Skip to main content
Glama

Release conversation

dsh_release
DestructiveIdempotent

Release the DSH process for a conversation to free its write lock so another DSH GUI can open it; optionally remove it from the registry or release all idle conversations to free memory.

Instructions

Release the DSH process a conversation occupies (this frees the write lock so the user can open the same conversation in their own DSH GUI). The conversation stays on disk and can be resumed later; forget=true writes a tombstone: it is removed from the registry and later lookups by id say it was forgotten (to bring it back, delete the tombstone file named in the error, by default $DSH_HOME/.dsh-any-agent-forgotten/<id>.json). To free memory in one go when you are done, pass all=true (each conversation is about 300-480 MB; the default MAX_LIVE=4 already reaps the least recently used one; all=true releases idle conversations and skips ones running a turn unless force=true). Releasing a single conversation stops its DSH process; if a turn is running, it is interrupted.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "dsh_release"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoIgnore conversation_id and release every **idle** conversation process (to free memory). Conversations running a turn are skipped by default. Default false.
forceNoOnly with all=true: also stop conversations that are running a turn (those turns are interrupted). Default false.
forgetNoAlso remove it from this server's registry. Default false.
conversation_idNoConversation id, from dsh_start or dsh_list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.6.8
    • changedInput schema / properties / all / description
      Previous value: -"忽略 conversation_id,释放所有**空闲**会话进程(腾内存用)。正在跑回合的默认跳过。默认 false。"New value: +"Ignore conversation_id and release every **idle** conversation process (to free memory). Conversations running a turn are skipped by default. Default false."
    • changedInput schema / properties / conversation_id / description
      Previous value: -"会话 id,来自 dsh_start 或 dsh_list。"New value: +"Conversation id, from dsh_start or dsh_list."
    • changedInput schema / properties / force / description
      Previous value: -"仅配合 all=true:连正在跑回合的会话也停掉(会中断那些回合)。默认 false。"New value: +"Only with all=true: also stop conversations that are running a turn (those turns are interrupted). Default false."
    • changedInput schema / properties / forget / description
      Previous value: -"同时从本服务的注册表里移除,默认 false。"New value: +"Also remove it from this server's registry. Default false."
  2. Changed2 schema fields changedv0.5.1
    • changedInput schema / properties / all / description
      Previous value: -"忽略 conversation_id,释放**所有**活着的会话进程(腾内存用)。默认 false。"New value: +"忽略 conversation_id,释放所有**空闲**会话进程(腾内存用)。正在跑回合的默认跳过。默认 false。"
    • addedInput schema / properties / force
      Added value: +{
      +  "description": "仅配合 all=true:连正在跑回合的会话也停掉(会中断那些回合)。默认 false。",
      +  "type": "boolean"
      +}
  3. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Far exceeds the annotations: it discloses that the conversation survives on disk, that forget=true writes a tombstone and removes it from the registry, and even gives the recovery path (delete `$DSH_HOME/.dsh-any-agent-forgotten/<id>.json`) named in the error. It also quantifies memory per conversation, names the `MAX_LIVE=4` LRU default, and warns that a running turn is interrupted. All consistent with destructiveHint=true and idempotentHint=true.

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

Conciseness4/5

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

Front-loads the core action and its rationale, then layers the riskier options. It is dense with nested parentheses and bolded flags, which costs some readability, but nearly every clause carries operational information.

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

Completeness4/5

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

Covers the key things an agent needs for a destructive, no-output-schema tool: what persists, what is destroyed, how to reverse it, memory implications, and the interrupted-turn caveat. It does not describe the success response shape beyond the error case, a minor gap given the tool's complexity.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains the tombstone consequence of forget=true and how to undo it, and the all/force interaction where running turns are skipped unless forced. Only conversation_id gets no extra treatment, which is acceptable given the schema's `from dsh_start or dsh_list` hint.

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?

States a specific verb and resource ('Release the DSH process a conversation occupies') and immediately clarifies the effect ('frees the write lock so the user can open the same conversation in their own DSH GUI'). This makes it distinguishable from lifecycle siblings like dsh_interrupt or dsh_takeover without opening any schema.

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

Usage Guidelines4/5

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

Gives clear situational context: use it to hand a conversation back to the user's GUI, and use all=true 'when you are done' to free memory. It also explains the idle-only default and the force escape hatch. It does not explicitly contrast against interrupt-style siblings, so it stops short of full when-not guidance.

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