'compaction' 검색 결과

Self-knowledge for stella, the self-hosted AI assistant. Use when users ask about configuration, setup, onboarding, providers, models, agents, channels, webhooks, memory, schedules, workflows, goals, workers, skills, plugins, session compaction, notifications, self-update, multi-user behavior, or how stella works. Also use for changing models, setting up channels or webhooks, configuring providers, updating stella, onboarding, switching agents, reporting bugs, and goal status or acceptance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Parse Claude Code JSONL session logs from ~/.claude/projects/ for tool call inventory, token costs, error detection, subagent traces, and compaction detection

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when verification depends on agent runtime phases, queued input, tool-call lifecycle, save points, retry, abort, compaction, or branch behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reads, searches and counts Claude Code session transcripts (the .jsonl files under ~/.claude/projects, subagents too) with the csift command-line tool, and ships hooks that re-inject compacted turns or record pending questions. Use when asked what a past or running session said, did, edited, spent or is doing now; when about to grep, jq or script over a transcript jsonl (a type=="user" filter overcounts the person's messages), count how many messages the person typed, tool calls or tokens, or claim something was never done or decided; to rebuild a lost file or plan from what a session wrote, extract pasted images, restore turns a compaction summary lost, find a subagent's own id when CLAUDE_CODE_SESSION_ID names the parent, wait on or message another session or subagent; or when csift prints "unknown label selector", "show needs an address", "looks like a session/agent id, not a project path" or "0 matches — a DEFINITIVE absence". Not for semantic or embedding search: csift matches regular expressions only.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Without identity infrastructure, every Claude Code session starts from zero. The agent has no name, no remembered preferences, no sense of who it works with or what it has learned. Context compaction erases everything mid-session. This skill fixes that — no external tools required.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build PFC 5.0 asphalt-mixture specimens with explicit aggregate objects, a declared homogenized-mastic or fine-particle abstraction, residual air voids, measured gradation conversion, contact-pair assignment, compaction, equilibrium, and mass-volume closure; use before Marshall, rutting, creep, or strength tests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manage LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

On-demand situational awareness — fresh git/PR snapshot plus continuation, distilled into one concrete "next action" suggestion. Use mid-session when you've lost track, after a compaction, or starting a new work block. Trigger on "where was I", "what's next", "progress", "what should I do now", "/progress".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when developing plugins, tools, and extensions for OpenCode v1 - plugin contract, crash-prevention rules, ctx/event APIs, subagent lifecycle (abort races, compaction, orphan detection), MCP integration, testing patterns, or publishing to npm

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write effective MCP server instructions for tool compaction support. Use when creating or updating the `instructions` parameter in MaaSProtectedFastMCP server initialization. Helps LLMs understand when to search for tools, workflow patterns, and cross-feature relationships.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a task needs the judgment of a Civil Engineering Technician — running and interpreting a concrete field acceptance test (slump, air content, cylinder breaks against ACI 318 criteria), verifying soil compaction against a Proctor density curve, reconciling a concrete or rebar quantity takeoff against a pay application, or documenting a field condition that deviates from the approved plans for the engineer of record.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-board communications, realtime voice agents, hardware agents and board deployment, self-refining recursive harnesses, programmable context, continual refinement, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Update PROJECT_CONTINUITY.md and notes.toml with current session state. Use proactively before context compaction or when switching tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Verify all cqs features work. Run on session start and after compaction.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Maintain SESSION-STATE.md, the durable within-session memory that survives context compaction. Use when a constraint, settled decision, existing-infrastructure (survey) finding, or open thread must persist across a long session so it is not re-derived or re-litigated. Triggers on /state, "remember this for the session", "record this constraint/decision", or after surveying what already exists. For cross-session/personal memory use .claude/memory/ on Claude or native memories on Codex; for repo-derivable facts, do not record at all.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for agent-tree overhead audit (context-audit).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persists and restores mid-session workflow progress across context resets. Use when resuming workflows, saving state, or handling context compaction. Triggers on: handoff, save state, resume workflow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.