kdeps-tools-session_ops

version: 1.14.0
category: agent
# Served on the kdeps API for slash commands (commands/clear, compact,
# history, copy) and for the tools that live only in an agent session
# (operation: tool); the model is not offered it. The REPL operations
# return JSON; tool returns that tool's answer.
description: "Read or change the active agent session: messages lists every message ({turns, messages: [{turn, role, content}]}); last_reply is the latest assistant message ({text}); get returns a session setting's state ({value, ...}); set stores a value the setting's command asset lists and returns the new state; clear empties the history, summarizing it first when it has at least summarize_min_turns turns ({turns, summary}); compact folds older turns into a summary ({summary, turns, keep}); sessions lists this folder's saved sessions ({sessions: [{id, name, prompt, model, turns, updated}]}); save stores the session ({id, name}); load and import make a saved session (or a JSONL file at path) the live one ({id, turns}); delete removes one ({id}); checkpoint marks the current entry ({id}); goto returns to an entry, stashing the turns after it ({id, found, turns}); branches lists the stashed ones ({branches: [{branch, at, ids}]}); model switches the model (name: a model, a .gguf/.llamafile URL, or an OpenAI-compatible base URL; {model, registered?, ambiguous?, closest?}); model_pick opens the model picker ({model, picked}); model_default saves the startup model ({model}); models lists cloud models by backend and local ones ({current, cloud, local}); model_favorite stars a model (on: on|off); loop_settings reads the agent loop settings and loop_set changes one (setting, value); servers lists running local model servers and server_kill stops one (model); hf_download downloads a GGUF file from HuggingFace and registers it (repo, file; {path, alias}); model_record is the current model's record of caught refusals ({model, count, refusals: [{kind, text, at}]}) and model_record_clear deletes it ({model, cleared}); skills and prompts list the loaded skills ({skills: [{name, description}]}) and prompt templates ({prompts: [{name, hint, description}]}); reload rereads them from disk ({skills, prompts}: counts); memory_entries lists memory entries, all or the matches of query, by key or (order recent) newest first, capped by limit ({total, more, query, entries: [{key, type, value}]}); memory_entry is one entry in full ({key, type, value, related, updated, graph}); judges is the judge panel ({judges: [{name, criteria, graders}], auto, last}); judge_add (name, criteria), judge_remove (name), judge_grade (name, kind, pattern) and judges_clear change it; harness_sections, harness_events, presets and harness_reminders list the harness sections, events, presets and reminders, and harness_set, event_set, preset_apply and reminder_set change them (name, enabled: on|off); efficiency is enforcement's state ({value, verbose, prompt, limits}), efficiency_limit sets one limit (setting, value: a count or off) and efficiency_reset restores the defaults; recall recalls knowledge vault notes for query, or returns the last turn's recall ({seeds, hits, tokens}); knowledge is the vault's state ({value, vault, graph}) and knowledge_extract reads the changed notes with the local model ({output}); last_request is the last request sent to the LLM with token estimates (raw: true for JSON); search_index, search_folders and search_folder (action: add|remove, folder) manage the folders the project searches; commands_help lists every installed command's usages; konfig_export and konfig_import write and apply a konfig file (path); pipelines is /kartographer's live state; tool runs one tool that exists only in the agent session (judge_verdict, knowledge_recall, knowledge_card_get, knowledge_card_update, knowledge_note_save, load_skill, identity_get, session_handshake) with args and returns its answer."
outputFormat: json
parameters:
  operation:
    type: string
    description: "messages, last_reply, get, set, clear, compact, sessions, save, load, delete, import, checkpoint, goto, branches, model, model_pick, model_default, models, model_favorite, loop_settings, loop_set, servers, server_kill, hf_download, model_record, model_record_clear, skills, prompts, reload, memory_entries, memory_entry, judges, judge_add, judge_remove, judge_grade, judges_clear, harness_sections, harness_set, harness_events, event_set, presets, preset_apply, harness_reminders, reminder_set, efficiency, efficiency_limit, efficiency_reset, recall, knowledge, knowledge_extract, last_request, search_index, search_folders, search_folder, commands_help, konfig_export, konfig_import, pipelines or tool"
    required: true
  summarize_min_turns:
    type: integer
    description: "clear only: summarize the branch first when the session has at least this many turns; 0 never summarizes"
  key:
    type: string
    description: "get and set: the session setting (refine, handshake, autocontext, permission, tools, thinking, theme, turo, fold, fold-threshold, fold-items, model-name, auto-judges, efficiency, efficiency-verbose, efficiency-prompt, knowledge, context); memory_entry: a memory key"
  value:
    type: string
    description: "set: one of the values the setting's command asset lists (commands/<name>.yaml setting: values); loop_set: the setting's new value"
  tool:
    type: string
    description: "tool only: the session tool to run (judge_verdict, knowledge_recall, knowledge_card_get, knowledge_card_update, knowledge_note_save, load_skill, identity_get, session_handshake)"
  args:
    type: object
    description: "tool only: the session tool's arguments, as its own tool asset declares them"
  id:
    type: string
    description: "load, delete: a saved session id; goto: an entry id"
  name:
    type: string
    description: "save: an optional name for the saved session; model, model_default, model_favorite: a model name"
  path:
    type: string
    description: "import: a JSONL session file; konfig_export, konfig_import: the konfig file"
  filter:
    type: string
    description: "model_pick only: text the picker starts filtered by"
  "on":
    type: string
    description: "model_favorite only: on stars, off unstars"
  setting:
    type: string
    description: "loop_set only: rounds, retries, retry-delay, stall-timeout, compact-threshold, compact-budget, max-turns, history-tokens, web-limit, bash-limit, file-limit, code-limit, leaf-nodes or leaf-chars"
  model:
    type: string
    description: "server_kill only: the model whose local server to stop"
  repo:
    type: string
    description: "hf_download only: a HuggingFace repo id"
  file:
    type: string
    description: "hf_download only: a .gguf file in the repo"
  query:
    type: string
    description: "memory_entries: words to search memory for; recall: what to recall notes for"
  order:
    type: string
    description: "memory_entries only: recent lists the newest first"
  limit:
    type: integer
    description: "memory_entries only: most entries to return"
  criteria:
    type: string
    description: "judge_add only: what the judge checks"
  kind:
    type: string
    description: "judge_grade only: exact, contains, not_contains, regex, json or expr"
  pattern:
    type: string
    description: "judge_grade only: the grader's pattern (json needs none)"
  enabled:
    type: string
    description: "harness_set, event_set, reminder_set only: on or off"
  raw:
    type: string
    description: "last_request only: true returns the request as JSON"
  action:
    type: string
    description: "search_folder only: add or remove"
  folder:
    type: string
    description: "search_folder only: the folder"