Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Proves defects in Python functions by executing them, and verifies proposed fixes the same way. Conditions are Python expressions. A 'proven' finding is reproducible by hand; 'unconfirmed' means not found within budget and is not a proof of safety.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
buggy_functionsA

List the functions in a Python file with their signatures, and say which can be investigated. Call this first when you do not know what is in a file, or when a function turns out not to be investigable and you need the reason.

buggy_investigateA

Prove whether a Python function has a defect, by executing it on generated inputs. Returns a certificate naming the exact failing call, verified three ways: the input satisfied the preconditions, the failure was re-observed in a fresh process, and it recurred on repeat attempts. A proven finding is reproducible by hand. 'unconfirmed' means no failing input was found within the budget and is NOT a proof of safety. Use this before editing a risky function, and after editing one to check the fix held.

buggy_repairA

Prove a defect and then propose fixes, each verified by execution: does it parse, does the proven trigger stop failing, does anything that worked change, and do other inputs of the same shape get fixed too. Verdicts are 'verified', 'overfit' or 'rejected', each with the evidence. Nothing is written to the file. Show the user a verified patch and let them decide; apply it yourself only if they agree.

buggy_recallA

Report what is already known about a function: defects previously proven against it, whether each was later observed fixed, and whether any came back. Call this BEFORE editing a risky function, so a defect that was already fixed once is not reintroduced. Answers come from stored triggers that can be re-run, not from remembered advice.

buggy_recheckA

Re-run every recorded trigger and report what changed: still failing, now fixed, regressed, or unreachable because the code moved. 'regressed' means a defect that had been observed fixed is failing again, which is the signal worth acting on. Use this after making changes, or to decide whether a fix held.

buggy_scanA

Investigate every supported function in a Python file and return one line per function. Use it to triage a file you are unfamiliar with. Note that any preconditions and postconditions apply to all functions alike, which is blunt; investigate individually for anything that matters.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.9/5.0

Scored across 6 tools

Disambiguation4/5

Each tool has a recognizably distinct role (list functions, recall history, investigate one function, repair, recheck, bulk scan), and the descriptions explicitly disambiguate the two closest pairs: investigate vs scan, and recall vs recheck. The remaining overlap is mild but real: scan is essentially a batched investigate, and recall and recheck both surface prior defect state, so an agent may hesitate between them in edge cases.

Naming Consistency4/5

All six tools share a consistent 'buggy_' namespace prefix followed by a short, predictable verb or noun. The only deviation is buggy_functions, which is a noun where every other tool uses a verb-style label, but it remains readable and idiomatic for a discovery tool.

Tool Count5/5

Six tools is tightly scoped to a single, well-defined workflow (discover, recall, prove, repair, recheck, triage). Every tool corresponds to a distinct stage with no filler, and the surface is small enough that an agent can hold the whole model in mind.

Completeness4/5

The lifecycle is nearly fully covered: discovery, historical recall, proof, patch proposal, regression recheck, and bulk triage all exist. The deliberate exclusion of file writing (repair only proposes) and the lack of any tool to manage or clear stored triggers/records are the only notable gaps, both workable around.

Maintenance

ActivityActive
ResponsivenessOutdated data