icon_localization.ocr has cognitive complexity 32 (threshold 15). Drivers by points: if/else 14 (28 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
OpenAILLM._achat_completion_stream (cognitive 30) metagpt/provider/openai_api.py:92— OpenAILLM._achat_completion_stream has cognitive complexity 30 (threshold 15). Drivers by points: if/else 8 (16 pts), ternaries 3 (10 pts), boolean chains 3, loops 1 (nesting depth added 15). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
SelfLearnAndReflect.run_reflect (cognitive 29) metagpt/ext/android_assistant/actions/self_learn_and_reflect.py:145— SelfLearnAndReflect.run_reflect has cognitive complexity 29 (threshold 15). Drivers by points: if/else 14 (24 pts), error handling 1 (3 pts), boolean chains 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
RepoParser._parse_classes (cognitive 29) REDACTED:746— RepoParser._parse_classes has cognitive complexity 29 (threshold 15). Drivers by points: if/else 6 (17 pts), loops 5 (11 pts), boolean chains 1 (nesting depth added 17). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
custom_decoder.py_scanstring (cognitive 29) metagpt/utils/custom_decoder.py:195— custom_decoder.py_scanstring has cognitive complexity 29 (threshold 15). Drivers by points: if/else 11 (22 pts), error handling 2 (5 pts), boolean chains 1, loops 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
WriteCode.get_codes (cognitive 28) metagpt/actions/write_code.py:168— WriteCode.get_codes has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (23 pts), loops 2 (4 pts), ternaries 1 (nesting depth added 14). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
st_plan._determine_action (cognitive 28) metagpt/ext/stanford_town/plan/st_plan.py:554— st_plan._determine_action has cognitive complexity 28 (threshold 15). Drivers by points: if/else 11 (26 pts), loops 2 (nesting depth added 15). To reduce it, flatten the nesting: this score is depth rather than breadth — most of its points come from checks stacked inside one another, so the work sits several levels in. Invert each enclosing check into an early exit (a return, or the language's equivalent) so the happy path stays at one level, and where a level cannot be exited early, lift the block it encloses into its own named function.
BaseLLM.compress_messages (cognitive 28) metagpt/provider/base_llm.py:340— BaseLLM.compress_messages has cognitive complexity 28 (threshold 15). Drivers by points: if/else 10 (21 pts), loops 3 (5 pts), boolean chains 2 (nesting depth added 13). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
a11y_tree.execute_step (cognitive 27) metagpt/utils/a11y_tree.py:23— a11y_tree.execute_step has cognitive complexity 27 (threshold 15). Drivers by points: if/else 13 (23 pts), ternaries 2 (3 pts), boolean chains 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ActionNode.xml_fill (cognitive 26) REDACTED:553— ActionNode.xml_fill has cognitive complexity 26 (threshold 15). Drivers by points: if/else 4 (13 pts), error handling 3 (12 pts), loops 1 (nesting depth added 18). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ParseRecord.run (cognitive 26) metagpt/ext/android_assistant/actions/parse_record.py:38— ParseRecord.run has cognitive complexity 26 (threshold 15). Drivers by points: if/else 9 (19 pts), error handling 1 (3 pts), boolean chains 2, loops 2 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ScreenshotParse.run (cognitive 25) metagpt/ext/android_assistant/actions/screenshot_parse.py:94— ScreenshotParse.run has cognitive complexity 25 (threshold 15). Drivers by points: if/else 13 (18 pts), loops 3 (4 pts), boolean chains 2, ternaries 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
sanitize.sanitize (cognitive 23) metagpt/utils/sanitize.py:124— sanitize.sanitize has cognitive complexity 23 (threshold 15). Drivers by points: if/else 6 (14 pts), boolean chains 6, loops 3 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
token_counter.count_message_tokens (cognitive 23) metagpt/utils/token_counter.py:430— token_counter.count_message_tokens has cognitive complexity 23 (threshold 15). Drivers by points: if/else 6 (14 pts), loops 3 (7 pts), boolean chains 1, error handling 1 (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
CodeReview.cr_by_points (cognitive 22) metagpt/ext/cr/actions/code_review.py:176— CodeReview.cr_by_points has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (15 pts), loops 3 (7 pts) (nesting depth added 12). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
TaskDecomp._func_cleanup (cognitive 22) metagpt/ext/stanford_town/actions/task_decomp.py:14— TaskDecomp._func_cleanup has cognitive complexity 22 (threshold 15). Drivers by points: if/else 7 (11 pts), loops 7 (11 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ExperienceUtils.load_experience (cognitive 21) metagpt/ext/aflow/scripts/optimizer_utils/experience_utils.py:13— ExperienceUtils.load_experience has cognitive complexity 21 (threshold 15). Drivers by points: if/else 7 (16 pts), error handling 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
mermaid.mermaid_to_file (cognitive 21) metagpt/utils/mermaid.py:19— mermaid.mermaid_to_file has cognitive complexity 21 (threshold 15). Drivers by points: if/else 9 (16 pts), boolean chains 2, loops 1 (2 pts), ternaries 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
utils.path_finder_v2 (cognitive 20) metagpt/ext/stanford_town/utils/utils.py:89— utils.path_finder_v2 has cognitive complexity 20 (threshold 15). Drivers by points: if/else 4 (8 pts), loops 6 (8 pts), boolean chains 4 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
index.app.post("/start") (cognitive 20) REDACTED:25— index.app.post("/start") has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (12 pts), loops 2 (4 pts), ternaries 2 (4 pts) (nesting depth added 8). Most of this is not in the body itself: 1 of the 20 points is its own statement and the rest belongs to 2 function items inside it that branch (a function literal at line 52, onDisconnect). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
(anonymous) (cognitive 20) REDACTED:25— (anonymous) has cognitive complexity 20 (threshold 15). Drivers by points: if/else 8 (12 pts), loops 2 (4 pts), ternaries 2 (4 pts) (nesting depth added 8). Most of this is not in the body itself: 1 of the 20 points is its own statement and the rest belongs to 5 function items inside it that branch (a function literal at line 52, onDisconnect, a function literal at line 48, …). The named helpers are already separate functions; the literals' work cannot be called, reviewed or tested from outside this body. To reduce it, move the named helpers out of the body to the enclosing scope and lift each literal's work into a named function there, so each is measured, reviewed and tested on its own, and reduce whichever one then reads as the largest.
text_icon_localization.remove_boxes (cognitive 19) metagpt/environment/android/text_icon_localization.py:310— text_icon_localization.remove_boxes has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (15 pts), loops 2 (3 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
Optimizer.optimize (cognitive 19) metagpt/ext/aflow/scripts/optimizer.py:71— Optimizer.optimize has cognitive complexity 19 (threshold 15). Drivers by points: if/else 4 (10 pts), loops 3 (5 pts), error handling 1 (3 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
tool_registry.validate_tool_names (cognitive 19) metagpt/tools/tool_registry.py:131— tool_registry.validate_tool_names has cognitive complexity 19 (threshold 15). Drivers by points: if/else 6 (13 pts), loops 2 (5 pts), boolean chains 1 (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
Node.run_node (cognitive 18) REDACTED:271— Node.run_node has cognitive complexity 18 (threshold 15). Drivers by points: if/else 8 (11 pts), error handling 2 (4 pts), boolean chains 2, loops 1 (nesting depth added 5). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
dashscope_api.build_api_arequest (cognitive 18) metagpt/provider/dashscope_api.py:36— dashscope_api.build_api_arequest has cognitive complexity 18 (threshold 15). Drivers by points: if/else 11 (17 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
RepoParser.extract_class_and_function_info (cognitive 18) REDACTED:446— RepoParser.extract_class_and_function_info has cognitive complexity 18 (threshold 15). Drivers by points: if/else 4 (11 pts), loops 2 (4 pts), ternaries 1 (3 pts) (nesting depth added 11). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ExecuteNbCode.parse_outputs (cognitive 17) metagpt/actions/di/execute_nb_code.py:160— ExecuteNbCode.parse_outputs has cognitive complexity 17 (threshold 15). Drivers by points: if/else 6 (12 pts), ternaries 1 (3 pts), boolean chains 1, loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
CodeReview.format_comments (cognitive 17) metagpt/ext/cr/actions/code_review.py:95— CodeReview.format_comments has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (12 pts), loops 2 (3 pts), error handling 1 (2 pts) (nesting depth added 9). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
Editor.search_dir (cognitive 17) metagpt/tools/libs/editor.py:998— Editor.search_dir has cognitive complexity 17 (threshold 15). Drivers by points: if/else 5 (10 pts), loops 4 (7 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ImportRepo._guess_src_workspace (cognitive 16) metagpt/actions/import_repo.py:153— ImportRepo._guess_src_workspace has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (13 pts), loops 2 (3 pts) (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
ScreenshotParse._makeup_ui_document (cognitive 16) metagpt/ext/android_assistant/actions/screenshot_parse.py:54— ScreenshotParse._makeup_ui_document has cognitive complexity 16 (threshold 15). Drivers by points: if/else 7 (13 pts), error handling 1 (2 pts), loops 1 (nesting depth added 7). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
utils.draw_bbox_multi (cognitive 16) REDACTED:111— utils.draw_bbox_multi has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (7 pts), ternaries 2 (6 pts), error handling 1 (2 pts), loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
converse.agent_conversation (cognitive 16) metagpt/ext/stanford_town/plan/converse.py:13— converse.agent_conversation has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (10 pts), loops 4 (6 pts) (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
RoleZero._run_commands (cognitive 16) metagpt/roles/di/role_zero.py:385— RoleZero._run_commands has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (12 pts), error handling 1 (3 pts), loops 1 (nesting depth added 8). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
SubscriptionRunner.run (cognitive 16) metagpt/subscription.py:76— SubscriptionRunner.run has cognitive complexity 16 (threshold 15). Drivers by points: if/else 4 (13 pts), loops 2 (3 pts) (nesting depth added 10). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
IndexRepo.search (cognitive 16) metagpt/tools/libs/index_repo.py:76— IndexRepo.search has cognitive complexity 16 (threshold 15). Drivers by points: if/else 6 (11 pts), loops 3 (4 pts), boolean chains 1 (nesting depth added 6). To reduce it, split the body into named stages: move each independent step or branch into its own named function so the body reads as a short sequence of named calls rather than one long body.
FunctionTooLong: index.app.post("/step") REDACTED:152— FunctionTooLong — app.post("/step") runs 177 significant lines (blank, comment-only and punctuation-only lines excluded) in one body. The bar is 100 significant lines; this is 77 over it, 1.77× the bar. This is length, not branching: a long straight-line body scores low on complexity and is still read whole to change any part of it, so the complexity numbers beside this row neither confirm nor excuse it. To reduce it, extract each cohesive step of the body — the runs of statements that work on the same values and would earn the same name — into its own named unit, and have this one call them in order.
TooManyMethods: ActionNode REDACTED:135— TooManyMethods — 51 methods. The bar is 30 methods; this is 21 over it, 1.70× the bar. To reduce it, group the members that share the same data into a smaller type of their own and delegate to it, so no single type carries every responsibility.
Change-coupling hub: prompt.py → operator_an.py, REDACTED, workflow.py metagpt/ext/aflow/scripts/prompts/prompt.py— `metagpt/ext/aflow/scripts/prompts/prompt.py` changes together with 3 other files — `metagpt/ext/aflow/scripts/operator_an.py`, `metagpt/ext/aflow/scripts/utils.py`, `metagpt/ext/aflow/scripts/workflow.py` — none of which declares a dependency on it: one file is the hub of 3 separate couplings, not 3 unrelated pairs. Read the hub first: if the others each duplicate a part of what it does, the shared concern belongs in ONE unit and extracting it clears every edge at once; if the hub is a registry, dispatcher or barrel that must name each of them, the coupling is structural and the question is whether that list can be discovered instead of enumerated. Fixing the hub is one change; breaking the couplings one pair at a time is 3.
Duplicated block (49–53 lines × 2) metagpt/utils/mmdc_playwright.py:59— metagpt/utils/mmdc_playwright.py:59-111 | metagpt/utils/mmdc_pyppeteer.py:63-111 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/utils/mmdc_playwright.py:59` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (21–23 lines × 2) metagpt/ext/stanford_town/actions/gen_action_details.py:57— metagpt/ext/stanford_town/actions/gen_action_details.py:57-79 | metagpt/ext/stanford_town/actions/gen_action_details.py:126-146 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (20–21 lines × 2) metagpt/ext/stanford_town/plan/st_plan.py:144— metagpt/ext/stanford_town/plan/st_plan.py:144-163 | metagpt/ext/stanford_town/plan/st_plan.py:180-200 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (19 lines × 2) metagpt/ext/stanford_town/reflect/reflect.py:204— metagpt/ext/stanford_town/reflect/reflect.py:204-222 | metagpt/ext/stanford_town/reflect/reflect.py:227-245 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (18 lines × 2) metagpt/ext/stanford_town/memory/agent_memory.py:261— metagpt/ext/stanford_town/memory/agent_memory.py:261-278 | metagpt/ext/stanford_town/memory/agent_memory.py:311-328 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/ext/stanford_town/memory/agent_memory.py:261` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (16 lines × 3) metagpt/ext/stanford_town/memory/agent_memory.py:210— metagpt/ext/stanford_town/memory/agent_memory.py:210-225 | metagpt/ext/stanford_town/memory/agent_memory.py:259-274 | metagpt/ext/stanford_town/memory/agent_memory.py:309-324 — all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites — resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/ext/stanford_town/memory/agent_memory.py:210` it does not close everything it opens, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that.
Duplicated block (15–16 lines × 2) metagpt/utils/mmdc_playwright.py:113— metagpt/utils/mmdc_playwright.py:113-127 | metagpt/utils/mmdc_pyppeteer.py:118-133 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/utils/mmdc_pyppeteer.py:118` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. ★ These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, `metagpt/utils/mmdc_playwright.py:112` calls `set_viewport_size`, `screenshot` and `metagpt/utils/mmdc_pyppeteer.py:118` does not — after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live.
Duplicated block (11–14 lines × 2) metagpt/ext/werewolf/roles/base_player.py:58— metagpt/ext/werewolf/roles/base_player.py:58-68 | metagpt/ext/werewolf/roles/moderator.py:141-154 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/ext/werewolf/roles/base_player.py:58` it does not close everything it opens, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names — the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately.
Duplicated block (3–14 lines × 4) metagpt/tools/search_engine_serpapi.py:91— metagpt/tools/search_engine_serpapi.py:91-94 | metagpt/tools/search_engine_serpapi.py:99-112 | metagpt/tools/search_engine_serper.py:93-95 | metagpt/tools/search_engine_serper.py:100-113 — there are 4 copies across 2 file(s) — more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 4 sites; resolving a subset leaves the remainder to drift apart. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/tools/search_engine_serpapi.py:91` it begins part-way through the construct above it, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that. The `return` at the foot of the matched lines is the enclosing body's own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that `return` occupied — no decision has to be handed back and re-acted on. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names — the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately. ★ These copies have DRIFTED, and that is worth reading before extracting anything: just before the matched lines, `metagpt/tools/search_engine_serpapi.py:99` calls `keys` and `metagpt/tools/search_engine_serper.py:93` does not — after which the two agree again for 2 more lines. One of those two behaviours is the intended one and the other is what a copy-paste left behind, so decide which BEFORE unifying them: extracting the shared part will silently settle it, and if the copy that skips the call is the wrong one, that bug is already live.
Duplicated block (11 lines × 2) metagpt/ext/stanford_town/actions/run_reflect_action.py:161— metagpt/ext/stanford_town/actions/run_reflect_action.py:161-171 | metagpt/ext/stanford_town/actions/run_reflect_action.py:197-207 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (7–8 lines × 2) metagpt/ext/stanford_town/roles/st_role.py:176— metagpt/ext/stanford_town/roles/st_role.py:176-182 | metagpt/roles/role.py:405-412 — the copies span different directories, so extracting a shared function means choosing where it lives: put it somewhere both call sites can already reach — a location they all depend on today, or a new shared one if there is none — and call it from each site; until then, every change has to be made twice.
Duplicated block (6 lines × 3) metagpt/ext/stanford_town/reflect/reflect.py:123— metagpt/ext/stanford_town/reflect/reflect.py:123-128 | metagpt/ext/stanford_town/reflect/reflect.py:207-220 | metagpt/ext/stanford_town/reflect/reflect.py:230-243 — all 3 copies are in the same file, so extract the block into one function there and call it from every one of those sites — resolving only two of them leaves the rest to drift apart the first time one is edited. Read the line range as the matched WINDOW rather than a finished unit: at `metagpt/ext/stanford_town/reflect/reflect.py:123` it does not close everything it opens, so those exact lines cannot be lifted as they stand — widen the region to the smallest complete statement or declaration that contains it, and extract that. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names — the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately.
Duplicated block (4–5 lines × 3) metagpt/ext/android_assistant/actions/screenshot_parse.py:122— metagpt/ext/android_assistant/actions/screenshot_parse.py:122-126 | REDACTED:68-71 | REDACTED:96-100 — there are 3 copies across 2 file(s) — more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names — the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately.
Duplicated block (1–5 lines × 3) metagpt/ext/android_assistant/actions/screenshot_parse.py:128— metagpt/ext/android_assistant/actions/screenshot_parse.py:128-132 | REDACTED:72-76 | REDACTED:102-102 — there are 3 copies across 2 file(s) — more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it. Note that the copies do not run to the end of the range shown: their LAST lines are different code, not the same code under different names — the matched region ends inside that line. Extract the lines above it, and read the last line of each site separately.
Duplicated block (7 lines × 3) metagpt/ext/stanford_town/actions/gen_action_details.py:248— metagpt/ext/stanford_town/actions/gen_action_details.py:248-254 | metagpt/ext/stanford_town/actions/gen_action_details.py:322-328 | metagpt/ext/stanford_town/actions/run_reflect_action.py:101-107 — there are 3 copies across 2 file(s) — more copies than files, so at least one file holds the block twice. Extract it once into a single shared function every call site can reach and call it from all 3 sites; resolving a subset leaves the remainder to drift apart. The matched lines also transfer control out of the body holding them, which cannot survive a move into a called unit unchanged: have the extracted unit return that decision and let each site act on it.
Duplicated block (6 lines × 2) metagpt/tools/search_engine.py:40— metagpt/tools/search_engine.py:40-45 | metagpt/tools/web_browser_engine.py:40-53 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The `return` at the foot of the matched lines is the enclosing body's own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that `return` occupied — no decision has to be handed back and re-acted on.
Duplicated block (13 lines × 2) metagpt/tools/search_engine_bing.py:88— metagpt/tools/search_engine_bing.py:88-100 | metagpt/tools/search_engine_googleapi.py:115-127 — the copies sit in sibling files of one directory, so a shared home is within easy reach: extract the block into a single shared function the call sites can all reach — a file they already depend on, or a new one alongside them — and call it from both call sites, so a change lands once. The `return` at the foot of the matched lines is the enclosing body's own terminal exit, not an early one: it moves with them unchanged, and each site calls the extracted unit from the position that `return` occupied — no decision has to be handed back and re-acted on.
Low cohesion: Engineer2 (LCOM4 4) metagpt/roles/di/engineer2.py:32— Engineer2's methods fall into 4 groups that share no field and call none of each other, against a bar of more than 3 for this run (LCOM4, configurable — your repository's bar is the one quoted here). Each group is a set of methods reachable from one another through shared fields or direct calls, so 4 groups means the type has that many internally-connected clusters with nothing tying them together. Types whose shape makes a high count expected — and which would otherwise dominate this list — are excluded before this row is raised, so this is a genuine split candidate rather than a metric reading. It is still a shape, not a defect: confirm the groups match responsibilities you can name before splitting.
P12 · CI test-gate honesty· Coverage collected but not gated · ×1
Coverage collected but not gated — CI collects a coverage report but no step enforces a minimum — coverage could halve and CI stays green. Add a step that fails the build when coverage drops below a floor (your coverage tool's minimum-threshold flag, or a coverage-gate action) so the number guards something. What was searched, so you can tell an absence from a miss: this repository's CI files AND its coverage configuration — the well-known coverage and test-runner config files, read at the repository root and inside workspace package directories two levels down, so a floor declared beside the tests rather than in the pipeline is credited — matched against the threshold settings this check knows by name. A floor set in your coverage service's web UI rather than in a committed file, or under a setting whose name is not one of those, is not seen here.
Duplicated block (10 lines × 2 locations) REDACTED:302— REDACTED:302 · REDACTED:312 — both copies are in the same file, so extract the block into one function there and call it from each site — the copies drift apart the first time only one of them is edited.
Duplicated block (9 lines × 2 locations) metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:38— metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:38 · metagpt/environment/minecraft/mineflayer/lib/skillLoader.js:48 — all 2 copies are in the same file, and the CITED SPAN is not a self-contained block — it runs from inside one construct into the next (the tail of a branch plus the head of the following one, a run of switch arms, the end of a declaration plus the list that follows it) rather than covering a whole unit. So do not lift these lines literally: no call can be substituted for a half-open construct. Extract the enclosing repeated UNIT instead — the whole function, component or branch these lines sit in — and where the repetition IS the construct (a run of switch arms, a stack of near-identical declarations) replace it with one table or registry looked up by key rather than a helper each arm calls. The copies still drift apart the first time only one of them is edited, which is why this is reported.
R10 · Code Duplication· Duplicated block with local edits (6 matched lines × 2 locations) · ×1
Duplicated block with local edits (6 matched lines × 2 locations) REDACTED:365— REDACTED:365 · REDACTED:376 — the two spans are one implementation copied and then locally edited — 60 tokens are still identical, in the same order in both spans, with only local edits between them. The copies have already begun to drift, which is this row's finding: an edit made to one and not the other changes behaviour silently. Diff the two spans first to learn what genuinely differs, then extract the shared core into one module both sites use, passing the differences in as parameters — or, if one copy exists only because the other could not be imported from its context, make one of them the single source the other is generated or re-exported from. If one copy is no longer reachable, delete it rather than letting it shadow the live one.
Complex function collectAll (cyclomatic 21, cognitive 55) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:18— collectAll has cyclomatic complexity 21 and cognitive complexity 55; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
Complex function collect (cyclomatic 15, cognitive 16) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:350— collect has cyclomatic complexity 15 and cognitive complexity 16; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
Complex function handleError (cyclomatic 13, cognitive 14) REDACTED:338— handleError has cyclomatic complexity 13 and cognitive complexity 14; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
Complex function findFromVein (cyclomatic 11, cognitive 33) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/BlockVeins.ts:4— findFromVein has cyclomatic complexity 11 and cognitive complexity 33; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
Complex function (anonymous) (cyclomatic 11, cognitive 18) REDACTED:52— (anonymous) has cyclomatic complexity 11 and cognitive complexity 18; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive is at or above cyclomatic here, so the branching is nested or entangled rather than laid out side by side — extracting each decision into its own named function is the change that pays. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
Complex function ItemFilter (cyclomatic 11, cognitive 10) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:310— ItemFilter has cyclomatic complexity 11 and cognitive complexity 10; this row is raised above a cyclomatic bar of 10. The two numbers answer different questions and the gap between them is what decides whether to act: cyclomatic counts the independent arms through the body, cognitive counts what it costs to hold them in your head, so nesting and mixed boolean chains raise it while a flat run of independent arms does not. Cognitive sits below cyclomatic here, so much of the count is breadth — arms side by side rather than stacked — and splitting per arm would leave a function per arm; group the work between the checks into named steps instead. Measured by this repository's own parse of the file, so a body assembled at runtime, or generated, is counted as written rather than as it executes.
R3 · Large Files· metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts · ×1
metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts: 423 lines of code metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:1— metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts has 423 significant lines (blank lines excluded), over the 400-line bar, and contains logic — a file this long is usually several responsibilities in one module.
No lint script — test ✓ · lint ✗ · typecheck ✓ — read from this repository's package.json scripts and corroborated against its CI workflows. A script counts when its name or command matches the step: `test` for the suite, `lint` or `prettier` for linting, `typecheck`/`type-check`/`tsc` for type checking. ✗ therefore means no script or CI step under those names was found, NOT that the step is absent from your pipeline — a task invoked by a runner this check does not read, or named something else entirely, is not seen and is worth confirming before acting on a cross. A ✓ means the wiring is DECLARED — a script or CI step under those names exists. It is not a statement that the step passes, or that it runs at all: nothing here installs a dependency or executes a suite.
Dead file (~77 LoC) metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/TaskQueue.ts— no import path from any entry point (2 application, 0 tooling, 0 test roots considered), and no other file in the scanned tree imports it — nothing in-repo names this module at all, which is the strongest form of this claim the import graph can make
Unused dependency 'graceful-fs' — Declared in metagpt/environment/minecraft/mineflayer/package.json but never imported anywhere in that package or its workspace members — no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it.
Unused dependency 'magic-string' — Declared in metagpt/environment/minecraft/mineflayer/package.json but never imported anywhere in that package or its workspace members — no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it.
Unused dependency 'prismarine-biome' — Declared in metagpt/environment/minecraft/mineflayer/package.json but never imported anywhere in that package or its workspace members — no static import reaches it. Usually that is dead weight and attack surface, but two shapes are indistinguishable from source and are NOT dead: an optional or native peer that another dependency loads dynamically at runtime, and a package a build, docs or test step installs and invokes separately. Confirm which of the three this is before removing it.
SC1 · Supply-chain hygiene· JavaScript dependencies are not locked · ×1
JavaScript dependencies are not locked — No package-lock.json / yarn.lock / pnpm-lock.yaml / bun.lock — JS installs aren't reproducible (SSDF PW.4.4). Commit your package manager's lockfile and install from it (`npm ci`, `yarn --immutable`, `pnpm i --frozen-lockfile` or `bun i --frozen-lockfile`). Advisory — never scored.
X1 · Async correctness· Task from `asyncio.create_task` is not kept · ×1
Task from `asyncio.create_task` is not kept metagpt/tools/libs/terminal.py:103— The task this creates is not kept anywhere. The event loop holds only a weak reference to its tasks, so a task nobody references can be garbage-collected before it finishes (Python's documentation for `asyncio.create_task`: save a reference to the result); and nothing ever awaits it, so an exception it raises is never handled — it surfaces, if at all, as "Task exception was never retrieved" in a log. Keep the task: `await` it, gather it, start it in an `asyncio.TaskGroup` (`async with asyncio.TaskGroup() as tg: tg.create_task(…)`), or, for genuine fire-and-forget, add it to a set and `task.add_done_callback(tasks.discard)` with a callback that also reads its exception.
Orphaned file REDACTED:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file REDACTED:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/schema.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/ext/stanford_town/plan/st_plan.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/utils/token_counter.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/ext/stanford_town/roles/st_role.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/utils/git_repository.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/actions/rebuild_sequence_view.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/roles/role.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/roles/engineer.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/roles/di/role_zero.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file REDACTED:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/tools/libs/index_repo.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/provider/base_llm.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/provider/general_api_base.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/actions/write_code_an_draft.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/environment/stanford_town/stanford_town_ext_env.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/environment/minecraft/minecraft_env.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/utils/graph_repository.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/environment/minecraft/mineflayer/mineflayer-collectblock/src/CollectBlock.ts:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/rag/engines/simple.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/ext/stanford_town/actions/gen_action_details.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/actions/requirement_analysis/trd/write_trd.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file REDACTED:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Orphaned file metagpt/utils/repair_llm_raw_output.py:1— No one still active in this repository holds living knowledge of this file: everyone who made a meaningful change to it has gone quiet, or what the current team did to it (moves, reformatting, log-level or import edits, renames) never needed understanding it. If it breaks, no one currently understands it. Attach the read to the next change that touches it: have a second person review that change, and leave behind a short comment or test recording what the file is for.
Duplicated predicate metagpt/tools/search_engine_serpapi.py:91— `"answer_box" in res.keys() and "answer" in res["answer_box"].keys()` appears character-identically in 2 files — metagpt/tools/search_engine_serpapi.py, metagpt/tools/search_engine_serper.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/tools/search_engine_serpapi.py:93— `"answer_box" in res.keys() and "snippet" in res["answer_box"].keys()` appears character-identically in 2 files — metagpt/tools/search_engine_serpapi.py, metagpt/tools/search_engine_serper.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/tools/search_engine_serpapi.py:95— `"answer_box" in res.keys() and "snippet_highlighted_words" in res["answer_box"].keys()` appears character-identically in 2 files — metagpt/tools/search_engine_serpapi.py, metagpt/tools/search_engine_serper.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/tools/search_engine_serpapi.py:99— `"knowledge_graph" in res.keys() and "description" in res["knowledge_graph"].keys()` appears character-identically in 2 files — metagpt/tools/search_engine_serpapi.py, metagpt/tools/search_engine_serper.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/tools/search_engine_serpapi.py:97— `"sports_results" in res.keys() and "game_spotlight" in res["sports_results"].keys()` appears character-identically in 2 files — metagpt/tools/search_engine_serpapi.py, metagpt/tools/search_engine_serper.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/ext/werewolf/roles/base_player.py:63— `len(m.restricted_to) and self.profile not in m.restricted_to and self.name not in m.restricted_to` appears character-identically in 2 files — metagpt/ext/werewolf/roles/base_player.py, metagpt/ext/werewolf/roles/moderator.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/ext/stanford_town/roles/st_role.py:181— `n.cause_by in self.rc.watch or self.name in n.send_to` appears character-identically in 2 files — metagpt/ext/stanford_town/roles/st_role.py, metagpt/roles/role.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/schema.py:184— `not filename or not Path(filename).exists()` appears character-identically in 2 files — metagpt/schema.py, metagpt/utils/common.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/ext/android_assistant/actions/manual_record.py:69— `not screenshot_path.exists() or not xml_path.exists()` appears character-identically in 3 files — metagpt/ext/android_assistant/actions/manual_record.py, metagpt/ext/android_assistant/actions/screenshot_parse.py, metagpt/ext/android_assistant/actions/self_learn_and_reflect.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/ext/sela/runner/runner.py:34— `num_runs <= max_retries and not run_finished` appears character-identically in 2 files — metagpt/ext/sela/runner/runner.py, REDACTED. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/actions/write_code.py:102— `self.input_args and hasattr(self.input_args, "issue_filename")` appears character-identically in 2 files — metagpt/actions/write_code.py, metagpt/roles/engineer.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
Duplicated predicate metagpt/roles/di/data_interpreter.py:55— `self.tools and not self.tool_recommender` appears character-identically in 2 files — metagpt/roles/di/data_interpreter.py, metagpt/roles/di/role_zero.py. It is one line, so the duplication detector's token window never sees it; the copies drift when only one is corrected. Give the condition a name and one home.
README/code drift docs/README_FR.md:138— docs/README_FR.md links to `docs/ROADMAP.md`, but `docs/docs/ROADMAP.md` does not exist. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong.
README/code drift docs/README_JA.md:78— docs/README_JA.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong.
README/code drift docs/install/cli_install.md:45— docs/install/cli_install.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong.
README/code drift docs/install/cli_install_cn.md:45— docs/install/cli_install_cn.md installs `@mermaid-js/mermaid-cli` (`npm install @mermaid-js/mermaid-cli`), but no package.json declares it. Checked without a model against the repository: its files and folders, the scripts and dependencies of every package.json, the projects, namespaces, package references and target frameworks of the .NET build, the SDK and Node pins, and the identifiers of every file that is not a document; the documents' own text never counts. A footprint generated at build time, read only by a platform, or living outside this repository is not seen, and this row is then wrong.
Off-boarding risk: anonymized user #1 — If anonymized user #1 becomes unavailable, 5 significant file(s) lose their only recent owner: metagpt/ext/aflow/scripts/operator.py, REDACTED, metagpt/ext/aflow/scripts/prompts/prompt.py, REDACTED, metagpt/ext/aflow/scripts/utils.py. Pair on, review, or document these before any departure.
Off-boarding risk: anonymized user #2 — If anonymized user #2 becomes unavailable, 4 significant file(s) lose their only recent owner: metagpt/ext/sela/data/dataset.py, metagpt/ext/sela/insights/instruction_generator.py, metagpt/ext/sela/utils.py, metagpt/ext/sela/data/custom_task.py. Pair on, review, or document these before any departure.
Off-boarding risk: anonymized user #3 — If anonymized user #3 becomes unavailable, 3 significant file(s) lose their only recent owner: metagpt/tools/libs/index_repo.py, metagpt/memory/brain_memory.py, metagpt/roles/assistant.py. Pair on, review, or document these before any departure.
D34 · Knowledge Freshness· Most significant orphaned file · ×3
Most significant orphaned file metagpt/strategy/experience_retriever.py:1— One of the orphaned files carrying the most lost knowledge — ranked by size weighted by the file's role in the codebase, the same weighting behind the score above, so core code outranks equally large plumbing. A reasonable place to start a read-through before the aggregate risk above bites.
Most significant orphaned file metagpt/tools/libs/editor.py:1— One of the orphaned files carrying the most lost knowledge — ranked by size weighted by the file's role in the codebase, the same weighting behind the score above, so core code outranks equally large plumbing. A reasonable place to start a read-through before the aggregate risk above bites.
Most significant orphaned file metagpt/utils/common.py:1— One of the orphaned files carrying the most lost knowledge — ranked by size weighted by the file's role in the codebase, the same weighting behind the score above, so core code outranks equally large plumbing. A reasonable place to start a read-through before the aggregate risk above bites.
X23 · Unguarded diagnostic materialisation· Diagnostic log message is built whether or not it is wanted · ×3
Diagnostic log message is built whether or not it is wanted metagpt/roles/engineer.py:277— `debug` at line 277 is called with an argument built by `msg.model_dump_json()` (line 277), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on.
Diagnostic log message is built whether or not it is wanted metagpt/roles/engineer.py:281— `debug` at line 281 is called with an argument built by `msg.model_dump_json()` (line 281), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on.
Diagnostic log message is built whether or not it is wanted metagpt/roles/engineer.py:285— `debug` at line 285 is called with an argument built by `msg.model_dump_json()` (line 285), whose cost grows with the collection it walks. Python evaluates a call's arguments BEFORE entering the method, so that join/projection runs in full every time this line is reached — and then the level check inside the logger discards the string it produced, because debug is a level a shipped configuration normally leaves off. Nothing here decides beforehand whether the message is wanted: no `isEnabledFor(logging.DEBUG)` test, no debug flag, no `lambda` the logger calls only when the level is on.
Silent fallback default on parse failure metagpt/ext/aflow/scripts/optimizer_utils/data_utils.py:24— `load_results` returns `[]` when `json.JSONDecodeError` is raised, with no log or raise — a malformed value silently becomes that default. Log the input or fail validation. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment on the handler or in the docstring, and the row stops firing.
Silent fallback default on parse failure metagpt/ext/spo/utils/data_utils.py:21— `load_results` returns `[]` when `json.JSONDecodeError` is raised, with no log or raise — a malformed value silently becomes that default. Log the input or fail validation. If that constant is the correct answer rather than a stand-in for a value that could not be read, say so in a comment on the handler or in the docstring, and the row stops firing.
D16 · Bus Factor· Further sole-owners (lower concentration) · ×1
Further sole-owners (lower concentration) — 4 other contributor(s) are each the sole owner of a small amount of code below the off-boarding threshold — folded into the bus-factor score and metrics (17 single-owned of 266 analysed files in total, counted over production source files of roughly 2,400 bytes or more, excluding vendored, generated and example/demo trees and test files identified by path convention, largest first; 266 of the 516 production source files in this repository met that bar). They are anonymized user #4 (2 file(s)), anonymized user #5 (1 file(s)), anonymized user #6 (1 file(s)), anonymized user #7 (1 file(s)) — spread or document their files in the same way, at lower priority than the named off-boarding risks above. The files folded here: metagpt/exp_pool/decorator.py, metagpt/exp_pool/manager.py, metagpt/ext/spo/app.py, metagpt/rag/benchmark/base.py, metagpt/tools/tool_convert.py.
Documentation: no project overview docs/README_CN.md— The software description is the first paragraph under '## 安装' rather than an overview stating what MetaGPT does and its main value proposition. Move the installation section to the top so readers can see the project's purpose before reading setup.
No ADRs found — No ADRs found. No recognised ADR directory (`docs/adr/`, `docs/decisions/`, `adr/`, `docs/rfcs/`, an `ADR0001/` folder, or their siblings) exists anywhere in this tree. What was searched, so you can tell an empty log from a search that missed one: every directory under the tree (build output, dependencies and VCS metadata excepted), for a document that is either any non-index page inside a recognised ADR directory, whatever its name and however deeply nested (`docs/adr/use-postgres.md`, `docs/adr/2024/0001-x.md`); or a file anywhere whose name is ADR-shaped (`0001-use-postgres.md`, `adr-012-caching.md`); or, when neither turned anything up, a document carrying the decision-record signature (an "Architecture Decision Record" heading, or Status / Context / Decision / Consequences as section headings). A decision log that clears none of these — unnumbered files outside any recognised directory, without those headings — is not seen by this check and this row is then wrong. If that is your case, say so rather than renaming anything; otherwise, consider recording architectural decisions in `docs/adr/`.
D26 · Project Cohesion· Projects may be oversized for their cohesion · ×1
Projects may be oversized for their cohesion — 1 of 4 project(s) overshoot their size bounds, lowering Project Cohesion to 5.0/10. The most over is `(repository root)` (52433 LoC, 849 module-visible types across 77 directories). Review these for cohesion — draw the boundary inside the module first (group each responsibility into its own package or directory and keep the cross-boundary members non-public), since splitting a published package moves types between packages and breaks consumers.
D28 · Secrets (history)· Rotate the exposed credentials · ×1
Dormant codebase — 273 of 273 significant files have no living knowledge — the codebase as a whole is dormant, not 273 separate risks. Counted over 273 of the 516 production source files in this repository: the rest are under the ~2,400-byte size floor this dimension measures over. Re-engage owners or document before change.
No ADRs — 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.
No src/ separation — Production code isn't grouped under a src/ folder — it's spread across several top-level directories, so there's no one place that says 'this is the product'.
Logging is not universal — Only 2/3 runnable modules use logging (modules with no entry point or server are excluded — they are libraries a runnable module hosts). Silent: `metagpt/environment/minecraft/mineflayer`.
No SAST — No static application security testing detected. For this repository's stack, add bandit, `semgrep --config=p/python`, or CodeQL's python pack as a CI step. What was searched, so you can tell an absence from a miss: the 7064 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.
No changelog — No CHANGELOG/HISTORY/RELEASES file — what shipped when isn't easy to reconstruct for support or audit. (Versioning/tagging makes releases traceable, but a changelog records the what.)
Outdated: aiofiles — `aiofiles` is pinned to 23.2.1, but 25.1.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 23.2.1 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: aiohttp — `aiohttp` is pinned to 3.8.6, but 3.14.5 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 3.8.6 until the declaration is edited.
Outdated: anthropic — `anthropic` is pinned to 0.47.2, but 2.3.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.47.2 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: beautifulsoup4 — `beautifulsoup4` is pinned to 4.12.3, but 4.15.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 4.12.3 until the declaration is edited.
Outdated: channels — `channels` is pinned to 4.0.0, but 4.3.2 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 4.0.0 until the declaration is edited.
Outdated: faiss-cpu — `faiss-cpu` is pinned to 1.7.4, but 1.15.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 1.7.4 until the declaration is edited.
Outdated: fire — `fire` is pinned to 0.4.0, but 0.7.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.4.0 until the declaration is edited.
Outdated: gitignore-parser — `gitignore-parser` is pinned to 0.1.9, but 0.1.13 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.1.9 until the declaration is edited.
Outdated: gitpython — `gitpython` is pinned to 3.1.40, but 3.2.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 3.1.40 until the declaration is edited.
Outdated: google-generativeai — `google-generativeai` is pinned to 0.4.1, but 0.8.6 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.4.1 until the declaration is edited.
Outdated: gymnasium — `gymnasium` is pinned to 0.29.1, but 1.4.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.29.1 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: imap-tools — `imap-tools` is pinned to 1.5.0, but 1.16.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 1.5.0 until the declaration is edited.
Outdated: ipykernel — `ipykernel` is pinned to 6.27.1, but 7.4.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 6.27.1 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: ipython — `ipython` is pinned to 8.17.2, but 9.17.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 8.17.2 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: ipywidgets — `ipywidgets` is pinned to 8.1.1, but 8.1.9 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 8.1.1 until the declaration is edited.
Outdated: lancedb — `lancedb` is pinned to 0.4.0, but 0.40.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.4.0 until the declaration is edited.
Outdated: libcst — `libcst` is pinned to 1.0.1, but 1.9.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 1.0.1 until the declaration is edited.
Outdated: loguru — `loguru` is pinned to 0.6.0, but 0.7.3 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.6.0 until the declaration is edited.
Outdated: meilisearch — `meilisearch` is pinned to 0.21.0, but 0.43.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.21.0 until the declaration is edited.
Outdated: nbclient — `nbclient` is pinned to 0.9.0, but 0.11.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.9.0 until the declaration is edited.
Outdated: nbformat — `nbformat` is pinned to 5.9.2, but 5.11.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 5.9.2 until the declaration is edited.
Outdated: openml — `openml` is pinned to 0.14.2, but 0.15.1 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.14.2 until the declaration is edited.
Outdated: pandas — `pandas` is pinned to 2.1.1, but 3.1.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 2.1.1 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: python-docx — `python-docx` is pinned to 0.8.11, but 1.2.0 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 0.8.11 until the declaration is edited. This crosses a major version, so it is a migration rather than a bump.
Outdated: pyyaml — `pyyaml` is pinned to 6.0.1, but 6.0.3 is the current stable release on PyPI. An exact pin never moves on its own, so this repository installs 6.0.1 until the declaration is edited.
+ 13 more in this group — see findings.md.
Appendix B — Reproduction & audit trail
Every external tool invocation behind a deep-scan dimension — the tool, its captured version, the exact command, how many findings it yielded, and a link to the retained raw output. To reproduce any finding: check out the same commit and run the command shown (repo-relative — never an absolute scratch path). The complete raw scanner output is retained verbatim under artifacts/raw/ (indexed in artifacts/raw/index.json); per-invocation exit codes and wall-clock durations are in sidecar.json — kept out of this table so the rendered report stays byte-identical across runs of the same commit.
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.
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.
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.
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.
Run 01a170c8-d118-7d66-9390-e11706fab0ec · every finding is also locatable in findings.md, and the complete scoring record (with exit codes + durations) in sidecar.json.
Issues: 49 · Warnings: 339 · Recommendations: 315 · Info: 38 — Appendix A · all findings · full markdown report.
Generated by Watchdog — deterministic code-health analysis. 25-10-2026 @ 01:59 UTC.
Downloadable artifacts
Machine-readable and reproducible from this commit + frozen rubric — drop them straight into a contract appendix, a CRA dossier, or a downstream SCA / VEX tool.