FlowState Hosted

Record one decision (a choice and why), change, problem, learning or todo. Call it right after each decision, change, fix or lesson, and before you end or hand back. To update todos or problems: manage_todos / manage_problems. Only adds. Review mode or suggested=true may queue it. A shared-component change alerts linked projects. A close decision gets a possible-conflict note; act on it. conflicts_with opens a disagreement card. Secrets are refused. Returns {logged, record, note} or {queued_for_review}.

Notes from one AI to the next. leave: before you end, if you stop mid-task, save where_i_was and next_step; the next start_here shows it after the hard rules. pickup: once you continue from a note, mark it so it stops showing. list: open notes. Not a session summary and not a todo. Adds or marks notes; never deletes. Returns the note or {notes}.

The edit trail of records. list: edits with old and new values. undo: take back a record's last edit, a record you created (if nothing refers to it), or a delete with everything removed with it (a deleted project: its old name and id); rows changed since are skipped and listed. who: who did what (app, model, machine), filtered and paged. metrics: usage counts only (brief sizes, how often search and ask returned records). Logged changes (kind=change): find them with search. Reads: list, who, metrics. list and undo require project. Returns {history}, the undo result, or {rows, page}.

Connect things across projects. add: a project uses a shared component (link_type=uses, target_project, target_component), depends on a project, two components are the same, records relate, or a record gets a URL (e.g. an issue). Then a change or decision logged on the shared component (log_work component=<name>) gives each linked project an update todo and a 'changed since' line; FlowState never edits other projects. remove: by link_id or the add fields; kept as removed (manage_history undo, record_type=link). flag_conflict: two records disagree (topic, evidence); the user keeps one. list: read-only. Requires project. Returns the link, the card, or {links}.

Memory upkeep. cleanup: queue likely duplicate, stale and misfiled records. import: a memory export or edited FlowState markdown into review. stale: facts unchecked for 60+ days, and records flagged possibly stale. files_changed: paths you changed; flags records whose file evidence names them. mark_checked: you re-checked one (clears the flag). set_source: correct an origin (user_stated waits for the user). set_aside: no longer applies but kept (needs reason; out of brief and search; restore_set_aside or undo). delete: only when the user asks; undo restores it; with approvals on it waits for the user's approve (manage_review). Requires project. Returns counts and ids.

Documented reusable procedures of a project (deploy, test, a code convention), with ordered steps. create, list (read), update (steps replaces the whole list; undo with manage_history), delete (undo restores it; with approvals on it waits for the user; refused for HTTP app keys and remote apps). A one-off choice is log_work kind=decision; a lesson is kind=learning. Requires project. Returns method rows.

Work on a project's existing problems (bugs, blockers). list: open problems. tree: one problem with every attempt and its solution. add_attempt: record a try. end_attempt: how a try ended. solve: close it with what fixed it (manage_history undo reopens it). Call add_attempt or solve right after a fix, and again before you end or hand back. Open a new problem with log_work kind=problem. Reads: list, tree. Writes need project. Returns problem rows, the tree, or the saved attempt or solution.

Projects and their components (named parts of a project). list: projects (by status). create: only when the user asks; names are unique. update: rename, describe, or set status (archived retires it). list_components / add_component / update_component: the same for components (deprecated retires one). delete / delete_component: only when the user asks. Deletes it with its child records after a safety copy; the answer gives the undo call. If the user turned approvals on it waits for their own approve instead (manage_review lists it; tell them the answer's next line). Reads: list, list_components. Returns project or component rows, or what was deleted.

The user's review queue and mode: summaries, suggestions, imports, clean-ups, deletes, conflicts. list (a line each; item_id: one in full), get_mode: read-only. walk: when the user asks what's waiting (boxes or links). approve: make it a record (edit / move_to first), delete (confirm_name), confirm a conflict (keep=a|b|both). set_mode: which new records wait. approve, reject, set_mode: ONLY call this when the user has explicitly told you, in this chat; quote them in user_request; never approve your own suggestions or change the mode to get your own writes saved. Hosted: approve/reject are refused for every AI; share the review page link. Returns {items, total}, the mode, or the result.

A project's hard rules: short never/always rules from the user, shown first in every brief and never cut. add: when the user states one (one sentence, max 300 chars; 25 rules, 2,000 chars in total); it waits in the review queue until the user approves it themselves (on their review page; no app can). list: active rules. remove: ONLY when the user asks in this chat; quote them in user_request; it waits like add; the rule is kept as removed. Preferences and lessons go in log_work. Requires project. Returns the rule or {rules}.

Inspect FlowState's sessions. They open and close by themselves (closed after 2 hours idle or when the app quits, with a summary queued for review), so this is rarely needed. current, list, conversations: read. start: returns the automatic session. end: close one with a summary (not undoable). Decisions go in log_work. Returns session or conversation rows.

The connected app's own learned skills, checkpoints and metrics: how the AI works, not project facts (those go in log_work). learn: save a skill. list: a project's and global skills. confirm: one more session where it held (promoted after 3 at a 0.8 rate). save_state / get_state: a checkpoint. log_metric / list_metrics: scores. Reads: list, get_state, list_metrics; the rest only add rows or counts. Returns rows.

Todos. list; next: top unblocked (others' claims last). update: status, priority or title, when done and before you end. block / unblock: waits on todos or a problem. add: subtask, blocker or due date only (else log_work). claim before you start (fails if someone has it); renew; release or handoff (with a note). Returns rows.

Non-secret project settings: hosts, ports, endpoints, config. create, list (read), update (undo with manage_history), delete (undo restores it; with approvals on it waits for the user; refused for HTTP app keys and remote apps). Secrets are refused; is_secret only labels a value and does not hide it, so never store passwords, tokens or keys. Requires project. Returns variable rows.

Find stored todos, decisions, changes, learnings, problems and solutions. query: ranked matches. query + answer=true: a short quoted answer with record ids, or says FlowState has nothing. query="D12": decision 12 in full. No query: the newest records. Read-only. Overview: start_here. Returns {results, count} or {answer, sources}.

CALL THIS FIRST in every conversation about a project. Returns the brief as text: hard rules, a handoff note if any, review mode, possible conflicts, open todos (and claims) and problems, recent changes, decisions and learnings. No project: lists projects. Side effects: opens or reuses the automatic session, notes when you looked.