Create
Query
event_store.db
—
events
actions
agent_runs
approvals
artifacts
commitments
constraints
conversation_compaction
conversation_state
conversation_turns
dead_letters
decisions
deliveries
effects
email_messages
email_reply_drafts
email_threads
entities
entity_aliases
entity_tags
episode_context_index
episodes
event_subjects
events
events_archive
fact_sources
facts
inbox_items
inbox_links
intel_memory
jobs
leader_leases
links
memory_candidates
memory_embeddings
memory_items
memory_items_fts
(v)
memory_items_fts_config
memory_items_fts_data
memory_items_fts_idx
opportunity_memory
pending_interactions
proposal_sources
proposals
reminders
schedules
schema_migrations
signal_candidates
signal_fps
signals
sms_conversations
sms_messages
sms_reply_drafts
source_cursors
sources
sqlite_sequence
sqlite_stat1
stream_cursors
threads
watchers
Toggle helper tables
memory_items_fts_content
memory_items_fts_docsize
memory_items_fts_segdir
memory_items_fts_segments
memory_items_fts_stat
Structure
Content
Query
Insert
Drop
Import
Export
Update row 58448 in events
seq
Primary key.
INTEGER
id
evt_f24de1dddc64
TEXT NOT NULL
kind
cognition_proposal
TEXT NOT NULL
ts
2026-04-16T18:07:29.420497+00:00
TEXT NOT NULL
actor
cognition
TEXT
subject_entity_ids
[]
TEXT
payload
{"context_ref":{"dedupe_key":"ctx:b8ce08ef45d8","event_id":"evt_4be1fdf994ee","kind":"episode_context_built"},"episode_id":"ep_ca1803357286","model":"gpt-5.4-nano","prompt_version":"v9_agentic","proposal":{"assistant_reply":"Sure\u2014I can run an agent to research top places to eat in Atlanta. Quick question first: what kind of food vibe are you after (e.g., Southern comfort, modern American, sushi, budget-friendly, date night), and do you have a budget per person?","confidence":0.74,"response_mode":"action_plan","workflow_goal":"Gather missing preferences (food type/vibe and budget) so the agent can return a tailored list of best restaurants in Atlanta.","workflow_steps":[{"action_type":"start_agent_run","blocking":true,"depends_on":[],"followup":{"answer_format_hint":"e.g., \u201cSushi, ~$30\u201350/person\u201d or \u201cSouthern comfort, date night, ~$60+/person\u201d","needed":["food vibe/type (e.g., sushi, Southern comfort, date night, budget-friendly)","budget per person"],"question":"What kind of food vibe are you after, and what budget per person?"},"params":{"brief":null,"budget_seconds":null,"goal":"Research and compile a tailored list of the best places to eat in Atlanta based on the user\u2019s preferences.","max_outer_steps":null,"rationale":"We need the user\u2019s food vibe and budget to run a meaningful restaurant search; without these, the agent would produce a generic list."},"rationale":"Agent run depends on missing user preferences; request them first.","step_id":"step_1","success_criteria":"User provides food vibe and budget per person so the agent can start research with proper constraints.","tier":"T2"}]},"reasoning_trace":{"steps":[{"decision":"finalize","finalize_reason":"Ask clarifying questions and propose a shortlist format; note that I can tailor recommendations once preferences are known.","iteration":1,"missing_facts":["User\u2019s preferences for the food search (cuisine types, budget, dietary restrictions, neighborhood/location, dining vibe, and whether they want lunch/dinner)."],"reasoning":"The user asks to \u201crun an agent\u201d to search for best places to eat in Atlanta. In this bounded investigation layer, I don\u2019t have access to an execution tool for web/agent browsing, and no missing internal facts are required to respond with a helpful next turn. I should ask for key preferences (neighborhood, cuisine, budget, dietary needs, vibe) and offer to proceed with a curated shortlist once those are provided.","tool_name":""}],"terminated_reason":"finalized","tool_calls":[]},"selection":{"confidence":0.74,"intent_summary":"User wants an autonomous agent to search for the best places to eat in Atlanta.","needs_action":true,"reasoning_brief":"The user asks to \u201crun an agent\u201d to search for best places to eat in Atlanta. In this bounded investigation layer, I don\u2019t have access to an execution tool for web/agent browsing, and no missing internal facts are required to respond with a helpful next turn. I should ask for key preferences (neighborhood, cuisine, budget, dietary needs, vibe) and offer to proceed with a curated shortlist once those are provided.","response_mode":"action_plan","selected_action_types":["start_agent_run"]},"temperature":0.15,"thread_id":"thr_d02a47f4e4e8f518d5","trigger_event_id":"evt_6ce2e4dc0230","turn_id":"turn_evt_6ce2e4dc0230","user_text":"I'm doing well. Can you run an agent to search for best places to eat in Atlanta"}
TEXT NOT NULL
source_ref
NULL
TEXT
confidence
REAL (default 0.0
dedupe_key
cognition_proposal:prop_9d71f84a96f1966a0416b706
TEXT
episode_id
ep_ca1803357286
TEXT
created_at
2026-04-16T18:07:43.026167+00:00
TEXT NOT NULL (default strftime('%Y-%m-%dT%H:%M:%fZ','now')
Update
Cancel