Skip to main content
Glama

memory_reconcile_candidates

Groups similar task memos into candidates for reconciliation, identifies outdated directions, and prepares promotion material, enabling efficient memory consolidation without LLM processing.

Instructions

按需整理·粗筛:返回情景层候选组 + 方向层清单 + 蒸馏素材 + 操作说明。

记忆整理 = 会话内按需显式动作(CC 非常驻,无后台整理进程)。本工具只做 确定性粗筛(零 LLM)——OS 无独立 LLM 凭据,判定由你(调用工具的会话内 agent)完成,工具只负责候选粗筛与操作应用("agent 算、工具存")。

返回四块(project_id 自动按当前上下文解析):

  • candidate_groups:有效 task_memos 按 scope_path/task 聚簇、簇内 BM25 两两 相似度超阈配对成的候选组(含组内各条全文 + id)。逐组做 LLM 精判: KEEP(都留)/ MERGE(合并)/ INVALIDATE(矛盾失效)/ NOOP(不动)。

  • direction_inventory:全部有效方向层条目全文——逐条做陈旧检查(引用的 功能已退役/版本过时/世界已变 → 提 invalidate)。

  • promotion_candidates:高频跨任务反复出现的簇,蒸馏为方向层条目的素材 (promote 操作,source_refs 回指源 memo)。

  • operation_guide:四操作语义 + reconcile 三守则(只留高频有用 / 指向权威 而非复述 / 重写精简优先)+ 量大开 ultracode 提示。

判完后把确认的操作交给 memory_reconcile_apply 批量应用。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thresholdNo簇内 BM25 相似度配对阈值(0-1,默认 0.45)
scope_pathNo仅整理该路径作用域的 memo(留空=全项目有效 memo)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries full burden. It discloses deterministic behavior (zero LLM), no independent LLM credentials, the agent's role in judgment, and the tool's role in coarse selection and operation application. It also details the four return blocks and their structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is quite long and includes detailed operational instructions that could be provided elsewhere. While structured with bullet points and bold, it could be more concise. Every sentence adds value, but overall length exceeds what is strictly necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (memory reconciliation with multiple output types and manual LLM steps), the description is highly complete. It explains the four output blocks, what to do with them (LLM judgment), and points to the next tool (memory_reconcile_apply). Output schema further complements completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description does not add extra meaning beyond the schema for the two parameters (threshold and scope_path). It mentions them briefly but does not elaborate on their effects or defaults more than the schema already does.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: returning candidate groups, direction inventory, promotion candidates, and operation guide for memory reconciliation. It uses specific verbs ('return', '粗筛') and distinguishes from the sibling tool 'memory_reconcile_apply' which handles the batch application step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly explains when to use this tool (for session-based memory reconciliation as a deterministic coarse filter) and contrasts it with the LLM's judgment role and the subsequent 'memory_reconcile_apply' step. It also clarifies that this is an on-demand action, not a background process.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CronusL-1141/AI-company'

If you have feedback or need assistance with the MCP directory API, please join our Discord server