Skip to main content
Glama

Continue Kimi session [experimental]

kimi_continue

Resumes an existing Kimi session thread in the same workspace so you can send follow-up prompts; pass the original project directory and run it only after an initial Kimi ask.

Instructions

Continue the Kimi session (EXPERIMENTAL): resumes the thread rooted at this workspace (kimi -c; Kimi scopes sessions per directory), so pass the same workspace= as the ask (without it the sub-agent sees no repo). Errors if no kimi_ask ran there. NO sandbox: trusted prompts only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "kimi_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYesFollow-up message for the existing session.
timeout_sNoMax seconds to wait for kimi to complete. Default 180.
workspaceNoWorking root used by the prior session. Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.26.0

TDQS

A4.1/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the no-sandbox/'trusted prompts only' security posture, the session-scoping behavior, and the failure mode when no prior ask exists. Annotations already cover mutability and open-world nature; the description usefully adds that omitting workspace silently degrades ('the sub-agent sees no repo') rather than erroring.

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 verb and the EXPERIMENTAL flag, then chains prerequisite, workspace constraint, failure mode, and safety note in a compact parenthetical style. The nested parentheses and semicolons make it dense, but no sentence is filler.

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?

An output schema exists, so return values need no explanation, and the three parameters are fully schema-documented. The description covers prerequisites, the workspace-footgun, error condition, and security posture for a session-mutating agent call; only multi-session/concurrency behavior is unstated.

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 description coverage is 100%, so the schema already documents prompt, timeout_s, and workspace individually. The description adds real meaning only for workspace (it must equal the prior session's root), which is valuable but scoped to one of three parameters; the prompt and timeout semantics are left entirely to the schema.

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 ('continue the Kimi session / resumes the thread') and names the sibling it depends on ('kimi_ask'). The per-directory scoping note ('Kimi scopes sessions per directory') further distinguishes it from the sibling *_continue tools by tying it to one agent family.

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?

Explicitly requires that a prior kimi_ask ran in the same workspace ('Errors if no kimi_ask ran there'), which is a clear when-to-use prerequisite and implicitly routes new conversations to kimi_ask. It does not spell out the inverse case (use kimi_ask for fresh sessions) or what to do on a workspace mismatch, so it falls just short of a 5.

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