Skip to main content Accueil Créateurs jeremylongshore tons-of-skills-marketplace mistral-debug-bundle
mistral-debug-bundle Collect Mistral AI debug evidence for support tickets and troubleshooting.
Use when encountering persistent issues, preparing support tickets,
or collecting diagnostic information for Mistral AI problems.
Trigger with phrases like "mistral debug", "mistral support bundle",
"collect mistral logs", "mistral diagnostic".
Aller à l'installation Skills Marketplace Découvrez et explorez les compétences IA créées par la communauté.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Afficher les détails du prompt Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill mistral-debug-bundleLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Télécharger Zip Téléchargement... Plus depuis ce dépôt langchain-deploy-integration Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
langchain-langgraph-agents Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
langchain-langgraph-human-in-loop Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before /
interrupt_after and Command(resume=...) — JSON-serializable state, clean
resume semantics, and UI wiring for approval decisions. Use when adding an
approval gate before an expensive tool call, wiring a Slack/web UI for agent
approvals, or debugging a graph that crashes on interrupt.
Trigger with "langgraph human in loop", "langgraph interrupt_before",
"langgraph approval flow", "Command resume", "langgraph HITL".
name mistral-debug-bundle description Collect Mistral AI debug evidence for support tickets and troubleshooting.
Use when encountering persistent issues, preparing support tickets,
or collecting diagnostic information for Mistral AI problems.
Trigger with phrases like "mistral debug", "mistral support bundle",
"collect mistral logs", "mistral diagnostic".
allowed-tools Read, Bash(grep:*), Bash(curl:*), Bash(tar:*), Grep version 1.12.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","mistral","debugging"] compatibility Designed for Claude Code
Mistral AI Debug Bundle
Current State
!node --version 2>/dev/null || echo 'N/A'
!python3 --version 2>/dev/null || echo 'N/A'
Overview
Collect all necessary diagnostic information for Mistral AI support tickets. Creates a redacted bundle with environment info, SDK versions, API connectivity test, available models, and recent error logs.
Prerequisites
Mistral AI SDK installed
Access to application logs
MISTRAL_API_KEY set (for connectivity test)
Instructions
Step 1: Complete Debug Script
#!/bin/bash
set -e
BUNDLE_DIR="mistral-debug-$(date +%Y%m%d-%H%M%S) "
mkdir -p "$BUNDLE_DIR "
echo "Creating Mistral AI debug bundle..."
cat > "$BUNDLE_DIR /summary.txt" << EOF
=== Mistral AI Debug Bundle ===
Generated: $(date -u +%Y-%m-%dT%H:%M:%SZ)
Hostname: $(hostname)
--- Environment ---
Node.js: $(node --version 2>/dev/null || echo 'not installed')
Python: $(python3 --version 2>/dev/null || echo 'not installed')
npm: $(npm --version 2>/dev/null || echo 'not installed')
OS: $(uname -a)
MISTRAL_API_KEY: ${MISTRAL_API_KEY:+[SET, length=${#MISTRAL_API_KEY}]}${MISTRAL_API_KEY:-[NOT SET]}
EOF
echo -e "\n--- SDK Versions ---" >> "$BUNDLE_DIR /summary.txt"
npm list @mistralai/mistralai 2>/dev/null >> "$BUNDLE_DIR /summary.txt" \
|| echo "Node SDK: not installed" >> "$BUNDLE_DIR /summary.txt"
pip show mistralai 2>/dev/null | grep -E "^(Name|Version)" >> "$BUNDLE_DIR /summary.txt" \
|| echo
"Python SDK: not installed"
"$BUNDLE_DIR /summary.txt"
echo
"\n--- API Connectivity ---"
"$BUNDLE_DIR /summary.txt"
if
"${MISTRAL_API_KEY:-} "
then
"$BUNDLE_DIR /api-response.json"
"%{http_code}"
"Authorization: Bearer ${MISTRAL_API_KEY} "
echo
"HTTP Status: $HTTP_STATUS "
"$BUNDLE_DIR /summary.txt"
if
"$HTTP_STATUS "
"200"
then
echo
"\n--- Available Models ---"
"$BUNDLE_DIR /summary.txt"
'.data[].id'
"$BUNDLE_DIR /api-response.json"
"$BUNDLE_DIR /summary.txt"
fi
rm
"$BUNDLE_DIR /api-response.json"
else
echo
"Skipped (no API key)"
"$BUNDLE_DIR /summary.txt"
fi
if
"package.json"
then
echo
"\n--- Dependencies ---"
"$BUNDLE_DIR /summary.txt"
'{dependencies, devDependencies}'
"$BUNDLE_DIR /summary.txt"
fi
echo
"--- Recent Logs (redacted) ---"
"$BUNDLE_DIR /logs.txt"
if
"logs"
then
"mistral\|error\|429\|401\|500"
log
tail
"$BUNDLE_DIR /logs.txt"
fi
if
".env"
then
's/=.*/=***REDACTED***/'
env
"$BUNDLE_DIR /config-redacted.txt"
fi
cat
"$BUNDLE_DIR /reproduce.sh"
'SCRIPT'
set
"Content-Type: application/json"
"Authorization: Bearer ${MISTRAL_API_KEY} "
'{"model":"mistral-small-latest","messages":[{"role":"user","content":"ping"}]}'
echo
"\nExit code: $?"
chmod
"$BUNDLE_DIR /reproduce.sh"
"$BUNDLE_DIR .tar.gz"
"$BUNDLE_DIR "
rm
"$BUNDLE_DIR "
echo
"Bundle: $BUNDLE_DIR .tar.gz"
echo
"IMPORTANT: Review for sensitive data before sharing!"
Step 2: TypeScript Debug Helper import { Mistral } from '@mistralai/mistralai' ;
interface DebugInfo {
timestamp : string ;
nodeVersion : string ;
apiKeySet : boolean ;
apiKeyLength : number ;
connectivity : 'ok' | 'auth_error' | 'network_error' | 'unknown_error' ;
availableModels : string [];
latencyMs : number ;
lastError ?: { message : string ; status ?: number };
}
async function collectDebugInfo (error ?: Error Promise <DebugInfo > {
const info : DebugInfo = {
timestamp : new Date ().toISOString (),
nodeVersion : process.version ,
apiKeySet : !!process.env .MISTRAL_API_KEY ,
apiKeyLength : process.env .MISTRAL_API_KEY ?.length ?? 0 ,
connectivity : 'unknown_error' ,
availableModels : [],
latencyMs : 0 ,
};
if (error) {
info.lastError = {
message : error.message ,
status : (error as any ).status ,
};
}
if (info.apiKeySet ) {
const start = performance.now ();
try {
const client = new Mistral ({ apiKey : process.env .MISTRAL_API_KEY });
const models = await client.models .list ();
info.connectivity = 'ok' ;
info.availableModels = models.data ?.map (m =>id ) ?? [];
info.latencyMs = Math .round (performance.now () - start);
} catch (e : any ) {
info.latencyMs = Math .round (performance.now () - start);
info.connectivity = e.status === 401 ? 'auth_error' : 'network_error' ;
}
}
return info;
}
try {
await client.chat .complete ({ model : 'mistral-small-latest' , messages });
} catch (error) {
const debug = await collectDebugInfo (error as Error );
console .error ('Debug info:' , JSON .stringify (debug, null , 2 ));
}
Step 3: Request/Response Logger for Debugging function createDebugClient (Mistral {
const client = new Mistral ({ apiKey : process.env .MISTRAL_API_KEY });
const originalComplete = client.chat .complete .bind (client.chat );
client.chat .complete = async (params : any ) => {
const start = performance.now ();
console .debug ('[MISTRAL REQUEST]' , {
model : params.model ,
messageCount : params.messages ?.length ,
hasTools : !!params.tools ?.length ,
temperature : params.temperature ,
});
try {
const response = await originalComplete (params);
console .debug ('[MISTRAL RESPONSE]' , {
durationMs : Math .round (performance.now () - start),
finishReason : response.choices ?.[0 ]?.finishReason ,
usage : response.usage ,
hasToolCalls : !!response.choices ?.[0 ]?.message ?.toolCalls ?.length ,
});
return response;
} catch (error : any ) {
console .debug ('[MISTRAL ERROR]' , {
durationMs : Math .round (performance.now () - start),
status : error.status ,
message : error.message ,
});
throw error;
}
};
return client;
}
Sensitive Data Rules ALWAYS REDACT: API keys, passwords, PII (emails, names), internal URLs
SAFE TO INCLUDE: Error messages, stack traces, SDK versions, HTTP status codes, model IDs
Output
mistral-debug-YYYYMMDD-HHMMSS.tar.gz containing:
summary.txt — environment, SDK versions, API statuslogs.txt — recent redacted error logsconfig-redacted.txt — config with secrets maskedreproduce.sh — minimal reproduction script
Error Handling Item Purpose Environment versions Compatibility check SDK version Version-specific bug identification API connectivity test Network/auth diagnosis Available models Key scope verification Error logs (redacted) Root cause analysis
Resources
Next Steps For rate limit issues, see mistral-rate-limits. For common errors, see mistral-common-errors.
