Data Engineering Technologies.
SQL, Python, Kafka, Spark, Pandas, Airflow, Clickhouse, Greenplum, Postgres, dbt, LLM, Agentic systems, AI, robots, drones etc.
Boost channel - https://t.me/boost/data_engi
Post #1017
346

- 😁 12
- 👏 2
- ❤🔥 1
AG @data_engi
Showing posts older than #1018 · Back to latest

Forwarded from #N/A
Forwarded from Марков цепи пропил



Forwarded from Data Secrets

AGENTS.md: ~/.codex/AGENTS.mdAGENTS.md AGENTS.override.mdcode_mapper# .codex/agents/code-mapper.toml
name = "code_mapper"
description = "Read-only codebase explorer for locating the relevant frontend and backend code paths."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
developer_instructions = """
Map the code that owns the failing UI flow.
Identify entry points, state transitions, and likely files before the worker starts editing.
"""
browser_debugger# .codex/agents/browser-debugger.toml
name = "browser_debugger"
description = "UI debugger that uses browser tooling to reproduce issues and capture evidence."
model = "gpt-5.4"
model_reasoning_effort = "high"
sandbox_mode = "workspace-write"
developer_instructions = """
Reproduce the issue in the browser, capture exact steps, and report what the UI actually does.
Use browser tooling for screenshots, console output, and network evidence.
Do not edit application code.
"""
[mcp_servers.chrome_devtools]
url = "http://localhost:3000/mcp"
startup_timeout_sec = 20
ui_fixer# .codex/agents/ui-fixer.toml
name = "ui_fixer"
description = "Implementation-focused agent for small, targeted fixes after the issue is understood."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
developer_instructions = """
Own the fix once the issue is reproduced.
Make the smallest defensible change, keep unrelated files untouched, and validate only the behavior you changed.
"""
Investigate why the settings modal fails to save.
Have browser_debugger reproduce it,
code_mapper trace the responsible code path,
and ui_fixer implement the smallest fix once the failure mode is clear.
Review this branch against main.
Have pr_explorer map the affected code paths,
reviewer find real risks,
and docs_researcher verify the framework APIs that the patch relies on.
/agent в CLI. Субагенты также наследуют текущую sandbox policy.# .codex/agents/docs-researcher.toml
name = "docs_researcher"
description = "Documentation specialist that uses the docs MCP server to verify APIs and framework behavior."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
developer_instructions = """
Use the docs MCP server to confirm APIs, options, and version-specific behavior.
Return concise answers with links or exact references when available.
Do not make code changes.
"""
[mcp_servers.openaiDeveloperDocs]
url = "https://developers.openai.com/mcp"
# .codex/agents/reviewer.toml
name = "reviewer"
description = "PR reviewer focused on correctness, security, and missing tests."
model = "gpt-5.4"
model_reasoning_effort = "high"
sandbox_mode = "read-only"
developer_instructions = """
Review code like an owner.
Prioritize correctness, security, behavior regressions, and missing test coverage.
Lead with concrete findings, include reproduction steps when possible, and avoid style-only comments unless they hide a real bug.
"""
.toml файл в .codex/agents/.name, description, developer_instructions.model, model_reasoning_effort, sandbox_mode, mcp_servers, skills.config и nickname_candidates. Если их не указывать, они наследуются от родительской сессии.# .codex/agents/pr-explorer.toml
name = "pr_explorer"
description = "Read-only codebase explorer for gathering evidence before changes are proposed."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
developer_instructions = """
Stay in exploration mode.
Trace the real execution path, cite files and symbols, and avoid proposing fixes unless the parent agent asks for them.
Prefer fast search and targeted file reads over broad scans.
"""
.codex/config.toml:[agents]
max_threads = 6
max_depth = 1
max_threads — сколько agent threads можно держать открытыми одновременно, по дефолту - 6
🟢max_depth — глубина вложенности спауна; по умолчанию 1, то есть дочерний агент может появиться, но более глубокая рекурсия уже режется