AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
fix(chat): count a channel whose adapter verified the sender as a verified surface (#513)
Rufus0dd25b16b8da
diff --git a/packages/core/openexecutive/architecture/architecture-facts.yaml b/packages/core/openexecutive/architecture/architecture-facts.yamlindex 3dfaa874..22e18d2b 100644--- a/packages/core/openexecutive/architecture/architecture-facts.yaml+++ b/packages/core/openexecutive/architecture/architecture-facts.yaml@@ -2754,9 +2754,13 @@ memory:email turn or an eval override, on the web chat signed in (or locallogin), their own Slack or Discord, a private Telegram chat with avalid webhook secret, or a channel whose adapter set- Session.speaker_verified. Session.speaker_verified and- Session.private_chat are read only by Always in the loop, never as a- grant for anything else. Never another person's words, never the reply,+ Session.speaker_verified. An adapter's Session.speaker_verified (with+ the caller_person_id it resolved from the sender identity it verified+ itself) makes its channel a verified surface everywhere+ (people_tools._is_verified_speaker_surface), as Slack and Discord are;+ Session.private_chat makes the conversation private+ (delegation.settings.private_conversation), so Act as me and+ recall_history may be offered there. Never another person's words, never the reply,never a turn that touched the speaker's mailbox.- Paced: messages under MIN_CHARS (40) are skipped and each person gets atmost MAX_PASSES_PER_DAY (40) passes a day, counted in the company DBdiff --git a/packages/core/openexecutive/architecture/prebuilt/agents.json b/packages/core/openexecutive/architecture/prebuilt/agents.jsonindex c080d617..2083b05a 100644--- a/packages/core/openexecutive/architecture/prebuilt/agents.json+++ b/packages/core/openexecutive/architecture/prebuilt/agents.json@@ -1,7 +1,7 @@{"section_id": "agents","title": "Agent Council",- "markdown": "The Executive (`openexecutive.orchestrator.executive.Executive`) is a single coherent persona that fans out to specialist sub-agents via Anthropic tool use. Each specialist subclasses `openexecutive.agents.base.BaseAgent`, carrying a `name`, `domain`, and `model`, and exposes `analyze(...)`, which wraps the question in user-turn context and calls Claude through the per-call provider. That context is per call and never cached: `<company_stage>` (the stage from the company profile — specialists never see the profile itself), in solo mode `<principal_role>` (what kind of principal the advice is for, in plain words, with their title and remit — `router.principal_role_context`), `<department_memory>`, `<past_decisions>`, `<failure_cases>` (the shipped case studies, and under them the workspace's own lessons that match the call, `memory/lessons.py`), `<relevant_knowledge>` and `<conversation_context>`, outermost first. The specialist's own system prompt is a static domain constant under one `cache_control` block, so it stays byte-identical across companies and profile edits. A chat turn takes the stage from its session's profile (the one the Executive reasons over, and the one an eval scenario injects); workflow steps and the MCP server's `consult_specialist` read it fresh from the profile on disk. The role tag follows the turn's mode: a chat turn pins the role on its session with the mode (`pin_turn_principal_role`: the session's `principal_role` override, else the workspace settings) and sends it in solo and nothing in team, so the org block, every specialist in the turn and any workflow the turn starts see the same role; callers with no chat turn read it fresh (`load_principal_role`: the current session's mode and role, else the workspace's), and a failed read sends no tag rather than failing the consult. The CFO, CSO and sales prompts key their advice on it: for a bootstrapped, self-funded or solo company they drop venture fundraising benchmarks and work from cash, and raise only if the founder wants to.\n\nRouting uses one `consult_specialist` tool. When to call it is spelled out in the persona's Domain Expertise section (\"Going deeper\") and in the tool's own description: any question that asks for judgment in a specialist's area (a decision, plan, analysis, negotiation, hire, contract term, pricing or fundraising move, board message, or a department's own targets and stance, since the specialist holds that department's memory) is consulted before the answer, several at once across areas; lookups in mail, calendar or documents, scheduling, status checks, routine drafting and questions about how the Executive works are answered without one. Chat eval scenarios hold this: `required_routing` names specialists the turn must consult and `no_routing: true` says it must consult none, and the runner fails a scenario that misses either (`evals.scenarios.routing_check`). Beside it the Executive carries two skill tools, `search_skills` and `load_skill` (skills are shown to users as **playbooks**, and every playbook belongs to a workflow: one that follows it, or its own Quick workflow). Chat finds and reads playbooks but never creates or changes one: work worth repeating is offered as a workflow through `draft_workflow`, with the method written into its steps, because workflows read playbooks at run time (approved scheduled ones included) and this loop also runs on inbound email and chat, so only a person can change what a workflow follows. A hidden built-in is invisible to search and load; each `search_skills` hit lists the `workflows` that follow it, Quick ones included, and the persona routes \"the finished deliverable\" to that workflow and quick or partial asks to the playbook inline; Tool calls made while proactive work is tagged (scheduler dispatch, reflection, research, alert review) feed the Attunement outcome ledger. Goals have three tools: `list_department_goals`, `update_department_goal` (progress the user reports) and `create_goal` (a new goal the principal states, filed under an area by slug or title and creating the area when none matches — see Org). `create_goal` runs only for the principal on a verified surface, and no unattended run is offered it: the tools in `schedule_tools.UNATTENDED_WITHHELD_TOOLS` are dropped from reflection's and research's toolkits by `unattended_toolkit`, and from the chat loop when its Session is marked `unattended` — the scheduler's PROACTIVE TRIGGER run, whose prompt quotes stored intent text; a call the model emits anyway gets an error tool_result. `record_decision_outcome` records how a past decision turned out — the weekly review lists decisions older than 30 days with no outcome as `[decision N]` — writing `decisions.outcome` (`episodic.update_decision`) and auditing the rationale; it has `create_goal`'s gate (the principal on a verified surface only; everyone else gets an audited refusal) and is in `UNATTENDED_WITHHELD_TOOLS` too. A missing or unknown id returns the decisions still waiting on an outcome, so the model can retry with the right one. Its schema is static; the solo persona has one line on it, and team mode learns it from the tool description, so the team persona is byte-identical. Attunement adds `list_open_loops` (what a person owes — everyone's for the principal only in a private conversation, otherwise the caller's own) and `close_open_loop`, which only closes a loop when the turn's resolved speaker is the principal or the loop's owner — an unrostered sender, a signed-in web user not on the roster, and unattended sessions are refused. `assign_open_loop` opens one on request (\"ask Ben to send me the Q3 numbers by Friday\") for the principal or a rostered teammate on a verified surface — never an email, a turn private to the principal or an unattended run, which are also withheld the tool — and only when `task` appears verbatim in what the speaker typed this turn, at most 5 per turn; that turn's extraction pass then opens no second loop for the same owner. The owner is told once on their own channel when someone else assigns it, and the result's `notified` says how that went, so the Executive reports it rather than messaging them as well. The roster write tools (`upsert_person`, `archive_person`, `set_department_head`) are the principal's alone, and only on a surface that verified the speaker — the web chat, the principal's own Slack or Discord, or a private Telegram chat when `TELEGRAM_WEBHOOK_SECRET` is set to a value Telegram can send (Telegram identifies the chat rather than the sender, and without that secret its webhook accepts anyone's update). A teammate, an email (even from the principal's address), Google Chat, the CLI, the MCP server and unattended runs get `status: refused` (audited, and no action chip), because a team member's People row is also the web sign-in and outbound-email allow-list. `upsert_person` takes `kind` (`team` / `contact`; a new person defaults to `contact` in solo mode, an update keeps the current kind) and `email_aliases` (other addresses the person writes from — the full list, replacing the current one; they match mail and may be emailed but never sign in, and one already on someone else is refused), and after every write any pending roster request whose sender now matches someone is closed and its held messages replayed. `resolve_roster_request` answers a **roster request** — someone not on the People list who wrote in and is waiting (see Org): `approve` (a new person; `kind` defaults to team for a company-domain sender, else contact, when the principal did not say), `link` (someone already listed, by `person_id`; `replace_channel_id` only when the principal said so) or `decline`. It has the roster tools' gate (the principal on a verified surface; audited refusal otherwise), is in `UNATTENDED_WITHHELD_TOOLS`, and answers only an id in `Session.trusted_roster_request_ids` — the ids the server printed that turn in a `<roster_requests>` block (`briefing.context.format_roster_requests_for_prompt`, up to 10 pending requests), which `render_and_trust` appends to the `<briefing>` digest on the principal's own verified turn only and records on the session in the same step, so an id the model invents or reads out of a message adds nobody. Each line is server-derived — id, channel, address or account id, the sender's name sanitised and marked unverified, a company-domain hint, the message count — and never what they wrote. The block rides in the **user turn**, like the digest, so the cached system blocks are unchanged; the tool definition is static, and the new tool only extends the sorted tool list. The web chat route resets the trusted set every turn, and a resolved id is removed from it. and `list_people` returns both kinds with `kind` — contacts only on the principal's own verified turn (they are private to the principal; anyone else gets the team as if no contact existed) — while `lookup_person` searches the team only. `ask_about_person` reads a person's peer memory fully only on their own verified turn; anyone else's answers only to a verified principal or teammate, and only when that person turned on \"Share my work style with the team\", framed to how they work and never their view of a colleague, and otherwise returns the same \"hasn't chosen to share\" result whether or not anything is known. A teammate's own mail with the Executive is theirs the same way: every mailbox call the model makes through the MCP gateway (Gmail or Outlook, by `call_tool`, from a script, or a workflow step run from chat) passes through `orchestrator.teammate_mail`. A search excludes every other teammate's address server-side, except on mail the reader is also on, and is filtered again entry by entry; any other call that names a message or thread (read, attachment, reply, forward, label) must use an id a filtered search returned to the same reader in this conversation (`Session.mail_ids_seen`) or the inbound email the turn answers; reads are filtered message by message, so a message naming another teammate is left out unless the reader is in its From / To / Cc; a reply that would quote such a thread, or an Outlook forward, reply or attachment read of such a message, is refused; and a conversation in which a teammate other than the principal was shown their own mail becomes theirs alone, as Act as me's do. Outside mail and the reader's own are untouched; an email turn reads as its sender only when Gmail authenticated it, and any other unverified reader sees no teammate's mail, a background run the model drives reads as the principal and a workflow step outside any session as nobody, an Outlook inbox rule that forwards or names another teammate is refused, and the poller and the brief, which read the mailbox themselves, are unaffected. Their own chats are theirs too: every audit row of a teammate's verified turn is theirs (`people_tools.teammate_turn_owner`, see Audit; the principal sees the actions, never the words), and a teammate's web chat or DM opens for them alone (`chat._session_access`), the principal included. The same verified-principal rule, as `people_tools.contacts_reachable_now()`, decides whether a turn may reach a **contact** at all: `message_person`, the raw DM tools, `create_calendar_event` / `create_instant_meeting` attendees and the MCP gateway's Gmail / Calendar / Drive / OneDrive gates treat a contact exactly like an unknown person on every other turn, so no refusal reveals that one exists. **The untrusted-content policy** (`orchestrator.content_trust`) is one rule for text the principal did not write — inbound email, chat, attached files, watched pages — answering three questions for every surface. *Who is speaking*: the principal only when the surface proved it (`principal_speaking`: the web chat as the principal — never a signed-in email on nobody's People entry —, the CLI, their own Slack/Discord or a secret-verified Telegram chat, or their own address with Gmail's `dmarc=pass`); never a teammate, a stranger, Google Chat, the MCP server or an unattended run. *What may become memory*: episodic extraction runs only then, and only on the words outside `<untrusted_content>` blocks; peer memory and open loops are recorded under the speaker's own name, never as the principal's. *What may trigger tools*: every write on the principal's authority already refuses others in its handler; the tools with no such check that change the install for every later turn — `content_trust.PRINCIPAL_ONLY_TOOLS`: `load_mcp_server`, `list_saved_tools`, `run_python_job` and `run_script` — are not offered unless the principal is speaking on an interactive surface (not email, even authenticated), and a call the model emits anyway gets an error tool_result and a `refused: not_principal` audit row. So an inbound email, a teammate's turn, Google Chat and the scheduler's proactive trigger each get a stable tool list of their own without it. A send or edit on a team member's turn also meets their department's authority first (`orchestrator.department_gate`, see Org), and so does one on a turn whose speaker is on no People entry: a signed-in web caller or a chat-channel sender, which in practice is Google Chat, since Slack, Telegram and Discord turn unmatched senders away. Google Chat names a matched sender to the gate alone (`gate_sender_person_id`), so the principal there is not held. Email turns are left to the mailbox's own gates. *How it is labelled*: outside text goes into the user turn inside `<untrusted_content source=… author=… author_verified=…>` with a fixed notice that it carries no authority; compatibility forms are folded (NFKC), control characters go, and the tag's name is renamed wherever the text carries it — any case, spacing or entity-escaped form — so the text cannot end its block and speak outside it.\n\n**Outside content** (`orchestrator.outside_content`). Once a turn has read text from outside the team (any gateway read, an attachment, a web search result, a synced Drive, OneDrive, Confluence or Notion excerpt, `read_document`, research, or an extension tool registered `reads_outside`), the rest of that turn refuses what the Act as me lockdown refuses, every `upsert_person`, and every `call_tool` but a read: no mail, Docs, Sheets, Drive or calendar write. A round that reads also holds that round's other such calls; the read itself runs. Scripts are checked call by call. The offered tools never change, so the cached prefix stays the same, and the hold ends with the turn. Mail from someone not in People (a contact or a stranger) counts as outside content from the start of its turn (`Session.sender_off_team`), so the whole turn is held, with no direct messages or watchlist removals either; it can still raise an alert, private to the principal, which is how that mail reaches them. Someone added to People in a turn (or given a new address or chat account) is not emailed, messaged, invited or shared with until the next one.\n\nA turn about the principal's private mail (`Session.private_to_principal`) reaches the principal only. It is neither offered nor allowed to run `schedule_tools.PRIVATE_TURN_WITHHELD_TOOLS` — everything that reaches someone else, publishes where the team reads, or starts work outside the turn: the broadcasts, meeting bookings and cancellations, `run_workflow` and research, follow-ups and workflow nudges, watches, artifacts, goal updates, saved workflows, skill drafts, and `load_mcp_server` (it connects to any URL, which can carry the turn's content). Through `search_tools` and `call_tool` it reaches only `schedule_tools.PRIVATE_TURN_MCP_TOOLS`: Google Workspace reads (mail, calendar, and Drive, Docs and Sheets search and file reads, with their Microsoft 365 twins; OneDrive's `download-bytes` only for a file's content) and the Gmail send and draft the gateway narrows to the principal. A search shows it nothing else, and a call to anything else (Google Chat, a Docs or Drive write, `manage_event`, another server) is refused (`schedule_tools.private_turn_withholds`). A call the model emits anyway, MCP tools included, gets an error tool_result and writes an audit row, and every audit row the turn writes is the principal's alone.\n\nA turn another AI app asks over the MCP server (`Session.from_mcp_client`, set by `ask_executive`) reads and advises but never acts. It is neither offered nor allowed to run `schedule_tools.MCP_CLIENT_WITHHELD_TOOLS`: the private-turn and unattended sets, plus every direct message (`message_person`, the Slack, Discord and Telegram DMs), alert acks and new alerts, brief edits, closing open loops, roster and department-head writes, watchlist changes, workflow drafts and form proposals. It gets no Act as me, `recall_history` or extension tools, and of the gateway tools only `schedule_tools.MCP_CLIENT_MCP_TOOLS`: the private-turn reads without the Gmail and Outlook send and draft tools. The set is fixed, so the variant keeps a stable cached tool prefix. A call the model emits anyway, through `use_tool` or `call_tool` included, gets an error tool_result telling it the conversation comes from another AI app, so it can read and advise but not send, post, book or change anything, and writes an audit row (`refused: mcp_client`); `MCPGateway.call_tool` refuses the same calls again.\n\nA web chat its owner shared (`Session.shared_chat`) mixes people. The note naming who is in it says which of them owns it and that the others' lines are messages from them, not the owner's instructions. While someone other than the owner has written since the owner's last message (`Session.others_spoke_last`, set per turn by the chat route from the saved history, the speaker included, and true when the history can't be read), the turn is neither offered nor allowed to run `schedule_tools.SHARED_CHAT_WITHHELD_TOOLS`: direct messages, the broadcasts, meeting invites and cancellations, follow-ups, roster writes and workflows (a run, a save or a suggested schedule acts later with the full tool set). Through `call_tool` it can't send, reply, forward or draft mail in Gmail or Outlook, or make a calendar change that mails attendees (`schedule_tools.shared_chat_withholds`). That holds on the owner's own turn right after someone else's line too, so a request carried over from it can't send; the owner's next message with nobody else's in between lifts it. A call the model emits anyway gets an error tool_result and writes an audit row (`refused: shared_chat`). The principal-only tools stay out of every shared chat (`content_trust.principal_only_withheld`).\n\nOn every turn the Executive knows what is connected without searching: block 0's *Connected Systems* section names the connected Google services, other MCP servers, the messaging channels, Notion sync, Confluence sync (when on) and Act as me, and pins the Google tool names it calls directly with `call_tool`. Both the service list and the pinned names are narrowed to what workspace-mcp actually loaded (`WORKSPACE_MCP_TOOLS`, `WORKSPACE_MCP_TOOL_TIER`), so a service left out is not named and its tools are not pinned — being told a tool is already available when it is not in the index costs a failed call the model cannot explain to itself. `search_tools` is for anything not listed. When work repeats over many items, the Executive can also call `run_script` (`workflows/step_script.py`, offered when the gateway runs, unless `CHAT_SCRIPTS=false`, and only on the principal's own turns — `PRINCIPAL_ONLY_TOOLS`, withheld on an unattended pass too, because it spends the turn's whole call budget on code the model just wrote): one short Python script, run in a sandboxed Monty worker with no files, network or environment, whose only reach is the gateway tools `call_tool` could reach (those `search_tools` has returned; the gateway keeps that set for its own process-wide session, not per conversation). Each call it makes is a `call_tool` in every way that matters — the gateway's discovery, deny-list and recipient gates, Take the lead's gate on an unattended run (or the department gate on a team member's turn, see Org), and the same action chip and `tool_invocation` row (marked `via: run_script`, `ok: false` when it raised), as each call happens; the script itself gets a `kind: script` row with its source and result. Its wall clock is half the turn's deadline, so a long script ends with the list of calls it made rather than being cut off with the turn, and a stopped turn closes it and its worker. A turn private to the principal is not offered it, and the Act as me lockdown withholds it whole. Besides gateway tools, a chat script may call a fixed list of the Executive's own tools (`step_script.CHAT_OWN_TOOLS`: reads, alerts, open loops, goals, the watch list, follow-ups, `message_person`, `upsert_person` — nothing that broadcasts, books calendars, edits memory or skills, or starts workflows or research), each only when the turn is offered it and through the turn's own handler (Take the lead's gate included), with the same chip and a `kind: skill`, `via: run_script` audit row. A direct call needs a `tool_use` each, so a turn's scripts share a budget instead: `CHAT_SCRIPT_MAX_CALLS` (default 200) calls in all, and per-turn caps on own tools that could otherwise act in bulk (`CHAT_OWN_TOOL_CAPS`: `message_person` 10 — messaging the whole roster would be a broadcast — `upsert_person` 25, `create_alert` 50); a refused call tells the model to say what is left. A call stopped mid-flight by the script's clock or the turn still gets a `cancelled` audit row, since it may have run. Because every round re-reads the conversation, the loop also nudges at the moment of choice: after a round whose results include a list of five or more items (`step_script.lists_many`), with `run_script` on offer and not used that round, it adds the constant `FANOUT_HINT` as a text block in that round's user message (never a cached block), once a turn, pointing the per-item work at one built tool. For library work on files (PDFs, spreadsheets, charts, images) the chat also has `run_python_job` (see Workflows → Python jobs): Python with a fixed library set in a Deno-isolated WebAssembly sandbox, fed Knowledge files by name, the message's own attachments as sent, or text it already holds, and able to keep a job that worked as a Custom tool, with result files linked for the principal to download; it is offered only on the principal's own turns and only where the sandbox is installed (not offered otherwise, so the tool prefix stays fixed per process). Agent Activity shows each run as one \"Built tool\" card (debug event `script_run`: ok, the calls it made, how many, how long, and the kept or reused tool's name). The persona's tool-building section is present only when chat scripts can actually run (the setting and Monty installed). `TOOL_BUILDING_ADDENDUM` in the cached persona tells the Executive when to build a tool — a job that looks something up and then checks or acts on each result, paged results, more than about ten items, or an answer that needs three or more reads (find, open, read; the tool returns only what answers the question, not whole documents, and only what is about to be edited or quoted at length is read in full), while a handful of items already named go as direct calls in one turn — and never to say it has none, and to talk about it as building a tool or doing it in one go. On the principal's own verified, interactive turns, a script that works can be saved as a named tool (`save_as`; elsewhere the script runs but is not saved) and run again with `run_script(tool=…, inputs=…)`; `list_saved_tools` (a constant definition, in `PRINCIPAL_ONLY_TOOLS` with `load_mcp_server`, so offered only while the principal is speaking on a verified, interactive surface; `run_script(tool=…)` is refused on any other turn) lists them, and each call a saved tool makes is a gateway call like any other (see Workflows → Saved tools). The tool's definition is a constant, so the cached tool prefix does not move. Multiple parallel `tool_use` blocks in a single assistant turn fan out concurrently through `router.route_parallel`, each running its own domain-filtered ChromaDB query (3 built-in and 2 company chunks by default, see the RAG section) before the specialist sees the question. The fan-out is failure-isolated per call: a specialist that raises or returns no text becomes an `UNAVAILABLE` tool_result (`router.specialist_unavailable_result`) instead of failing the whole turn, and its area — \"finance\", \"legal\", never the specialist's name — is reported to the user under the web reply, or by the Executive in its reply on other channels, unless another call to it answered that turn. A failed specialist does not count as consulted, so it takes no committee seat. Cancellation (Stop) still propagates. The Executive then synthesizes the returned analyses into one reply.\n\n`remember_fact`, `forget_fact` and `update_company_profile` (`orchestrator/fact_tools.py`) make a correction stick: the first two keep or retire a standing fact in `memory.facts`, and the third changes one field of the company profile. They share `record_decision_outcome`'s gate (the principal on a verified surface, an audited refusal for everyone else) and are in `UNATTENDED_WITHHELD_TOOLS`. `remember_fact` alone also admits a rostered teammate on a verified surface (web signed in, their own Slack or Discord): the fact is stored attributed (`recorded_by_role=\"teammate\"`, rendered `(per <name>)`), and is held as a `proposed` row (`awaiting_approval`) until the principal approves it, unless the principal marked that teammate trusted (\"needs my approval\" off; on by default) — and even then when it would replace the principal's fact. All three are also in `PRIVATE_TURN_WITHHELD_TOOLS`, since what they write or retire is read on everyone's turns. On the principal's own authenticated email (primary address, with Gmail's own `Authentication-Results` reporting `dmarc=pass`, not forwarded) the three tools check the request as usual, then hold it as `awaiting_confirmation`. It applies only when the principal replies to a one-time token emailed to their own address (`integrations.fact_confirmation`); the split into a check step and an `apply_*` step lets chat and the confirmed reply share one apply path. Each write also needs a `source_quote` found in the speaker's own words this turn. The active facts reach every specialist as a `<standing_facts>` user-turn tag: `route_to_specialist` reads them (None → the store, \"\" → none) for chat consults and workflow steps alike, and `BaseAgent.analyze` places the tag next to `<past_decisions>`, never in the cached specialist system prompt.\n\nThe ten entries in `SPECIALIST_REGISTRY` (`openexecutive.orchestrator.router`):\n\n| Key | Agent | Domain |\n| --- | --- | --- |\n| `cso` | `StrategyAgent` | strategy |\n| `cfo` | `FinanceAgent` | finance |\n| `chro` | `HRAgent` | hr |\n| `gc` | `LegalAgent` | legal |\n| `coo` | `OperationsAgent` | operations |\n| `cmo` | `MarketingAgent` | marketing |\n| `cpo` | `ProductAgent` | product |\n| `sales` | `SalesAgent` | sales |\n| `board_comms` | `BoardCommsAgent` | board |\n| `triage` | `TriageAgent` | triage |\n\nModels: specialists default to `claude-sonnet-5-5`; the deep-reasoning tier (CSO, CFO, GC, Board) runs on `DEEP_REASONING_MODEL`, `claude-sonnet-5-5` by default, with adaptive thinking; routing/fast classification uses `claude-haiku-5-5`. Requests are fitted to the model's generation on the way out (`feature_gate.fit_claude_generation`): 5-generation Claude models never receive `temperature` / `top_p` / `top_k`, and Haiku 5.5, which thinks unless told otherwise, gets thinking turned off when the caller asked for none. The Council's **Deep reasoning** toggle is honoured on Claude Opus/Sonnet (direct or via OpenRouter) and on any OpenRouter model whose live catalog entry supports `reasoning` (today all OpenAI, Gemini, DeepSeek and Grok entries; not Llama) — the request translator turns Anthropic adaptive thinking + effort into OpenRouter's `reasoning` parameter. It is a silent no-op on models that can't reason, and disabled for Haiku, which rejects adaptive thinking. A PDF `document` block is translated too: it becomes an OpenAI `file` part, and OpenRouter requests carrying one add the `file-parser` plugin (`native` for models whose catalog entry lists `file` input, else `PDF_OPENROUTER_ENGINE`, default `mistral-ocr`). `FeatureSpec.supports_pdf_input` gates it per model — off for a local server unless `LOCAL_PDF_INPUT` — and a gated-off PDF becomes a text note rather than vanishing. The Council picks a model in two steps: a **Provider** dropdown (Anthropic, OpenAI, Google, Meta, DeepSeek, xAI, Local, …), then a **Model** dropdown limited to that provider, with readable names (\"Claude Opus 5.5\") and the raw id and serving route shown underneath. The Anthropic group combines the direct Claude models (`claude-fable-5-1`, `claude-opus-5-5`, `claude-opus-5`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-haiku-5-5`, `claude-haiku-4-5`) with any Claude generation that exists only on OpenRouter, and never lists a model twice. With `OPENROUTER_ENABLED`, the non-Anthropic entries come from OpenRouter's live `/models` catalog (fetched at startup, refreshed in the background, filtered to tool-capable paid text models from an allowlisted vendor set), falling back to a built-in snapshot if the fetch fails. Every Council agent also takes **additional instructions** (`agent_overrides.instructions`): text appended after its prompt by `agents.overrides.append_instructions` inside an `<additional_instructions>` block. `BaseAgent.base_system_prompt()` is the built-in prompt or its full replacement (what the Council's editor shows); `effective_system_prompt()` is that plus the instructions (what every call sends), and the Executive gets the same text through `build_system_blocks(persona_instructions=…)`. Unlike a replaced prompt, instructions leave the agent on its built-in prompt, so prompt improvements keep reaching it. A **Quality** choice above the agents (`agents.presets`) sets every agent's model and deep reasoning at once: **Fast** puts every agent on a small model (`claude-haiku-5-5`, else `claude-haiku-4-5`) with deep reasoning off, **Balanced** returns each agent to its built-in defaults, and **Thorough** puts the Executive and the domain specialists on the largest allowed model (`claude-opus-5-5`, else `claude-opus-5`) with deep reasoning on where the model supports it, leaving triage and the helpers below on their defaults. Presets change quality only; they never cap spend. Each preset resolves against the install's model allowlist at request time and is offered only when one of its models is allowed. Applying one writes ordinary per-agent overrides (model and deep reasoning only), so history, rollback and later per-agent edits keep working; an agent changed on its own afterwards shows as **Custom**. Each Council agent has a **visibility**: `core` for the Executive and the domain specialists (`BaseAgent.visibility = \"core\"`, which a new specialist must declare) and `internal` (the default) for triage and the helper agents below. Thorough moves only core agents. The Council opens in a **simple view**: the Quality choice, the voice picker, and only the core agents, each with its additional instructions and a model badge. **Show all agents** lists the internal ones too, and **Advanced** opens the full page (the browser remembers the choice). Eight Council-only agents are model/prompt-overridable in the UI but NOT callable via `consult_specialist`, because they are deliberately kept out of `SPECIALIST_REGISTRY`: `quality_judge` (committee review), `utility_fast` (gates, titles, decision parsing), `research` (the `executive_research` fan-out), `fixture_generator` (invents demo companies), `engagement_intake` (models a real client from intake material), `onboarding_interviewer` (interviews a new user about their own company and drafts its profile, people and departments), `workflow_designer` (runs the conversational New workflow wizard on `/jobs/new`: searches the available tools, asks clarifying questions, then drafts a validated dynamic-workflow definition for the user to review), and `workflow_actor` (runs a workflow's `action` steps: a bounded tool-use loop limited to the tools the user approved for that step). `fixture_generator`, `engagement_intake` and `onboarding_interviewer` share one shape — a forced tool call producing a whole company, validated for referential integrity, with a single repair retry — but opposite epistemics: the fixture author invents, the other two extract and leave unstated facts empty rather than guessing. When the workspace is in solo mode, `onboarding_interviewer`'s first user turn is prefixed with a short hint (`interview.solo_hint(role_kind)`, one static constant per role kind from the onboarding role step): the draft names only the principal, as principal, and no departments; an owner is asked about the offer, customers, pricing, cash and runway, an in-house executive about their organisation (drafted as the company — their employer), function, remit, manager, team size as context and what they are measured on, an independent about their practice, clients and pricing, and with no role given the role-neutral `SOLO_HINT` asks which they are. The hint rides in the user turn and the tool array is unchanged, so the cached system prompt and tool prefix are the same in both modes.\n\n**Voice.** The Executive answers in one voice persona, substituted into block 0 at `{VOICE_PERSONA}` (`personas/loader.get_active_body`) from the Executive override's `voice_persona_slug`. Three general voices ship in `personas/builtin/`: **Direct** (`default`, the slug used when none is set: answer first, brief and decisive), **Supportive** (a warm coach who explains the why and checks how the plan sits) and **Analytical** (numbers first, options and trade-offs, then one recommendation). They are offered by a shared picker in setup (`/onboard`, after the workspace choice) and in Settings → Executive, which saves through `PATCH /agents/executive`; a built-in voice's frontmatter carries the picker's one-line `description` and `sample` reply. The named-executive voices are marked `legacy: true`: the picker hides them, but they still load, so an install that picked one keeps it, and the Agent Council lists them under \"Legacy voices\". Voice files hold disposition only; the response-length ladder lives in `prompts/executive_persona.py`, and a test keeps numeric length rules out of every voice file. An eval scenario may set `voice_persona` to answer in a voice; it rides on `Session.voice_persona_slug`, which wins over the override for that session only.\n\nOne more structured-output utility agent sits beside `triage`: `openexecutive.agents.alert_review.AlertReviewAgent` (routing model, one forced `emit_alert_reviews` tool call, never raises). The alert review job hands it a batch of open alerts with evidence and gets back, per alert, a verdict (relevant / changed / resolved / stale), a confidence, the evidence it relied on, a one-line note, why-now, an optional deadline, and a recommended move (none / route / nudge / escalate / draft / suggest_workflow / merge / close) with its parameters. Like `triage`, it never mutates state — `alerts.review.apply_verdict` executes the verdicts deterministically within authority, so the model's job is judgment, not action.\n\n**Solo mode.** When the workspace (or the turn's session) is solo — one person using Open Executive for themselves — the Executive works for that one person, the principal, whatever their role: they may run their own business, lead a function inside a larger organisation, or work independently, and the persona reads which from the context instead of assuming it — the role lines under \"Your Principal\" in the org block, when the principal gave their role (workspace settings: kind, title, reports to, remit, measured on). Its persona swaps the team sections (\"You Are a Member of This Executive Team\", \"Choosing Who to Tell\", \"Departments & Org Coordination\") for \"You Work for One Person\", \"The People in Their World\", \"Who Hears From You\" and \"Goals and Areas\". Solo means only the principal uses Open Executive — not that they have no people: their manager, direct reports, peers, clients, investors and board are contacts. The Executive helps the principal work with them (a 1:1 or review prep, an update or budget case for their manager or board, a negotiation) but does not coordinate them, contacts them only when the principal asks and only if they are a contact, and never offers to loop the principal in. Every specialist stays relevant — HR for the principal's own reports, board and investor communications for reporting upward. Goals are grouped by *area* (the tools' `department_slug` is the area's slug). The chat loop withholds `send_department_message`, `send_company_broadcast` and `set_department_head` from its tool list, and a call to one of them anyway gets a JSON error tool_result instead of running. The mode is resolved once per turn and pinned on the session, so the persona, the org block, the tools and every tool handler agree — a switch made mid-turn applies from the next turn. Team mode is unchanged.\n\nEvery specialist *advises* — each returns domain analysis the Executive synthesizes into one voice. None of them act on the company's behalf; the side-effecting tools in the main loop (schedule, people, departments, broadcast, watchlist, workflows) belong to the Executive, not to a specialist.\n\n`recall_history` (Always in the loop, `orchestrator.history_tools`) reads the speaker's own notes, on the same terms as `ghostwrite_email` below: its own registry, offered only on a verified turn in a conversation private to them with their switch on; its `due` flag lists only dated notes, soonest first (see Memory). The ghostwriter below also gets the writer's notes from mail every recipient was on, as a consistency check (`<writer_noted>`).\n\nThe morning reflection, which has no question to look up and no specialist to consult, gets one more read-only tool of its own: `search_knowledge` (`orchestrator.knowledge_tools`), the same knowledge lookup a chat turn makes, for what the company's documents say about a customer, contract, price or policy before it acts.\n\nA fifth, `remind_me` (`orchestrator.reminder_tools`), sets a plain-text reminder sent to the speaker alone when it is due; it opens no mailbox, so it never locks a turn. A sixth, `propose_actions` (`orchestrator.action_card_tools`), does nothing itself: it leaves the speaker a card of up to five actions (a meeting, a message, a new contact) that happen only when they tap Approve, so it stays on after a turn read mail; it is where what an email itself asks for goes, since that is never done on the email's say-so. Four read-only tools beside it read the speaker's own mailbox on the same terms — `search_my_email`, `read_my_email`, `read_my_email_attachment`, `my_email_awaiting_reply` (`orchestrator.mail_read_tools`) — and `my_calendar` their own calendar while Read my calendar is on, capped per turn, other people's messages and attached files returned as untrusted blocks (see Act as me). Beside them, `save_my_email_attachment` copies one attached file, when the speaker asked in their own words, into a fixed folder of the Executive's own Drive or OneDrive and shares it with them alone, every call built in codeOne tool writes under someone else's name, and it is fenced in code rather than the prompt. `ghostwrite_email` (**Act as me**, `orchestrator.delegation_tools`) writes an email as the person the Executive is speaking with and saves it as a draft in their own mailbox, Gmail or Outlook (`delegation.gmail.gmail_for` picks the client by the person's credential); chat never sends it (the person sends it themselves, or taps Send on its card). It lives in its own registry, never `_ALL_SKILL_TOOLS`, so reflection, research and workflow toolkits can never carry it. The chat loop adds it only on a turn `delegation.settings.pin_turn_delegation` offered it to — the principal, or a team member once the owner lets them, with it on, verified, in a conversation private to them (the web chat, a Slack or Discord DM, a verified private Telegram chat), on an attended turn — and builds that turn's handler map from both registries, so on any other turn a call to it is an unknown tool. From the round that calls it until the turn ends, the dispatch guard refuses only what opens an outside address, runs a script or workflow, or posts to everyone (`delegation.lockdown`), without changing the offered list; messages and invites to the roster, follow-ups, facts in the person's own words and a contact they name still run, each fenced in its own path. A later turn in the conversation stays private to its owner but holds nothing: the person asking again, having read the reply, is their own request. A contact add the lockdown refuses becomes an approval card in the chat instead (`propose_actions`). Recipients are chosen in code, never by the model (a draft's new email may go to any address, named back to check when it is neither on the roster nor typed), and the text comes from the **ghostwriter** (`delegation.ghostwriter`), a tool-less call with a constant prompt plus the person's \"How I write\" profile. The ghostwriter is deliberately not a Council agent: the Council's edit routes have no principal check. See **Act as Me (Delegation)**. A second tool joins the same way: `recall_history` (`orchestrator.history_tools`, Always in the loop) reads the speaker's own notes of what they said, by email or in chat. It has its own registry and per-turn handler map too, and the loop adds it only when `history_tools.recall_person` finds the speaker verified, in a conversation private to them, on an interactive turn that isn't private to the principal, with their notes switch on. It doesn't need Act as me. After every chat turn the Executive also hands the speaker's own words to `history_chat.schedule_chat_notes`, which takes notes in the background when their switch is on and the surface verified them (see **Memory**). A meeting `create_calendar_event` proposes works the same way when the person chatting is the one who approves it: its chip carries the `decision_id` and the chat shows the meeting card (Approve, Edit, Dismiss) under the reply, while the briefing keeps it too. A tool result held for someone else's approval (`waiting_for_approval`, the department gate) gets a *Waiting for approval* chip, never a done one.\n\nThe Executive can also launch *any* workflow conversationally: `orchestrator.workflow_run_tools` adds `list_workflows` (the launchable catalog with each workflow's inputs) and `run_workflow` (runs a built-in or custom workflow to completion and returns its artifact, checkpointing approval gates as `awaiting_human`). `run_workflow` runs the weekly review, and in solo mode the morning brief, only for the principal on a verified surface (`Workflow.principal_only_modes`, `create_goal`'s rule); anyone else gets an audited refusal that does not name the rule. A run whose `result` event reports `private_to_principal` (the morning brief on the principal's own verified turn, when it read their private rows) still returns its artifact into that turn, but the stored run keeps `persistence.PRIVATE_RUN_ARTIFACT` instead of the text, since run history is readable by everyone signed in. This makes the `/jobs` catalog reachable from chat — see the Workflows section.\n\nDeliverables are first-class too. `orchestrator.artifact_tools` gives the Executive three tools: `draft_artifact` publishes a memo, web page (`html`), Word document (`docx`), spreadsheet (`xlsx`, from structured `sheets`) or a `link` to something it created in one of the principal's connected apps through the generic MCP gateway (`search_tools` → `call_tool`, any server — no vendor is named), and returns the artifact's id and link; `list_artifacts` and `get_artifact` let it find and reread its own past work (drafts and workflow outputs alike, through the same `artifact_records` read model the API uses). Every artifact belongs to someone: a draft to the person whose turn published it (`artifact_records.current_viewer`; with nobody speaking, the scheduler or the CLI, the principal), and a run someone started by hand to them, while scheduled runs are the team's. The tools, the recall, `message_person`'s link and mail attachments only ever reach the speaker's own (a link is refused when the recipient couldn't open it), not even the principal sees a teammate's, and a speaker who isn't on the People list publishes nothing. A workflow's own session inside someone's turn (the research synthesis) is pinned to that turn's viewer (`Session.documents_viewer`). Revising is `draft_artifact(supersedes=<id>)`, which archives the earlier version. When the principal asks for a deliverable the tool is always used; the \"quiet is the right default\" bar applies only to unprompted drafts. The format enum is a hard-coded sorted tuple so the cached tool schema stays byte-stable. Delivery: `message_person(person_id, text, artifact_id?)` appends the artifact's title and a `UI_BASE_URL/artifacts/<id>` link (through the same outbound guard as any DM; the link needs Open Executive access), and a Gmail send/draft can attach the file itself by `artifact_id` — see Integrations.\n\n**Extensions** (`orchestrator.extensions`). An install can add chat tools and kinds of document without changing this code. `OPENEXECUTIVE_EXTENSIONS` names Python modules. The first turn, or the first Documents read, imports each one and calls its `register()`. A module that fails is logged and skipped. `register_tool` takes an `ExtraTool`: a definition, an async handler, an optional `tool_groups` group (new or existing) and an optional chip. It refuses a name the loop already knows (`executive.builtin_tool_names`). An extension tool is never in `_ALL_SKILL_TOOLS`, so reflection, research and the synthesis never see it. The chat loop adds it per turn, like the Act as me tools, but never on an unattended run, a turn private to the principal or to a speaker who isn't on the People list (mail from a stranger), and only where its own `offered(session)` says. That predicate depends only on the kind of turn, so each kind of turn keeps one cached tool list. Act as me's lockdown refuses it once the turn has read the owner's mail, because it is unclassified and the lockdown fails closed, unless it was registered with `after_mail_read=True`: a tool that only reads the install's own data and carries nothing the model wrote anywhere outside. Its chip goes through `action_chips.summarize_action`, which applies the same no-chip rules for an error or refusal and keeps a link to a path inside the app. `register_collection` adds a kind of document: a drafted artifact tagged `collection:<name>` carries that collection on its record. The Documents page gives each collection its own filter. The collection's `on_change` hears about archive, restore and delete before they happen; if it raises, the change does not happen. `draft_artifact(supersedes=…)` refuses a collection's document. The alert pipeline strips `collection:` tags, so only the extension's own code files a document in its collection. A module that fails partway through `register()` leaves nothing registered. A tool registered with `workflow=True` is also offered to workflow action steps as `oe__<name>` (see Workflows); `read_only=True` marks one that only reads. A step runs with nobody in the turn, so `offered` isn't asked: `extensions.in_workflow_step(name)` is True for that tool, during its call only, and the handler decides what an unattended call may do.\n\nDocuments come in the other way through `read_document` (`orchestrator.document_tools`): it reads a PDF, Word, Excel, CSV, Markdown or text file by `path` — one another tool saved, such as a Gmail attachment (`get_gmail_attachment_content`) or a Drive file (`get_drive_file_download_url`) — or a company document by `filename`, with an optional PDF `pages` range. A scanned PDF is converted (`knowledge.pdf_reader`: local OCR by default; with `PDF_PROVIDER_READING=true`, the deployment's own model through its provider's PDF support, falling back to local OCR) rather than returned empty. Reads are confined to the tool download folders — the same resolve-then-contain check as `oe__read_file` — plus the company docs folder, and it is withheld on turns private to the principal (`PRIVATE_TURN_WITHHELD_TOOLS`): those come from a contact's email, whose own attachments the poller has already read into the turn, and must not steer the Executive into company documents.\n\nThe Executive also backs the **Ask OE** panel's form-fill tier via `orchestrator.form_tools.propose_form_values`: when a chat turn arrives with a `<page_context>` block describing a form on the user's screen, the Executive can propose values for it. The proposal is delivered to the UI as a `form_patch` SSE event and placed into the form as highlighted suggestions — the tool never saves or submits anything; the user reviews and saves manually. The tool is **always** in the tool list (tool definitions sit at the top of the cached prompt prefix, so a conditionally-present tool would invalidate the prompt cache whenever panel and non-panel turns alternate); its description restricts usage to turns that carry a form descriptor. For questions about the product itself, the always-offered `read_user_guide` tool (`orchestrator/guide_tools.py`) returns any `guide/prebuilt/<id>.json` section; its description lists the section ids, fixed at import, so it never changes the cached tools prefix.\n\n**Take the lead** (`orchestrator.take_the_lead`) is how the Executive acts on its own, behind one gate. It has two switches, both off until someone turns them on. **As the Executive** is the principal's alone (`PUT /take-the-lead`). With it on, the unattended passes (reflection, research, the scheduler's proactive trigger) keep the acting tools solo mode otherwise withholds from them: booking, starting workflows, and messaging teammates rather than only the principal. `schedule_tools.unattended_toolkit` and the chat loop's unattended path then wrap every acting tool (`ACTING_TOOLS`, plus any MCP tool whose name sends, creates, updates, deletes or shares) in `gated_handlers` / `gated_call_tool`. The principal-only tools (`UNATTENDED_WITHHELD_TOOLS`) stay withheld, and every guard inside a handler still applies, including department approval levels (a booking in a department on Proposes is still a proposal) and the contact-egress rule. New mail or chat (any turn with an `origin_channel`) wakes the existing reflection early (`take_the_lead.wake`): one run waiting at most, five minutes after the first message and no more than every 30 minutes, as a one-off `take_the_lead_wake` scheduled action. Pause holds it like any scheduled work. **As you** is the Handle it for me dial's top step (delegation section).\n\n**The gate** is plain code (`take_the_lead.check`). Six kinds of action wait for a yes first, each with an Ask first switch, all on to start. The switch is the decision ledger's own mode for the class `take_the_lead_action:<kind>` (`propose` asks first, the default; `auto_execute` doesn't). The kinds are money, contracts and legal, hiring and people decisions, deleting/cancelling/sharing, someone new (an address on neither the roster nor the contacts) and big sends (a broadcast or department message, or more than five people). On top of these, the company (set by the principal) and each person (for their own As you) add structured rules: a person or address, a domain, words, or an amount at or above a figure. Added rules always hold, and an error reading them holds the action. The one thing the gate lets straight through is a direct message (`message_person` or a Slack, Telegram or Discord DM) whose only recipient is the principal (`_only_to_principal`): they are who it would wait for, so a card would only ask them to approve a message to themselves. Anything that reaches or acts on anyone else is checked, and a roster that can't be read is not the principal. A held action becomes a `take_the_lead_action` decision instance with a companion `DECISION_ALERT_SOURCE` card on Today, routed to the first teammate holding one of its People approval ranges (`take_the_lead.approval_ranges`, plain code, closest fit first: money to `spend_lt_2k`, `spend_lt_10k` or `spend_gt_10k` by its largest amount, with a higher range able to approve a lower one and no amount read as large, or to `customer_credit` for credit and payment terms; vendor contracts to `vendor_onboarding` then `legal_sign`, other contracts to `legal_sign`; hiring to `hiring_signoff`; anything else about the board or investors to `board_comms`; in Personal as in team mode), or else the principal through the authority gate's fallback (`departments.authority._route_proposal`). Deletes and shares always go to the principal. Only the principal and that approver see or resolve it (`DecisionClassSpec.principal_and_approver`). Approving it claims the row and carries out the exact call once (`take_the_lead.carry_out`: the unwrapped handler, or the gateway's `call_tool`, on an unattended session, with contact egress only when the principal approves). Declining drops it. Everything done or held is a row in `take_the_lead_log`. What it did and what was approved show in Recent activity (`today._build_activity`, kind `took_the_lead`), named but never quoted, since that feed is the team's. The held card's own `decision_resolved` row is left out because its payload quotes the message. `GET /today/activity` also adds the caller's own Handle it sends (kind `sent_as_you`, actor `you`), which are never in the shared feed.\n\n**In training.** The As the Executive switch has three positions: Off, **In training** and On (`take_the_lead.training`). In training, an action the gate would let through still waits, as a `training` hold for the principal alone, unless the principal has allowed that action with that person or thing (`take_the_lead.allowance`: \"Message Priya Nair\" covers a message to her on any channel; \"Book meetings with Priya Nair and Sam Lee\" meetings with exactly them; a workflow by id; a connected tool by name and the file it names, never one that reaches people such as a mail send or a share). The card carries Approve, **Approve + allow**, **Edit** (the message, a meeting's title, times or description, a task and its due date: `take_the_lead.apply_edits`) and Decline. Allowing is the principal's alone and needs a request the API can tie to them, as turning it on does; the six kinds and the added rules hold whatever is allowed. An edit approved with \"Do it like this next time\" is kept as an example (only the edited text, the principal's own words), and `take_the_lead.learned_note` hands the examples and the fact it's in training to the reflection and research passes in their user turn. After `SUGGEST_AFTER` (3) unchanged approvals of the same action in 30 days, Settings suggests allowing it. What it's learned is one list keyed by feature (`take_the_lead_allowed.feature`), so other features that learn from approvals can join it; each keeps its own switch. Act as me is the second (`act_as_me`, per person, `delegation.training`), with a training switch per setting (Replies, Follow-ups, Suggested actions, Drafts): its rows carry the person's id and the setting in their key, are listed and removed by that person alone, count toward their own cap, and never reach `learned_note`.\n\n**AI disclosure.** Nothing the Executive sends to people outside the web chat goes without saying it is an AI: plain code adds the line in the MCP gateway (mail) and at each chat send (Slack, Telegram, Discord, Google Chat replies, its DMs and room posts), never the prompt, so the persona and the cached system blocks are unchanged and a reply the model writes can't drop it. Replies the inbox watcher writes as a person carry their own line by that person's switches. See Integrations → **AI disclosure** and Act as me → **AI line on replies**.\n",+ "markdown": "The Executive (`openexecutive.orchestrator.executive.Executive`) is a single coherent persona that fans out to specialist sub-agents via Anthropic tool use. Each specialist subclasses `openexecutive.agents.base.BaseAgent`, carrying a `name`, `domain`, and `model`, and exposes `analyze(...)`, which wraps the question in user-turn context and calls Claude through the per-call provider. That context is per call and never cached: `<company_stage>` (the stage from the company profile — specialists never see the profile itself), in solo mode `<principal_role>` (what kind of principal the advice is for, in plain words, with their title and remit — `router.principal_role_context`), `<department_memory>`, `<past_decisions>`, `<failure_cases>` (the shipped case studies, and under them the workspace's own lessons that match the call, `memory/lessons.py`), `<relevant_knowledge>` and `<conversation_context>`, outermost first. The specialist's own system prompt is a static domain constant under one `cache_control` block, so it stays byte-identical across companies and profile edits. A chat turn takes the stage from its session's profile (the one the Executive reasons over, and the one an eval scenario injects); workflow steps and the MCP server's `consult_specialist` read it fresh from the profile on disk. The role tag follows the turn's mode: a chat turn pins the role on its session with the mode (`pin_turn_principal_role`: the session's `principal_role` override, else the workspace settings) and sends it in solo and nothing in team, so the org block, every specialist in the turn and any workflow the turn starts see the same role; callers with no chat turn read it fresh (`load_principal_role`: the current session's mode and role, else the workspace's), and a failed read sends no tag rather than failing the consult. The CFO, CSO and sales prompts key their advice on it: for a bootstrapped, self-funded or solo company they drop venture fundraising benchmarks and work from cash, and raise only if the founder wants to.\n\nRouting uses one `consult_specialist` tool. When to call it is spelled out in the persona's Domain Expertise section (\"Going deeper\") and in the tool's own description: any question that asks for judgment in a specialist's area (a decision, plan, analysis, negotiation, hire, contract term, pricing or fundraising move, board message, or a department's own targets and stance, since the specialist holds that department's memory) is consulted before the answer, several at once across areas; lookups in mail, calendar or documents, scheduling, status checks, routine drafting and questions about how the Executive works are answered without one. Chat eval scenarios hold this: `required_routing` names specialists the turn must consult and `no_routing: true` says it must consult none, and the runner fails a scenario that misses either (`evals.scenarios.routing_check`). Beside it the Executive carries two skill tools, `search_skills` and `load_skill` (skills are shown to users as **playbooks**, and every playbook belongs to a workflow: one that follows it, or its own Quick workflow). Chat finds and reads playbooks but never creates or changes one: work worth repeating is offered as a workflow through `draft_workflow`, with the method written into its steps, because workflows read playbooks at run time (approved scheduled ones included) and this loop also runs on inbound email and chat, so only a person can change what a workflow follows. A hidden built-in is invisible to search and load; each `search_skills` hit lists the `workflows` that follow it, Quick ones included, and the persona routes \"the finished deliverable\" to that workflow and quick or partial asks to the playbook inline; Tool calls made while proactive work is tagged (scheduler dispatch, reflection, research, alert review) feed the Attunement outcome ledger. Goals have three tools: `list_department_goals`, `update_department_goal` (progress the user reports) and `create_goal` (a new goal the principal states, filed under an area by slug or title and creating the area when none matches — see Org). `create_goal` runs only for the principal on a verified surface, and no unattended run is offered it: the tools in `schedule_tools.UNATTENDED_WITHHELD_TOOLS` are dropped from reflection's and research's toolkits by `unattended_toolkit`, and from the chat loop when its Session is marked `unattended` — the scheduler's PROACTIVE TRIGGER run, whose prompt quotes stored intent text; a call the model emits anyway gets an error tool_result. `record_decision_outcome` records how a past decision turned out — the weekly review lists decisions older than 30 days with no outcome as `[decision N]` — writing `decisions.outcome` (`episodic.update_decision`) and auditing the rationale; it has `create_goal`'s gate (the principal on a verified surface only; everyone else gets an audited refusal) and is in `UNATTENDED_WITHHELD_TOOLS` too. A missing or unknown id returns the decisions still waiting on an outcome, so the model can retry with the right one. Its schema is static; the solo persona has one line on it, and team mode learns it from the tool description, so the team persona is byte-identical. Attunement adds `list_open_loops` (what a person owes — everyone's for the principal only in a private conversation, otherwise the caller's own) and `close_open_loop`, which only closes a loop when the turn's resolved speaker is the principal or the loop's owner — an unrostered sender, a signed-in web user not on the roster, and unattended sessions are refused. `assign_open_loop` opens one on request (\"ask Ben to send me the Q3 numbers by Friday\") for the principal or a rostered teammate on a verified surface — never an email, a turn private to the principal or an unattended run, which are also withheld the tool — and only when `task` appears verbatim in what the speaker typed this turn, at most 5 per turn; that turn's extraction pass then opens no second loop for the same owner. The owner is told once on their own channel when someone else assigns it, and the result's `notified` says how that went, so the Executive reports it rather than messaging them as well. The roster write tools (`upsert_person`, `archive_person`, `set_department_head`) are the principal's alone, and only on a surface that verified the speaker — the web chat, the principal's own Slack or Discord, a channel whose adapter verified the sender itself (`Session.speaker_verified`, with the `caller_person_id` it resolved, never on a turn an email started), or a private Telegram chat when `TELEGRAM_WEBHOOK_SECRET` is set to a value Telegram can send (Telegram identifies the chat rather than the sender, and without that secret its webhook accepts anyone's update). A teammate, an email (even from the principal's address), Google Chat, the CLI, the MCP server and unattended runs get `status: refused` (audited, and no action chip), because a team member's People row is also the web sign-in and outbound-email allow-list. `upsert_person` takes `kind` (`team` / `contact`; a new person defaults to `contact` in solo mode, an update keeps the current kind) and `email_aliases` (other addresses the person writes from — the full list, replacing the current one; they match mail and may be emailed but never sign in, and one already on someone else is refused), and after every write any pending roster request whose sender now matches someone is closed and its held messages replayed. `resolve_roster_request` answers a **roster request** — someone not on the People list who wrote in and is waiting (see Org): `approve` (a new person; `kind` defaults to team for a company-domain sender, else contact, when the principal did not say), `link` (someone already listed, by `person_id`; `replace_channel_id` only when the principal said so) or `decline`. It has the roster tools' gate (the principal on a verified surface; audited refusal otherwise), is in `UNATTENDED_WITHHELD_TOOLS`, and answers only an id in `Session.trusted_roster_request_ids` — the ids the server printed that turn in a `<roster_requests>` block (`briefing.context.format_roster_requests_for_prompt`, up to 10 pending requests), which `render_and_trust` appends to the `<briefing>` digest on the principal's own verified turn only and records on the session in the same step, so an id the model invents or reads out of a message adds nobody. Each line is server-derived — id, channel, address or account id, the sender's name sanitised and marked unverified, a company-domain hint, the message count — and never what they wrote. The block rides in the **user turn**, like the digest, so the cached system blocks are unchanged; the tool definition is static, and the new tool only extends the sorted tool list. The web chat route resets the trusted set every turn, and a resolved id is removed from it. and `list_people` returns both kinds with `kind` — contacts only on the principal's own verified turn (they are private to the principal; anyone else gets the team as if no contact existed) — while `lookup_person` searches the team only. `ask_about_person` reads a person's peer memory fully only on their own verified turn; anyone else's answers only to a verified principal or teammate, and only when that person turned on \"Share my work style with the team\", framed to how they work and never their view of a colleague, and otherwise returns the same \"hasn't chosen to share\" result whether or not anything is known. A teammate's own mail with the Executive is theirs the same way: every mailbox call the model makes through the MCP gateway (Gmail or Outlook, by `call_tool`, from a script, or a workflow step run from chat) passes through `orchestrator.teammate_mail`. A search excludes every other teammate's address server-side, except on mail the reader is also on, and is filtered again entry by entry; any other call that names a message or thread (read, attachment, reply, forward, label) must use an id a filtered search returned to the same reader in this conversation (`Session.mail_ids_seen`) or the inbound email the turn answers; reads are filtered message by message, so a message naming another teammate is left out unless the reader is in its From / To / Cc; a reply that would quote such a thread, or an Outlook forward, reply or attachment read of such a message, is refused; and a conversation in which a teammate other than the principal was shown their own mail becomes theirs alone, as Act as me's do. Outside mail and the reader's own are untouched; an email turn reads as its sender only when Gmail authenticated it, and any other unverified reader sees no teammate's mail, a background run the model drives reads as the principal and a workflow step outside any session as nobody, an Outlook inbox rule that forwards or names another teammate is refused, and the poller and the brief, which read the mailbox themselves, are unaffected. Their own chats are theirs too: every audit row of a teammate's verified turn is theirs (`people_tools.teammate_turn_owner`, see Audit; the principal sees the actions, never the words), and a teammate's web chat or DM opens for them alone (`chat._session_access`), the principal included. The same verified-principal rule, as `people_tools.contacts_reachable_now()`, decides whether a turn may reach a **contact** at all: `message_person`, the raw DM tools, `create_calendar_event` / `create_instant_meeting` attendees and the MCP gateway's Gmail / Calendar / Drive / OneDrive gates treat a contact exactly like an unknown person on every other turn, so no refusal reveals that one exists. **The untrusted-content policy** (`orchestrator.content_trust`) is one rule for text the principal did not write — inbound email, chat, attached files, watched pages — answering three questions for every surface. *Who is speaking*: the principal only when the surface proved it (`principal_speaking`: the web chat as the principal — never a signed-in email on nobody's People entry —, the CLI, their own Slack/Discord or a secret-verified Telegram chat, or their own address with Gmail's `dmarc=pass`); never a teammate, a stranger, Google Chat, the MCP server or an unattended run. *What may become memory*: episodic extraction runs only then, and only on the words outside `<untrusted_content>` blocks; peer memory and open loops are recorded under the speaker's own name, never as the principal's. *What may trigger tools*: every write on the principal's authority already refuses others in its handler; the tools with no such check that change the install for every later turn — `content_trust.PRINCIPAL_ONLY_TOOLS`: `load_mcp_server`, `list_saved_tools`, `run_python_job` and `run_script` — are not offered unless the principal is speaking on an interactive surface (not email, even authenticated), and a call the model emits anyway gets an error tool_result and a `refused: not_principal` audit row. So an inbound email, a teammate's turn, Google Chat and the scheduler's proactive trigger each get a stable tool list of their own without it. A send or edit on a team member's turn also meets their department's authority first (`orchestrator.department_gate`, see Org), and so does one on a turn whose speaker is on no People entry: a signed-in web caller or a chat-channel sender, which in practice is Google Chat, since Slack, Telegram and Discord turn unmatched senders away. Google Chat names a matched sender to the gate alone (`gate_sender_person_id`), so the principal there is not held. Email turns are left to the mailbox's own gates. *How it is labelled*: outside text goes into the user turn inside `<untrusted_content source=… author=… author_verified=…>` with a fixed notice that it carries no authority; compatibility forms are folded (NFKC), control characters go, and the tag's name is renamed wherever the text carries it — any case, spacing or entity-escaped form — so the text cannot end its block and speak outside it.\n\n**Outside content** (`orchestrator.outside_content`). Once a turn has read text from outside the team (any gateway read, an attachment, a web search result, a synced Drive, OneDrive, Confluence or Notion excerpt, `read_document`, research, or an extension tool registered `reads_outside`), the rest of that turn refuses what the Act as me lockdown refuses, every `upsert_person`, and every `call_tool` but a read: no mail, Docs, Sheets, Drive or calendar write. A round that reads also holds that round's other such calls; the read itself runs. Scripts are checked call by call. The offered tools never change, so the cached prefix stays the same, and the hold ends with the turn. Mail from someone not in People (a contact or a stranger) counts as outside content from the start of its turn (`Session.sender_off_team`), so the whole turn is held, with no direct messages or watchlist removals either; it can still raise an alert, private to the principal, which is how that mail reaches them. Someone added to People in a turn (or given a new address or chat account) is not emailed, messaged, invited or shared with until the next one.\n\nA turn about the principal's private mail (`Session.private_to_principal`) reaches the principal only. It is neither offered nor allowed to run `schedule_tools.PRIVATE_TURN_WITHHELD_TOOLS` — everything that reaches someone else, publishes where the team reads, or starts work outside the turn: the broadcasts, meeting bookings and cancellations, `run_workflow` and research, follow-ups and workflow nudges, watches, artifacts, goal updates, saved workflows, skill drafts, and `load_mcp_server` (it connects to any URL, which can carry the turn's content). Through `search_tools` and `call_tool` it reaches only `schedule_tools.PRIVATE_TURN_MCP_TOOLS`: Google Workspace reads (mail, calendar, and Drive, Docs and Sheets search and file reads, with their Microsoft 365 twins; OneDrive's `download-bytes` only for a file's content) and the Gmail send and draft the gateway narrows to the principal. A search shows it nothing else, and a call to anything else (Google Chat, a Docs or Drive write, `manage_event`, another server) is refused (`schedule_tools.private_turn_withholds`). A call the model emits anyway, MCP tools included, gets an error tool_result and writes an audit row, and every audit row the turn writes is the principal's alone.\n\nA turn another AI app asks over the MCP server (`Session.from_mcp_client`, set by `ask_executive`) reads and advises but never acts. It is neither offered nor allowed to run `schedule_tools.MCP_CLIENT_WITHHELD_TOOLS`: the private-turn and unattended sets, plus every direct message (`message_person`, the Slack, Discord and Telegram DMs), alert acks and new alerts, brief edits, closing open loops, roster and department-head writes, watchlist changes, workflow drafts and form proposals. It gets no Act as me, `recall_history` or extension tools, and of the gateway tools only `schedule_tools.MCP_CLIENT_MCP_TOOLS`: the private-turn reads without the Gmail and Outlook send and draft tools. The set is fixed, so the variant keeps a stable cached tool prefix. A call the model emits anyway, through `use_tool` or `call_tool` included, gets an error tool_result telling it the conversation comes from another AI app, so it can read and advise but not send, post, book or change anything, and writes an audit row (`refused: mcp_client`); `MCPGateway.call_tool` refuses the same calls again.\n\nA web chat its owner shared (`Session.shared_chat`) mixes people. The note naming who is in it says which of them owns it and that the others' lines are messages from them, not the owner's instructions. While someone other than the owner has written since the owner's last message (`Session.others_spoke_last`, set per turn by the chat route from the saved history, the speaker included, and true when the history can't be read), the turn is neither offered nor allowed to run `schedule_tools.SHARED_CHAT_WITHHELD_TOOLS`: direct messages, the broadcasts, meeting invites and cancellations, follow-ups, roster writes and workflows (a run, a save or a suggested schedule acts later with the full tool set). Through `call_tool` it can't send, reply, forward or draft mail in Gmail or Outlook, or make a calendar change that mails attendees (`schedule_tools.shared_chat_withholds`). That holds on the owner's own turn right after someone else's line too, so a request carried over from it can't send; the owner's next message with nobody else's in between lifts it. A call the model emits anyway gets an error tool_result and writes an audit row (`refused: shared_chat`). The principal-only tools stay out of every shared chat (`content_trust.principal_only_withheld`).\n\nOn every turn the Executive knows what is connected without searching: block 0's *Connected Systems* section names the connected Google services, other MCP servers, the messaging channels, Notion sync, Confluence sync (when on) and Act as me, and pins the Google tool names it calls directly with `call_tool`. Both the service list and the pinned names are narrowed to what workspace-mcp actually loaded (`WORKSPACE_MCP_TOOLS`, `WORKSPACE_MCP_TOOL_TIER`), so a service left out is not named and its tools are not pinned — being told a tool is already available when it is not in the index costs a failed call the model cannot explain to itself. `search_tools` is for anything not listed. When work repeats over many items, the Executive can also call `run_script` (`workflows/step_script.py`, offered when the gateway runs, unless `CHAT_SCRIPTS=false`, and only on the principal's own turns — `PRINCIPAL_ONLY_TOOLS`, withheld on an unattended pass too, because it spends the turn's whole call budget on code the model just wrote): one short Python script, run in a sandboxed Monty worker with no files, network or environment, whose only reach is the gateway tools `call_tool` could reach (those `search_tools` has returned; the gateway keeps that set for its own process-wide session, not per conversation). Each call it makes is a `call_tool` in every way that matters — the gateway's discovery, deny-list and recipient gates, Take the lead's gate on an unattended run (or the department gate on a team member's turn, see Org), and the same action chip and `tool_invocation` row (marked `via: run_script`, `ok: false` when it raised), as each call happens; the script itself gets a `kind: script` row with its source and result. Its wall clock is half the turn's deadline, so a long script ends with the list of calls it made rather than being cut off with the turn, and a stopped turn closes it and its worker. A turn private to the principal is not offered it, and the Act as me lockdown withholds it whole. Besides gateway tools, a chat script may call a fixed list of the Executive's own tools (`step_script.CHAT_OWN_TOOLS`: reads, alerts, open loops, goals, the watch list, follow-ups, `message_person`, `upsert_person` — nothing that broadcasts, books calendars, edits memory or skills, or starts workflows or research), each only when the turn is offered it and through the turn's own handler (Take the lead's gate included), with the same chip and a `kind: skill`, `via: run_script` audit row. A direct call needs a `tool_use` each, so a turn's scripts share a budget instead: `CHAT_SCRIPT_MAX_CALLS` (default 200) calls in all, and per-turn caps on own tools that could otherwise act in bulk (`CHAT_OWN_TOOL_CAPS`: `message_person` 10 — messaging the whole roster would be a broadcast — `upsert_person` 25, `create_alert` 50); a refused call tells the model to say what is left. A call stopped mid-flight by the script's clock or the turn still gets a `cancelled` audit row, since it may have run. Because every round re-reads the conversation, the loop also nudges at the moment of choice: after a round whose results include a list of five or more items (`step_script.lists_many`), with `run_script` on offer and not used that round, it adds the constant `FANOUT_HINT` as a text block in that round's user message (never a cached block), once a turn, pointing the per-item work at one built tool. For library work on files (PDFs, spreadsheets, charts, images) the chat also has `run_python_job` (see Workflows → Python jobs): Python with a fixed library set in a Deno-isolated WebAssembly sandbox, fed Knowledge files by name, the message's own attachments as sent, or text it already holds, and able to keep a job that worked as a Custom tool, with result files linked for the principal to download; it is offered only on the principal's own turns and only where the sandbox is installed (not offered otherwise, so the tool prefix stays fixed per process). Agent Activity shows each run as one \"Built tool\" card (debug event `script_run`: ok, the calls it made, how many, how long, and the kept or reused tool's name). The persona's tool-building section is present only when chat scripts can actually run (the setting and Monty installed). `TOOL_BUILDING_ADDENDUM` in the cached persona tells the Executive when to build a tool — a job that looks something up and then checks or acts on each result, paged results, more than about ten items, or an answer that needs three or more reads (find, open, read; the tool returns only what answers the question, not whole documents, and only what is about to be edited or quoted at length is read in full), while a handful of items already named go as direct calls in one turn — and never to say it has none, and to talk about it as building a tool or doing it in one go. On the principal's own verified, interactive turns, a script that works can be saved as a named tool (`save_as`; elsewhere the script runs but is not saved) and run again with `run_script(tool=…, inputs=…)`; `list_saved_tools` (a constant definition, in `PRINCIPAL_ONLY_TOOLS` with `load_mcp_server`, so offered only while the principal is speaking on a verified, interactive surface; `run_script(tool=…)` is refused on any other turn) lists them, and each call a saved tool makes is a gateway call like any other (see Workflows → Saved tools). The tool's definition is a constant, so the cached tool prefix does not move. Multiple parallel `tool_use` blocks in a single assistant turn fan out concurrently through `router.route_parallel`, each running its own domain-filtered ChromaDB query (3 built-in and 2 company chunks by default, see the RAG section) before the specialist sees the question. The fan-out is failure-isolated per call: a specialist that raises or returns no text becomes an `UNAVAILABLE` tool_result (`router.specialist_unavailable_result`) instead of failing the whole turn, and its area — \"finance\", \"legal\", never the specialist's name — is reported to the user under the web reply, or by the Executive in its reply on other channels, unless another call to it answered that turn. A failed specialist does not count as consulted, so it takes no committee seat. Cancellation (Stop) still propagates. The Executive then synthesizes the returned analyses into one reply.\n\n`remember_fact`, `forget_fact` and `update_company_profile` (`orchestrator/fact_tools.py`) make a correction stick: the first two keep or retire a standing fact in `memory.facts`, and the third changes one field of the company profile. They share `record_decision_outcome`'s gate (the principal on a verified surface, an audited refusal for everyone else) and are in `UNATTENDED_WITHHELD_TOOLS`. `remember_fact` alone also admits a rostered teammate on a verified surface (web signed in, their own Slack or Discord): the fact is stored attributed (`recorded_by_role=\"teammate\"`, rendered `(per <name>)`), and is held as a `proposed` row (`awaiting_approval`) until the principal approves it, unless the principal marked that teammate trusted (\"needs my approval\" off; on by default) — and even then when it would replace the principal's fact. All three are also in `PRIVATE_TURN_WITHHELD_TOOLS`, since what they write or retire is read on everyone's turns. On the principal's own authenticated email (primary address, with Gmail's own `Authentication-Results` reporting `dmarc=pass`, not forwarded) the three tools check the request as usual, then hold it as `awaiting_confirmation`. It applies only when the principal replies to a one-time token emailed to their own address (`integrations.fact_confirmation`); the split into a check step and an `apply_*` step lets chat and the confirmed reply share one apply path. Each write also needs a `source_quote` found in the speaker's own words this turn. The active facts reach every specialist as a `<standing_facts>` user-turn tag: `route_to_specialist` reads them (None → the store, \"\" → none) for chat consults and workflow steps alike, and `BaseAgent.analyze` places the tag next to `<past_decisions>`, never in the cached specialist system prompt.\n\nThe ten entries in `SPECIALIST_REGISTRY` (`openexecutive.orchestrator.router`):\n\n| Key | Agent | Domain |\n| --- | --- | --- |\n| `cso` | `StrategyAgent` | strategy |\n| `cfo` | `FinanceAgent` | finance |\n| `chro` | `HRAgent` | hr |\n| `gc` | `LegalAgent` | legal |\n| `coo` | `OperationsAgent` | operations |\n| `cmo` | `MarketingAgent` | marketing |\n| `cpo` | `ProductAgent` | product |\n| `sales` | `SalesAgent` | sales |\n| `board_comms` | `BoardCommsAgent` | board |\n| `triage` | `TriageAgent` | triage |\n\nModels: specialists default to `claude-sonnet-5-5`; the deep-reasoning tier (CSO, CFO, GC, Board) runs on `DEEP_REASONING_MODEL`, `claude-sonnet-5-5` by default, with adaptive thinking; routing/fast classification uses `claude-haiku-5-5`. Requests are fitted to the model's generation on the way out (`feature_gate.fit_claude_generation`): 5-generation Claude models never receive `temperature` / `top_p` / `top_k`, and Haiku 5.5, which thinks unless told otherwise, gets thinking turned off when the caller asked for none. The Council's **Deep reasoning** toggle is honoured on Claude Opus/Sonnet (direct or via OpenRouter) and on any OpenRouter model whose live catalog entry supports `reasoning` (today all OpenAI, Gemini, DeepSeek and Grok entries; not Llama) — the request translator turns Anthropic adaptive thinking + effort into OpenRouter's `reasoning` parameter. It is a silent no-op on models that can't reason, and disabled for Haiku, which rejects adaptive thinking. A PDF `document` block is translated too: it becomes an OpenAI `file` part, and OpenRouter requests carrying one add the `file-parser` plugin (`native` for models whose catalog entry lists `file` input, else `PDF_OPENROUTER_ENGINE`, default `mistral-ocr`). `FeatureSpec.supports_pdf_input` gates it per model — off for a local server unless `LOCAL_PDF_INPUT` — and a gated-off PDF becomes a text note rather than vanishing. The Council picks a model in two steps: a **Provider** dropdown (Anthropic, OpenAI, Google, Meta, DeepSeek, xAI, Local, …), then a **Model** dropdown limited to that provider, with readable names (\"Claude Opus 5.5\") and the raw id and serving route shown underneath. The Anthropic group combines the direct Claude models (`claude-fable-5-1`, `claude-opus-5-5`, `claude-opus-5`, `claude-sonnet-5-5`, `claude-sonnet-5`, `claude-haiku-5-5`, `claude-haiku-4-5`) with any Claude generation that exists only on OpenRouter, and never lists a model twice. With `OPENROUTER_ENABLED`, the non-Anthropic entries come from OpenRouter's live `/models` catalog (fetched at startup, refreshed in the background, filtered to tool-capable paid text models from an allowlisted vendor set), falling back to a built-in snapshot if the fetch fails. Every Council agent also takes **additional instructions** (`agent_overrides.instructions`): text appended after its prompt by `agents.overrides.append_instructions` inside an `<additional_instructions>` block. `BaseAgent.base_system_prompt()` is the built-in prompt or its full replacement (what the Council's editor shows); `effective_system_prompt()` is that plus the instructions (what every call sends), and the Executive gets the same text through `build_system_blocks(persona_instructions=…)`. Unlike a replaced prompt, instructions leave the agent on its built-in prompt, so prompt improvements keep reaching it. A **Quality** choice above the agents (`agents.presets`) sets every agent's model and deep reasoning at once: **Fast** puts every agent on a small model (`claude-haiku-5-5`, else `claude-haiku-4-5`) with deep reasoning off, **Balanced** returns each agent to its built-in defaults, and **Thorough** puts the Executive and the domain specialists on the largest allowed model (`claude-opus-5-5`, else `claude-opus-5`) with deep reasoning on where the model supports it, leaving triage and the helpers below on their defaults. Presets change quality only; they never cap spend. Each preset resolves against the install's model allowlist at request time and is offered only when one of its models is allowed. Applying one writes ordinary per-agent overrides (model and deep reasoning only), so history, rollback and later per-agent edits keep working; an agent changed on its own afterwards shows as **Custom**. Each Council agent has a **visibility**: `core` for the Executive and the domain specialists (`BaseAgent.visibility = \"core\"`, which a new specialist must declare) and `internal` (the default) for triage and the helper agents below. Thorough moves only core agents. The Council opens in a **simple view**: the Quality choice, the voice picker, and only the core agents, each with its additional instructions and a model badge. **Show all agents** lists the internal ones too, and **Advanced** opens the full page (the browser remembers the choice). Eight Council-only agents are model/prompt-overridable in the UI but NOT callable via `consult_specialist`, because they are deliberately kept out of `SPECIALIST_REGISTRY`: `quality_judge` (committee review), `utility_fast` (gates, titles, decision parsing), `research` (the `executive_research` fan-out), `fixture_generator` (invents demo companies), `engagement_intake` (models a real client from intake material), `onboarding_interviewer` (interviews a new user about their own company and drafts its profile, people and departments), `workflow_designer` (runs the conversational New workflow wizard on `/jobs/new`: searches the available tools, asks clarifying questions, then drafts a validated dynamic-workflow definition for the user to review), and `workflow_actor` (runs a workflow's `action` steps: a bounded tool-use loop limited to the tools the user approved for that step). `fixture_generator`, `engagement_intake` and `onboarding_interviewer` share one shape — a forced tool call producing a whole company, validated for referential integrity, with a single repair retry — but opposite epistemics: the fixture author invents, the other two extract and leave unstated facts empty rather than guessing. When the workspace is in solo mode, `onboarding_interviewer`'s first user turn is prefixed with a short hint (`interview.solo_hint(role_kind)`, one static constant per role kind from the onboarding role step): the draft names only the principal, as principal, and no departments; an owner is asked about the offer, customers, pricing, cash and runway, an in-house executive about their organisation (drafted as the company — their employer), function, remit, manager, team size as context and what they are measured on, an independent about their practice, clients and pricing, and with no role given the role-neutral `SOLO_HINT` asks which they are. The hint rides in the user turn and the tool array is unchanged, so the cached system prompt and tool prefix are the same in both modes.\n\n**Voice.** The Executive answers in one voice persona, substituted into block 0 at `{VOICE_PERSONA}` (`personas/loader.get_active_body`) from the Executive override's `voice_persona_slug`. Three general voices ship in `personas/builtin/`: **Direct** (`default`, the slug used when none is set: answer first, brief and decisive), **Supportive** (a warm coach who explains the why and checks how the plan sits) and **Analytical** (numbers first, options and trade-offs, then one recommendation). They are offered by a shared picker in setup (`/onboard`, after the workspace choice) and in Settings → Executive, which saves through `PATCH /agents/executive`; a built-in voice's frontmatter carries the picker's one-line `description` and `sample` reply. The named-executive voices are marked `legacy: true`: the picker hides them, but they still load, so an install that picked one keeps it, and the Agent Council lists them under \"Legacy voices\". Voice files hold disposition only; the response-length ladder lives in `prompts/executive_persona.py`, and a test keeps numeric length rules out of every voice file. An eval scenario may set `voice_persona` to answer in a voice; it rides on `Session.voice_persona_slug`, which wins over the override for that session only.\n\nOne more structured-output utility agent sits beside `triage`: `openexecutive.agents.alert_review.AlertReviewAgent` (routing model, one forced `emit_alert_reviews` tool call, never raises). The alert review job hands it a batch of open alerts with evidence and gets back, per alert, a verdict (relevant / changed / resolved / stale), a confidence, the evidence it relied on, a one-line note, why-now, an optional deadline, and a recommended move (none / route / nudge / escalate / draft / suggest_workflow / merge / close) with its parameters. Like `triage`, it never mutates state — `alerts.review.apply_verdict` executes the verdicts deterministically within authority, so the model's job is judgment, not action.\n\n**Solo mode.** When the workspace (or the turn's session) is solo — one person using Open Executive for themselves — the Executive works for that one person, the principal, whatever their role: they may run their own business, lead a function inside a larger organisation, or work independently, and the persona reads which from the context instead of assuming it — the role lines under \"Your Principal\" in the org block, when the principal gave their role (workspace settings: kind, title, reports to, remit, measured on). Its persona swaps the team sections (\"You Are a Member of This Executive Team\", \"Choosing Who to Tell\", \"Departments & Org Coordination\") for \"You Work for One Person\", \"The People in Their World\", \"Who Hears From You\" and \"Goals and Areas\". Solo means only the principal uses Open Executive — not that they have no people: their manager, direct reports, peers, clients, investors and board are contacts. The Executive helps the principal work with them (a 1:1 or review prep, an update or budget case for their manager or board, a negotiation) but does not coordinate them, contacts them only when the principal asks and only if they are a contact, and never offers to loop the principal in. Every specialist stays relevant — HR for the principal's own reports, board and investor communications for reporting upward. Goals are grouped by *area* (the tools' `department_slug` is the area's slug). The chat loop withholds `send_department_message`, `send_company_broadcast` and `set_department_head` from its tool list, and a call to one of them anyway gets a JSON error tool_result instead of running. The mode is resolved once per turn and pinned on the session, so the persona, the org block, the tools and every tool handler agree — a switch made mid-turn applies from the next turn. Team mode is unchanged.\n\nEvery specialist *advises* — each returns domain analysis the Executive synthesizes into one voice. None of them act on the company's behalf; the side-effecting tools in the main loop (schedule, people, departments, broadcast, watchlist, workflows) belong to the Executive, not to a specialist.\n\n`recall_history` (Always in the loop, `orchestrator.history_tools`) reads the speaker's own notes, on the same terms as `ghostwrite_email` below: its own registry, offered only on a verified turn in a conversation private to them with their switch on; its `due` flag lists only dated notes, soonest first (see Memory). The ghostwriter below also gets the writer's notes from mail every recipient was on, as a consistency check (`<writer_noted>`).\n\nThe morning reflection, which has no question to look up and no specialist to consult, gets one more read-only tool of its own: `search_knowledge` (`orchestrator.knowledge_tools`), the same knowledge lookup a chat turn makes, for what the company's documents say about a customer, contract, price or policy before it acts.\n\nA fifth, `remind_me` (`orchestrator.reminder_tools`), sets a plain-text reminder sent to the speaker alone when it is due; it opens no mailbox, so it never locks a turn. A sixth, `propose_actions` (`orchestrator.action_card_tools`), does nothing itself: it leaves the speaker a card of up to five actions (a meeting, a message, a new contact) that happen only when they tap Approve, so it stays on after a turn read mail; it is where what an email itself asks for goes, since that is never done on the email's say-so. Four read-only tools beside it read the speaker's own mailbox on the same terms — `search_my_email`, `read_my_email`, `read_my_email_attachment`, `my_email_awaiting_reply` (`orchestrator.mail_read_tools`) — and `my_calendar` their own calendar while Read my calendar is on, capped per turn, other people's messages and attached files returned as untrusted blocks (see Act as me). Beside them, `save_my_email_attachment` copies one attached file, when the speaker asked in their own words, into a fixed folder of the Executive's own Drive or OneDrive and shares it with them alone, every call built in codeOne tool writes under someone else's name, and it is fenced in code rather than the prompt. `ghostwrite_email` (**Act as me**, `orchestrator.delegation_tools`) writes an email as the person the Executive is speaking with and saves it as a draft in their own mailbox, Gmail or Outlook (`delegation.gmail.gmail_for` picks the client by the person's credential); chat never sends it (the person sends it themselves, or taps Send on its card). It lives in its own registry, never `_ALL_SKILL_TOOLS`, so reflection, research and workflow toolkits can never carry it. The chat loop adds it only on a turn `delegation.settings.pin_turn_delegation` offered it to — the principal, or a team member once the owner lets them, with it on, verified, in a conversation private to them (the web chat, a Slack or Discord DM, a verified private Telegram chat), on an attended turn — and builds that turn's handler map from both registries, so on any other turn a call to it is an unknown tool. From the round that calls it until the turn ends, the dispatch guard refuses only what opens an outside address, runs a script or workflow, or posts to everyone (`delegation.lockdown`), without changing the offered list; messages and invites to the roster, follow-ups, facts in the person's own words and a contact they name still run, each fenced in its own path. A later turn in the conversation stays private to its owner but holds nothing: the person asking again, having read the reply, is their own request. A contact add the lockdown refuses becomes an approval card in the chat instead (`propose_actions`). Recipients are chosen in code, never by the model (a draft's new email may go to any address, named back to check when it is neither on the roster nor typed), and the text comes from the **ghostwriter** (`delegation.ghostwriter`), a tool-less call with a constant prompt plus the person's \"How I write\" profile. The ghostwriter is deliberately not a Council agent: the Council's edit routes have no principal check. See **Act as Me (Delegation)**. A second tool joins the same way: `recall_history` (`orchestrator.history_tools`, Always in the loop) reads the speaker's own notes of what they said, by email or in chat. It has its own registry and per-turn handler map too, and the loop adds it only when `history_tools.recall_person` finds the speaker verified, in a conversation private to them, on an interactive turn that isn't private to the principal, with their notes switch on. It doesn't need Act as me. After every chat turn the Executive also hands the speaker's own words to `history_chat.schedule_chat_notes`, which takes notes in the background when their switch is on and the surface verified them (see **Memory**). A meeting `create_calendar_event` proposes works the same way when the person chatting is the one who approves it: its chip carries the `decision_id` and the chat shows the meeting card (Approve, Edit, Dismiss) under the reply, while the briefing keeps it too. A tool result held for someone else's approval (`waiting_for_approval`, the department gate) gets a *Waiting for approval* chip, never a done one.\n\nThe Executive can also launch *any* workflow conversationally: `orchestrator.workflow_run_tools` adds `list_workflows` (the launchable catalog with each workflow's inputs) and `run_workflow` (runs a built-in or custom workflow to completion and returns its artifact, checkpointing approval gates as `awaiting_human`). `run_workflow` runs the weekly review, and in solo mode the morning brief, only for the principal on a verified surface (`Workflow.principal_only_modes`, `create_goal`'s rule); anyone else gets an audited refusal that does not name the rule. A run whose `result` event reports `private_to_principal` (the morning brief on the principal's own verified turn, when it read their private rows) still returns its artifact into that turn, but the stored run keeps `persistence.PRIVATE_RUN_ARTIFACT` instead of the text, since run history is readable by everyone signed in. This makes the `/jobs` catalog reachable from chat — see the Workflows section.\n\nDeliverables are first-class too. `orchestrator.artifact_tools` gives the Executive three tools: `draft_artifact` publishes a memo, web page (`html`), Word document (`docx`), spreadsheet (`xlsx`, from structured `sheets`) or a `link` to something it created in one of the principal's connected apps through the generic MCP gateway (`search_tools` → `call_tool`, any server — no vendor is named), and returns the artifact's id and link; `list_artifacts` and `get_artifact` let it find and reread its own past work (drafts and workflow outputs alike, through the same `artifact_records` read model the API uses). Every artifact belongs to someone: a draft to the person whose turn published it (`artifact_records.current_viewer`; with nobody speaking, the scheduler or the CLI, the principal), and a run someone started by hand to them, while scheduled runs are the team's. The tools, the recall, `message_person`'s link and mail attachments only ever reach the speaker's own (a link is refused when the recipient couldn't open it), not even the principal sees a teammate's, and a speaker who isn't on the People list publishes nothing. A workflow's own session inside someone's turn (the research synthesis) is pinned to that turn's viewer (`Session.documents_viewer`). Revising is `draft_artifact(supersedes=<id>)`, which archives the earlier version. When the principal asks for a deliverable the tool is always used; the \"quiet is the right default\" bar applies only to unprompted drafts. The format enum is a hard-coded sorted tuple so the cached tool schema stays byte-stable. Delivery: `message_person(person_id, text, artifact_id?)` appends the artifact's title and a `UI_BASE_URL/artifacts/<id>` link (through the same outbound guard as any DM; the link needs Open Executive access), and a Gmail send/draft can attach the file itself by `artifact_id` — see Integrations.\n\n**Extensions** (`orchestrator.extensions`). An install can add chat tools and kinds of document without changing this code. `OPENEXECUTIVE_EXTENSIONS` names Python modules. The first turn, or the first Documents read, imports each one and calls its `register()`. A module that fails is logged and skipped. `register_tool` takes an `ExtraTool`: a definition, an async handler, an optional `tool_groups` group (new or existing) and an optional chip. It refuses a name the loop already knows (`executive.builtin_tool_names`). An extension tool is never in `_ALL_SKILL_TOOLS`, so reflection, research and the synthesis never see it. The chat loop adds it per turn, like the Act as me tools, but never on an unattended run, a turn private to the principal or to a speaker who isn't on the People list (mail from a stranger), and only where its own `offered(session)` says. That predicate depends only on the kind of turn, so each kind of turn keeps one cached tool list. Act as me's lockdown refuses it once the turn has read the owner's mail, because it is unclassified and the lockdown fails closed, unless it was registered with `after_mail_read=True`: a tool that only reads the install's own data and carries nothing the model wrote anywhere outside. Its chip goes through `action_chips.summarize_action`, which applies the same no-chip rules for an error or refusal and keeps a link to a path inside the app. `register_collection` adds a kind of document: a drafted artifact tagged `collection:<name>` carries that collection on its record. The Documents page gives each collection its own filter. The collection's `on_change` hears about archive, restore and delete before they happen; if it raises, the change does not happen. `draft_artifact(supersedes=…)` refuses a collection's document. The alert pipeline strips `collection:` tags, so only the extension's own code files a document in its collection. A module that fails partway through `register()` leaves nothing registered. A tool registered with `workflow=True` is also offered to workflow action steps as `oe__<name>` (see Workflows); `read_only=True` marks one that only reads. A step runs with nobody in the turn, so `offered` isn't asked: `extensions.in_workflow_step(name)` is True for that tool, during its call only, and the handler decides what an unattended call may do.\n\nDocuments come in the other way through `read_document` (`orchestrator.document_tools`): it reads a PDF, Word, Excel, CSV, Markdown or text file by `path` — one another tool saved, such as a Gmail attachment (`get_gmail_attachment_content`) or a Drive file (`get_drive_file_download_url`) — or a company document by `filename`, with an optional PDF `pages` range. A scanned PDF is converted (`knowledge.pdf_reader`: local OCR by default; with `PDF_PROVIDER_READING=true`, the deployment's own model through its provider's PDF support, falling back to local OCR) rather than returned empty. Reads are confined to the tool download folders — the same resolve-then-contain check as `oe__read_file` — plus the company docs folder, and it is withheld on turns private to the principal (`PRIVATE_TURN_WITHHELD_TOOLS`): those come from a contact's email, whose own attachments the poller has already read into the turn, and must not steer the Executive into company documents.\n\nThe Executive also backs the **Ask OE** panel's form-fill tier via `orchestrator.form_tools.propose_form_values`: when a chat turn arrives with a `<page_context>` block describing a form on the user's screen, the Executive can propose values for it. The proposal is delivered to the UI as a `form_patch` SSE event and placed into the form as highlighted suggestions — the tool never saves or submits anything; the user reviews and saves manually. The tool is **always** in the tool list (tool definitions sit at the top of the cached prompt prefix, so a conditionally-present tool would invalidate the prompt cache whenever panel and non-panel turns alternate); its description restricts usage to turns that carry a form descriptor. For questions about the product itself, the always-offered `read_user_guide` tool (`orchestrator/guide_tools.py`) returns any `guide/prebuilt/<id>.json` section; its description lists the section ids, fixed at import, so it never changes the cached tools prefix.\n\n**Take the lead** (`orchestrator.take_the_lead`) is how the Executive acts on its own, behind one gate. It has two switches, both off until someone turns them on. **As the Executive** is the principal's alone (`PUT /take-the-lead`). With it on, the unattended passes (reflection, research, the scheduler's proactive trigger) keep the acting tools solo mode otherwise withholds from them: booking, starting workflows, and messaging teammates rather than only the principal. `schedule_tools.unattended_toolkit` and the chat loop's unattended path then wrap every acting tool (`ACTING_TOOLS`, plus any MCP tool whose name sends, creates, updates, deletes or shares) in `gated_handlers` / `gated_call_tool`. The principal-only tools (`UNATTENDED_WITHHELD_TOOLS`) stay withheld, and every guard inside a handler still applies, including department approval levels (a booking in a department on Proposes is still a proposal) and the contact-egress rule. New mail or chat (any turn with an `origin_channel`) wakes the existing reflection early (`take_the_lead.wake`): one run waiting at most, five minutes after the first message and no more than every 30 minutes, as a one-off `take_the_lead_wake` scheduled action. Pause holds it like any scheduled work. **As you** is the Handle it for me dial's top step (delegation section).\n\n**The gate** is plain code (`take_the_lead.check`). Six kinds of action wait for a yes first, each with an Ask first switch, all on to start. The switch is the decision ledger's own mode for the class `take_the_lead_action:<kind>` (`propose` asks first, the default; `auto_execute` doesn't). The kinds are money, contracts and legal, hiring and people decisions, deleting/cancelling/sharing, someone new (an address on neither the roster nor the contacts) and big sends (a broadcast or department message, or more than five people). On top of these, the company (set by the principal) and each person (for their own As you) add structured rules: a person or address, a domain, words, or an amount at or above a figure. Added rules always hold, and an error reading them holds the action. The one thing the gate lets straight through is a direct message (`message_person` or a Slack, Telegram or Discord DM) whose only recipient is the principal (`_only_to_principal`): they are who it would wait for, so a card would only ask them to approve a message to themselves. Anything that reaches or acts on anyone else is checked, and a roster that can't be read is not the principal. A held action becomes a `take_the_lead_action` decision instance with a companion `DECISION_ALERT_SOURCE` card on Today, routed to the first teammate holding one of its People approval ranges (`take_the_lead.approval_ranges`, plain code, closest fit first: money to `spend_lt_2k`, `spend_lt_10k` or `spend_gt_10k` by its largest amount, with a higher range able to approve a lower one and no amount read as large, or to `customer_credit` for credit and payment terms; vendor contracts to `vendor_onboarding` then `legal_sign`, other contracts to `legal_sign`; hiring to `hiring_signoff`; anything else about the board or investors to `board_comms`; in Personal as in team mode), or else the principal through the authority gate's fallback (`departments.authority._route_proposal`). Deletes and shares always go to the principal. Only the principal and that approver see or resolve it (`DecisionClassSpec.principal_and_approver`). Approving it claims the row and carries out the exact call once (`take_the_lead.carry_out`: the unwrapped handler, or the gateway's `call_tool`, on an unattended session, with contact egress only when the principal approves). Declining drops it. Everything done or held is a row in `take_the_lead_log`. What it did and what was approved show in Recent activity (`today._build_activity`, kind `took_the_lead`), named but never quoted, since that feed is the team's. The held card's own `decision_resolved` row is left out because its payload quotes the message. `GET /today/activity` also adds the caller's own Handle it sends (kind `sent_as_you`, actor `you`), which are never in the shared feed.\n\n**In training.** The As the Executive switch has three positions: Off, **In training** and On (`take_the_lead.training`). In training, an action the gate would let through still waits, as a `training` hold for the principal alone, unless the principal has allowed that action with that person or thing (`take_the_lead.allowance`: \"Message Priya Nair\" covers a message to her on any channel; \"Book meetings with Priya Nair and Sam Lee\" meetings with exactly them; a workflow by id; a connected tool by name and the file it names, never one that reaches people such as a mail send or a share). The card carries Approve, **Approve + allow**, **Edit** (the message, a meeting's title, times or description, a task and its due date: `take_the_lead.apply_edits`) and Decline. Allowing is the principal's alone and needs a request the API can tie to them, as turning it on does; the six kinds and the added rules hold whatever is allowed. An edit approved with \"Do it like this next time\" is kept as an example (only the edited text, the principal's own words), and `take_the_lead.learned_note` hands the examples and the fact it's in training to the reflection and research passes in their user turn. After `SUGGEST_AFTER` (3) unchanged approvals of the same action in 30 days, Settings suggests allowing it. What it's learned is one list keyed by feature (`take_the_lead_allowed.feature`), so other features that learn from approvals can join it; each keeps its own switch. Act as me is the second (`act_as_me`, per person, `delegation.training`), with a training switch per setting (Replies, Follow-ups, Suggested actions, Drafts): its rows carry the person's id and the setting in their key, are listed and removed by that person alone, count toward their own cap, and never reach `learned_note`.\n\n**AI disclosure.** Nothing the Executive sends to people outside the web chat goes without saying it is an AI: plain code adds the line in the MCP gateway (mail) and at each chat send (Slack, Telegram, Discord, Google Chat replies, its DMs and room posts), never the prompt, so the persona and the cached system blocks are unchanged and a reply the model writes can't drop it. Replies the inbox watcher writes as a person carry their own line by that person's switches. See Integrations → **AI disclosure** and Act as me → **AI line on replies**.\n","mermaid": "flowchart TD\n User([User message]) --> Exec[\"Executive<br/>orchestrator\"]\n Exec -->|consult_specialist| Cso[\"cso: StrategyAgent\"]\n Exec -->|consult_specialist| Cfo[\"cfo: FinanceAgent\"]\n Exec -->|consult_specialist| Gc[\"gc: LegalAgent\"]\n Exec -->|consult_specialist| More[\"chro / coo / cmo / cpo / sales<br/>board_comms / triage\"]\n Mode{{\"Team or solo<br/>(persona + tools per turn)\"}} --> Exec\n Exec -->|\"ghostwrite_email (Act as me)\"| Gw[\"ghostwriter<br/>(tool-less, not a Council agent)\"]\n Cso --> Claude[\"Claude (Anthropic)\"]\n Cfo --> Claude\n Gc --> Claude\n More --> Claude\n Claude --> Exec\n class User entry\n class Exec compute\n class Mode compute\n class Cso compute\n class Cfo compute\n class Gc compute\n class More compute\n class Claude external\n class Gw compute","generated_at": "2026-10-16T16:18:55.969671+00:00"}diff --git a/packages/core/openexecutive/architecture/prebuilt/delegation.json b/packages/core/openexecutive/architecture/prebuilt/delegation.jsonindex 71fc5844..0c070219 100644--- a/packages/core/openexecutive/architecture/prebuilt/delegation.json+++ b/packages/core/openexecutive/architecture/prebuilt/delegation.json@@ -1,7 +1,7 @@{"section_id": "delegation","title": "Act as Me (Delegation)",- "markdown": "The **delegation** module (`openexecutive.delegation`) is **Act as me**: the one place the Executive writes *as* a person instead of as itself. Everywhere else it has its own Google account and bots and signs as itself. Here — when the person asks, or, with a second switch, for mail in their inbox that needs them — it writes an email in their voice and saves it as a **draft in their own mailbox** — Gmail or Outlook — for them to review and send. The one thing it ever sends is one of those inbox drafts, exactly as it is in their mailbox: when the person taps **Send** on its card, or, with a third switch, **Handle it for me**, on its own when plain-code rules allow it (below); chat never sends. The principal can turn it on for themselves, and so can each team member once the owner lets them. It is off by default, and off changes nothing: the prompts, tool lists and prompt caches are byte-identical to an install without it.\n\n## Who can have it, and when it is offered\n\n`delegation.settings.can_delegate(person)` is the single rule for who may turn it on: the principal (a non-archived team member flagged `is_principal`), and any other non-archived team member — never a contact — once team members may have it (`team_members_enabled`). That takes two things: the install allows it (`DELEGATION_TEAM_MEMBERS`, default off, which offers the owner the switch) and the owner turned on **Let team members use it** (`PUT /delegation/team`, principal only, one row in `delegation_team`). Turning the owner's switch off takes it away from every team member from their next message, and their inbox watchers stop at their next check; their own switches, drafts and cards are kept. Everything is keyed by `person_id`. A person turns it on for themselves (`PUT /delegation`); nobody turns it on for anyone else. The setting is one row per person in `delegation_settings`, and a missing, unreadable or zero row all mean off.\n\nAt the start of every chat turn (`Executive.stream_chat` and the committee path) `pin_turn_delegation(session, speaker_text)` runs next to the workspace-mode pin and records a `TurnDelegation` on the session. `ghostwrite_email` is **offered** only when all of these hold:\n\n- the speaker may have it and turned it on — read fresh every turn, so turning it off applies from the next message;\n- the speaker is on a surface that verified it is them — the principal through `people_tools.is_principal_on_verified_surface`, a team member through `teammate_on_verified_surface` (the web app signed in, their own Slack or Discord, never an email turn) — and a web turn also carried a signed-in caller (`Session.web_caller_signed_in`, set from `x-caller-email`) or runs under local login — a request with no caller header is not a sign-in and never gets it (whoever holds the shared secret is trusted as the UI proxy that stamps that header, as on every principal-only route);\n- the conversation is private to the speaker: the web chat, a Slack or Discord DM, or a verified private Telegram chat — never a shared channel or thread, where the draft's preview or the matching threads would be posted for everyone and other people's messages sit in the model's context;\n- the turn is neither unattended (the scheduler's proactive run) nor private to the principal (the email poller's turns), so inbound text can never reach it. The MCP server, workflows, reflection and research never carry it at all.\n\nThe mailbox connection is deliberately **not** part of the offer: the handler checks it on every call and says how to fix it, so the cached tool prefix never flips when a token lapses. The pin lives in a context variable for the turn's task as well as on the session, so two turns running at once on one session (a second browser tab) each read their own. It also carries the speaker's own words for the turn (a new email may go to an address they just typed — the turn's message joins the history only once the turn ends), a per-turn draft count, and `touched_mail` (see Privacy). `own_words` reads those words back for every own-words check (addresses here, facts and task assignments elsewhere): it first removes the hydrated `<outbound_reply_context>` backstory by its exact, anchored shape, so a look-alike closing tag quoted inside it cannot pass the rest off as the speaker's, then drops other adapter tag blocks, and returns nothing for a message carrying an attachment.\n\n## The tool: `ghostwrite_email`\n\nIt lives in its own registry (`orchestrator.delegation_tools.DELEGATION_TOOLS` / `DELEGATION_TOOL_HANDLERS`), **never** `_ALL_SKILL_TOOLS`, so no other toolkit can carry it. On a turn it is offered to, the agent loop adds it to the pool *before* the sort and builds that turn's handler map from both registries; on any other turn a call to it is an unknown tool. The handler re-checks the pin and the surface anyway, then:\n\n1. **Caps** — at most 5 drafts per turn, and `DELEGATION_MAX_DRAFTS_PER_DAY` (default 50, at most 1000) per person per UTC day, shared with the inbox watcher (`delegation.caps`). It is counted from `delegation_drafts`, one row of ids per draft saved from either place, with a count kept in the process as a floor in case a row was lost. Each slot is taken before the first await — a round's tool calls run concurrently, so otherwise every call in it would pass the caps before any counted — and handed back if nothing was drafted. If the rows can't be read it refuses rather than guess.\n2. **Marks the turn** — sets `TurnDelegation.touched_mail` *before* its first read of the mailbox.\n3. **Checks the mailbox** — `gmail_status` asks Google or Microsoft whose mailbox the credential opens and compares it with the person's People email, on every call: a roster email can change, and a client slot swaps the roster.\n4. **Finds the thread** — by `thread_id` (checked against the mailbox's own id shape), or a Gmail-style search (`find`; on Outlook, words, `from:`, `to:`, `cc:`, `subject:` and `newer_than:` are kept and other Gmail operators dropped). Several matches return `{status: \"choose\", candidates}` (subject, sender and date — no message text) and draft nothing; none returns `not_found`.\n5. **Sets the recipients in code**, never from the model. A reply goes to the last inbound message's `From` — never its `Reply-To` (a different one is flagged `reply_to_ignored`) — with the thread's other recipients only on `reply_all`. A new email or a forward may go to any well-formed address: it is only a draft, waiting in their own mailbox, where they see who it is to before they send it. An address that is neither on the roster (contacts only when `contacts_reachable_now()`) nor typed by the speaker this turn comes back in `not_in_people`, and the Executive names it for them to check (`delegation_tools.not_in_people`). Mailing-list mail, a thread they replied to last and a reply-all trimmed to 10 recipients are flagged. An address inside a block an adapter added to their message (the backstory hydrated into a DM) is not one they typed, and when the message carries an attachment — a document's inlined text, or a note naming the file — none of its addresses count as typed: neither has an end mark, and a filename is chosen by whoever sent the file, so such an address is named back to check.\n6. **Writes it** (the ghostwriter, below) and saves it with the mailbox client's `create_draft` (Gmail: threaded with `In-Reply-To`, `References` (whole message ids: when the chain is too long for one header the oldest after the thread's first go, never the parent) and `threadId`, and stamped `X-OE-Ghostwritten`; Outlook: Graph's `createReply` on the message it answers, then the text and recipients, and a named property marking it).\n\nThe result is `{status: \"drafted\", draft_id, gmail_link, to, cc, subject, preview, flags, open_questions, note}`, plus `not_in_people` and `check_address` when a recipient needs checking. The link (`gmail.mailbox_link`) is built server-side from a fixed prefix — the thread in Gmail, the draft itself in Outlook on the web — and the note tells the model the preview is the person's draft, to be treated as data. The chat shows an action chip — \"Drafted an email as you to … — in your Drafts\" — that opens it, and only a link under `MAILBOX_LINK_PREFIXES` is ever linked. A sincere \"are you an AI?\" in the thread comes back as an open question for the person to answer themselves.\n\n## Reading their mailbox\n\nFive read-only mail tools ride with `ghostwrite_email` in the same registry (`orchestrator.mail_read_tools`), so they are offered, re-checked and fenced exactly as it is: `search_my_email` (a Gmail-style search through the client's `search_threads`, or with no query the threads that reached their inbox in the last few days through `inbox_message_ids` + `get_message`), `read_my_email` (one thread's last 10 messages, each sender's new text only, drafts left out, with the files attached to them listed by message id and index), `read_my_email_attachment` (one of those files as text: PDF, Word, Excel, CSV or text, up to 20 MB, a scanned PDF converted) and `my_email_awaiting_reply` (their own sent mail from the last 14 days, to at most 10 people besides the Executive, that is still the last message in its thread). They change, label, draft and send nothing.\n\nThe fifth, `my_email_read_before`, lists the threads `read_my_email` opened for the same person before, in this conversation or an earlier one, so a later conversation can open the same email again instead of asking them to search for it. It keeps where, never what (`delegation.mail_reads`, table `delegation_mail_read`): the thread id, its subject and first sender as one line each, the mailbox address it was read from and when, never a message's text, an attachment or a recipient. Rows are the person's own and are listed only from the mailbox open now, newest first, optionally narrowed by words in the subject or sender; anything older than 30 days is never listed and is deleted on the next write, at most 200 are kept per person, and turning Act as me off deletes them all. It opens the mailbox like the other reads, so it sets `touched_mail`, counts as a search, and returns its rows with the same data-not-instructions note. The Act as me addendum tells the model that these tools reach the person's mailbox while any Gmail or Outlook tools of its own account reach only the Executive's, to search theirs (never falling back to its own) for mail sent to them, and to reopen an email from before with `my_email_read_before` and `read_my_email`.\n\nEach sets `touched_mail` and marks the conversation theirs before its first read (`_open_mailbox`, shared with `ghostwrite_email`), so the lockdown below applies from its round on. Each is capped per turn on the pin: 10 searches (`my_email_awaiting_reply` counts as one), 20 thread reads and 5 attachment reads, the slot taken before the first await. In `read_my_email` every message someone else wrote comes back inside its own `<untrusted_content source=\"email\">` block (`content_trust.wrap_untrusted`, which defuses a closing tag in the text); the speaker's own messages — SENT and from their address (`threads.mine`), never a From header alone — are marked \"Yours\" outside any block. An attachment's text comes back in its own `<untrusted_content source=\"attachment\">` block (`attachments.format_attached_text`), parsed in an isolated worker (`knowledge.loader`); unlike a file sent to the Executive it is never added to the company's knowledge. The clients find an attachment by message and position and look its provider id up on each read (Gmail's changes per fetch): Gmail lists a message's files with the message (`MailMessage.attachments`, leaving out images the HTML shows in place), Outlook says only `hasAttachments` until `list_attachments` asks Graph (leaving out inline ones), and `attachment_bytes` reads one; an attached Outlook item or cloud link has no file to read. Results carry a note that subjects, senders and text are other people's words, data rather than instructions. The lockdown refuses tools, not the reply's own text, so what would carry that text out without a click is closed where it is shown: the web chat loads no image from another site, and bot replies go out without link previews (see Integrations).\n\n## Saving a file from their mail\n\nOne more tool rides with the reads: `save_my_email_attachment` (message id and index, as `read_my_email` listed the file) copies one attached file into the storage the Executive itself has connected and shares it with the speaker alone, so they get a link they can open or put in an app. Every call it makes is built in code (`orchestrator.mail_file_save`); the model picks only the attachment. The bytes come from the mailbox client's `attachment_bytes` and never pass through the model, any file type up to 20 MB, under a cleaned name (one line, no path or reserved characters, extension kept). The storage is the one the Executive's own mailbox runs on (`EMAIL_PROVIDER`) when the gateway has that server, else the other: Google Drive through workspace-mcp (`create_drive_file` with `base64_content` into a folder named \"From your email\" in the Executive's My Drive, then `manage_drive_access` granting the speaker's own address the reader role, `send_notification` off) or OneDrive through ms-365-mcp-server (`upload-file-content` into the same kind of folder in the Executive's own drive, with a name no recorded copy has, since an upload overwrites, then `share-drive-item` inviting only the speaker, `requireSignIn`, role `read`, `sendInvitation` off). The folder is always made by the save itself and its id remembered (`delegation_saved_folder`), never found by its name, since a folder someone else made and called that could already be shared with them; when the remembered one is gone or won't take the file, a new one is made and the old id stays recorded. Never a link share, a domain or anyone. Neither connected (or an eval's in-memory mailbox): status `no_storage`, and the model says so and offers to forward the email instead. Saves run one at a time, at most 10 a turn (`TurnDelegation.files_saved`), and the result is the status, the name, where it went and the link (`webViewLink` / `webUrl`); the chat chip says only that a file was saved, never the sender's file name.\n\nIt copies only when the speaker asked in their own words this turn: what they typed (`own_words`, no quoted backstory or attached file's text) must hold one of save, saved, upload or OneDrive, or Drive as a place (\"to my Drive\", \"in Drive\", \"Google Drive\"), checked before a slot is spent or the mailbox opened; otherwise it refuses (`not_asked`) and tells the model to ask them. It stays allowed after the turn read mail (`MAIL_TOUCHED_ALLOWED_TOOLS`): its gateway calls are admitted past the lockdown only as the very objects the handler built (`mcp_gateway.code_built_call`, for its seven Drive and OneDrive tools: folder create, file create or upload, the speaker's share, and OneDrive's `list-drives`), so a model's own `call_tool` on that turn is still refused, and every other gateway gate still runs on them (the acting account, URL fetches, sheet formulas, the share gates' roster check, writes kept to the Executive's own drives).\n\nEach copy is recorded before it is shared (`delegation.saved_files`, table `delegation_saved_files`: the person, the storage, the file id, its name and when; never content or the mail it came from), and the folder in `delegation_saved_folder`. The gateway reads that table on every Google Workspace and Microsoft 365 call: on a turn whose speaker is not the file's owner (the owner is the speaker only when Act as me was offered to them, so a shared chat, a workflow or the poller sees none), a call naming a recorded file id, raw or percent-encoded (OneDrive's `download-bytes` path is decoded by Graph), is refused, and a result, filtered against the table as it stands after the call so a copy recorded while a listing ran is caught too, loses each list entry or line naming one, with any id left masked. It matches ids as text, so a result that names such a file without its id (a notification quoting its title) still shows the name, and a copy someone makes is a new file. The folders are guarded harder, on every turn and for every speaker, the owner too: a model call whose arguments name any recorded folder id, or an OneDrive item path through the folder (`root:/From your email/x.pdf:` or `<folder id>:/x.pdf:`), is refused, so nobody can share, move, rename, copy, list or delete the folder from chat, and folder ids are dropped from or masked in every result; only the save's own code-built calls touch it. When a copy is made but its row can't be written, it is not shared, the save reports `failed` and logs an error, and the copy's id is hidden from every turn, the owner's included, for the life of the process. When the table can't be read, the file tools (`_FILE_TOOL_RE`: Drive, folder, file, Docs, Sheets, Slides and presentation tools, attachment bytes) are refused (fail closed) while mail and calendar run. The rows are kept when Act as me is turned off: the copies stay in the Executive's storage, and the rows keep them out of other people's turns.\n\n## Reading their calendar\n\nA third switch under Act as me, **Read my calendar** (`delegation.calendar`, table `delegation_calendar`: one row per person, absent or unreadable meaning off), lets the Executive read the person's own calendar, read-only. It rides on the same per-person sign-in as their mailbox: `calendar.readonly` on Google, `Calendars.Read` on Microsoft, added when they run the connect script with `--calendar` (`scripts/connect-own-gmail.py`, `scripts/connect-own-outlook.py`). Those scopes are optional, so a mail-only sign-in keeps working for mail; the mailbox clients note the scopes the token refresh reports, and `list_events` raises `CalendarNotGranted` before calling the calendar when the scope is missing (or when the calendar answers 403). Only the person turns it on (`PUT /delegation/calendar`), only while Act as me is on and a one-hour read works; a sign-in without the calendar is refused with `calendar_not_granted` and the command to run. Turning Act as me off turns it off. Changes are audited privately (`delegation_calendar_changed`).\n\n`my_calendar` sits with the mailbox reads, offered and fenced the same way: it refuses while the switch is off (before anything is opened), then takes a search slot, opens the mailbox privately (`_open_mailbox`, so `touched_mail` and the lockdown apply: an invite's title is in the words of whoever sent it) and lists the events from `start` (default today) for `days` days (1 to 31) in the workspace time zone, recurring events expanded and cancelled ones left out: title, start, end, all-day, location, organizer, attendees (25 at most) and the person's own answer, each on one line, with a data-not-instructions note. Google's `events.list` on the primary calendar and Graph's `calendarView` (times asked for in UTC) are its only calls; it changes nothing and keeps nothing. The first week's brief also lists today's meetings from it on the principal's own delivery (see Today).\n\n## Forwarding and reminders\n\n`ghostwrite_email` also forwards: with `forward` (a thread id) and `to`, it drafts a forward of the thread's latest message, or of the earlier one `forward_message_id` names (the one with the files, say, when their own reply came after it), `intent` becoming the short note above it (the ghostwriter writes only the note; the forwarded email's subject, someone else's words, is never put in the intent). Recipients follow the new-email rule (`_new_recipients`: the roster, or addresses the speaker typed this turn). Gmail's draft quotes a forward header and the original's own words under the note and attaches the original's files, up to 10 and 20 MB (`FORWARD_MAX_FILES`, `FORWARD_MAX_BYTES`; any left off are flagged `attachments_left_off`); Outlook uses Graph's `createForward`, which keeps the original and its files, with the note as its comment and the body never patched. It is still only a draft.\n\n`remind_me(text, when)` (`orchestrator.reminder_tools`) rides with the same tools and checks, but opens no mailbox, so it never marks or locks a turn (`MAILBOX_TOOL_NAMES` are the ones that do). It stores the text once cleaned — one line, anything a chat app could turn into a link (a URL of any scheme, an address, a domain-like word, a host and port, an IP address) replaced with \"[link]\", at most 300 characters — with its time (stored in UTC) in `delegation_reminders` (5 a turn, 25 waiting, a year ahead, refused when the person has no channel). When it is due the scheduler sends that text to the person alone, as \"Reminder you set on <date>: …\", running nothing (see Scheduler); the Slack and Discord DMs it may go by turn link previews off. The chat chip shows the text as it will be sent. A reminder that comes due in the person's quiet hours or leave (when `OUTBOUND_RESPECT_QUIET_HOURS` is on) waits unclaimed and goes once they end, rather than being suppressed and lost. It is allowed after mail is read and in later turns of that conversation: it reaches only the speaker, as plain text. `schedule_followup`, which runs a turn with tools and is listed to everyone, stays refused there.\n\n## Approval cards\n\nA turn that read someone's mail may not message anyone, invite anyone or change the roster (see the lockdown above), yet what the mail asks for is often right. `propose_actions` (`orchestrator.action_card_tools`) leaves the speaker a card instead: up to five actions, each spelled out exactly as it will happen, done only when they tap Approve. It rides with the other Act as me tools and checks (`_writer`), opens no mailbox, and is allowed after mail is read because it does nothing on the turn.\n\n- **Kinds.** `invite` (a meeting with people on the roster), `message` (a direct message to someone on the roster, as written) and `add_contact` (a new contact; the principal's cards only, since contacts are theirs). A team member's card can't name a contact. Each action is checked when the card is made (`delegation.action_cards.check`) and again when it is carried out, so an archived person or a time that has passed fails that action alone.\n- **Whose.** A card is a `delegation_actions` decision for the speaker, `approver_only` like a reply card: only they see it (`GET /delegation/actions`) or resolve it, a team member's answers 404 to the principal too, and it is never an alert. The same actions still waiting are that card, not a new one. 3 cards a turn, 25 waiting, dropped after 7 days.\n- **Approve.** In the chat, under the reply that left it (the `propose_actions` chip carries the card's `decision_id`, and `ChatActionCards` shows the card while it waits), and on the Briefing's Needs you list, with a box per action. Approve (`POST /decisions/{id}/approve`, `edits.only`) needs the card's person signed in (`verified.caller_refusal`) with Act as me on; the card is claimed first so it runs once, then each ticked action runs as stored with no model call, in an unattended session (the principal's with contact egress) under `rows_for_person`, so every audit row it writes is theirs and nothing reaches the team's activity rail: `message_person` (a direct message or nothing; never its Briefing-alert fallback, which more people read), `create_calendar_event`, or a contact row. Approving also needs the person still allowed Act as me (`can_delegate`) and switched on. An invite is booked straight away when the person approving is the one the meeting gate would ask (`calendar_tools.approved_by`), and otherwise goes to that approver as usual, so a card never widens anyone's authority. Per-action results (`done`, `waiting`, `failed`, `skipped`) are kept on the decision and shown on the card. Dismiss rejects it and does nothing else. With Suggested actions in training the card adds Approve + allow, and a card of actions all allowed is carried out on its own (see In training above).\n- **Channels.** A card can come from any surface Act as me runs on; it is approved in the web app, since the chat apps have no buttons here.\n\n## The ghostwriter\n\n`delegation.ghostwriter.compose` writes the text. The Executive decides *what* to say (`intent`); this call decides *how* the person would say it, and it is deliberately small:\n\n- a constant `GHOSTWRITER_PROMPT` plus the person's voice block as the system prompt;\n- the thread (each message cut to its sender's own words, every line scrubbed, all labelled alike), then the writer's own earlier words in it (`<writer_said>`, from their sent mail only), the intent and the recipients' names in the user turn — no company profile, memory or roster;\n- with Always in the loop on, `<writer_noted>`: what the writer's own notes say they told these same people in earlier Act as me replies (`memory.history_drafts.notes_for_draft`: only notes from mail **every** recipient of the new draft was on, so nothing told to one person reaches another; chat notes name no recipient and never qualify; at most 8, newest first, the person's own words or their correction, with dates). The prompt's rule 6 makes it a consistency check, never content: a draft that contradicts it is still written as the intent says, and the conflict becomes an open question on the card, which only the writer sees. Both the chat tool and the inbox watcher pass it;\n- **no tools** but the forced `compose_reply` return, so text in the thread can ask for anything and there is nothing to do it with.\n\nIt is not a Council agent — the Council's edit routes have no principal check — and runs on `DELEGATION_COMPOSER_MODEL` (default: the default model), logged as `ghostwriter` usage. `lint` then runs in code on what comes back: a link or an email address survives only if it appears in the intent, the signature or the recipients, so a link planted in the thread is removed and flagged; the Executive's own name is flagged; and the body is capped, cut at a paragraph, line or word break in its last fifth. A draft with nothing left after that is refused. The signature from the person's Gmail settings (or the one already stored, for Outlook) is appended.\n\n## How I write\n\n`delegation.voice` learns how a person writes *their own* email (`attunement.style` learns how the Executive should write *to* someone). `POST /delegation/voice/learn` reads up to 40 recent sent messages, keeps only what they wrote (quoted replies stripped with the email poller's `sender_new_text`), skips automatic mail, every thread chat drafted into, and every sent message that began as a draft written for them (`delegation_drafts.sent_message_id`), and makes one forced-tool call (`record_voice_profile`). Code validates every field before it is stored:\n\n- greetings per audience (their team, their contacts, anyone else), a sign-off of at most two lines, and a usual length and tone (a backslash-n the model wrote instead of a line break is read as one, keeping the first lines that fit, which also repairs a profile stored before that rule);\n- up to 8 habits and 6 things to avoid, through the same deny-list as working-style rules — no actions, links, handles, amounts, tool names or names of people; the conversation review (`memory.chat_review`) adds one when the person states how they write in a chat (`add_conversation_rule`, `updated_by=conversation`; never on a locked or full list, and an edit or lock made meanwhile wins);\n- up to 3 short exemplars, each checked to be verbatim from a sample, with addresses and phone numbers masked — and none while a client slot is active, so one client's mail never lands in another's state.\n\nThe signature comes from Gmail's `sendAs` settings, not the model (Outlook gives apps no way to read one, so a learn keeps the stored signature and `POST /delegation/voice/signature` answers 409 `signature_unavailable` rather than clearing it), as plain text with its lines kept (`gmail.html_to_text`: a `<br>` always ends a line, and a block tag, opening or closing, ends one when it has text, so Gmail's layout of a first line followed by one `<div>` per line comes out line by line). `POST /delegation/voice/signature` reads it again without relearning: nothing else changes and a locked profile stays locked, so it picks up a changed Gmail signature and undoes **Don't add my signature**. A person can also describe their style in their own words: `POST /delegation/voice/describe` applies the description to the profile they have through the same forced tool (a separate system prompt, no exemplars) and the same validation, keeps their signature and writing examples, and returns the result with a short sample reply for them to review. It saves nothing and needs no mailbox; Save stores it as an ordinary edit. The person can edit the profile, lock it (a locked profile is never relearned) and reset it, and every change is kept in `delegation_voice_history`. One learn runs at a time per person, and a lock or an edit made while it runs wins: the learned profile is dropped (`changed`).\n\n## Draft replies to my inbox\n\nA second switch under Act as me, **Draft replies to my inbox** (`delegation.inbox`), has the Executive watch the person's own inbox and write a first reply to mail that needs them. The reply waits on a private card on Today; nothing is sent until they tap **Send** (below). Where the reply lives is the person's choice, **Also save replies in my Gmail Drafts** (`mailbox_drafts`, off by default): off, it lives on the card alone (`delegation.card_drafts`: the card keeps the draft's recipients, subject and thread headers as `draft_spec`, and Send makes the mailbox draft from exactly that just before the send-time checks, taking it back out if they refuse), so their Drafts folder doesn't fill with replies they may never send; on, it is also saved in their Drafts as before. The switch is one row per person in `delegation_inbox_watch`. Turning it on needs Act as me on and their mailbox connected, and sets `watch_since` to now every time, so it never drafts for mail that arrived before; turning Act as me off turns it off too. Off means no mailbox call and no row written, with one exception: a send the person started that the mailbox never confirmed is still followed through until it is settled.\n\n### When it looks\n\nA throttled hook in the scheduler tick (`_maybe_scan_inbox`, after the pause, company-profile and rotation gates) checks each person whose switch is on every `DELEGATION_INBOX_POLL_MINUTES` (default 5). It is not a scheduled action, because those are listed on `/scheduled` for everyone and anyone may cancel them. One scan task runs at a time, one scan per person, and none while a client slot is active. **Check now** on the Settings card runs the same scan. Every row a scan writes is private and the person's own (`audit.rows_for_person`: a team member's rows are hidden from the principal too, see Privacy), and the process log carries counts and codes, never an address or a line of mail. The scan never marks mail read or changes a label.\n\n### What it drafts for\n\nA scan first settles the open cards (below), and stops with `backlog_full` once 25 are waiting, counting the ones it makes. It then lists the inbox since `watch_since` (`inbox_message_ids`) — not chats, not mail from the person, and not the promotions, social, updates or forums tabs (on Outlook: the Focused inbox only) — up to 100 messages, and takes the newest message of each thread that still needs a look, at most 10: settled threads and threads with an open card are passed over first, so a burst of mail, or a pause for a limit or a back-off, never hides older threads for good. `delegation_inbox_messages` is its durable cursor: one row per message (`UNIQUE(person_id, message_id)`) with what happened to it, the reason, how many tries it took, and the draft and card ids. It stores a hash of the sender's address, never the address. A message is skipped, with the reason recorded, when:\n\n- it came before `watch_since`, or more than three days ago;\n- it is from the person or one of their send-as addresses, from the Executive, or one of this module's own drafts;\n- it is automatic — `Auto-Submitted`, a bulk or auto-reply `Precedence`, a bounce, a calendar invite or a no-reply sender — or from a mailing list, or in a Gmail tab, spam or trash;\n- the person is not in To or Cc, or it has more than 10 recipients;\n- the person replied last, or a draft already sits in the thread.\n\nThree kinds are left unrecorded, so a later scan looks again: mail under 10 minutes old (mail the person answers straight away never gets a card), mail in a thread whose card is still open, and mail a daily limit holds back.\n\n### Deciding, then writing\n\nTwo model calls, and code decides between them. The classifier (`delegation.inbox_classifier`) is one forced-tool call, `classify_email`, returning whether the email needs a personal reply, what kind it is and how sure it is. It sees a few one-lined header lines and the sender's own new words (at most 3000 characters, every line scrubbed) inside one `<email>` block marked as data, and it has no other tools, context or memory, so an email can ask for anything and there is nothing to do it with. A reply is drafted only for a question, a request, scheduling, an introduction or a follow-up, and only when the confidence clears a bar that rises the less the sender is known: 0.6 for their team or a contact (the principal's contacts count only for the principal: a team member's mail is weighed by the team and their own sent mail), 0.7 for someone they have written to before (`has_written_to`, a search of their sent mail), 0.85 for a stranger. Pitches, notes of thanks, FYIs, notifications, newsletters and phishing get nothing, and so does any failure. An email that also went to other people is drafted for only when the person is in To and it asks them themselves: the classifier is told their name, whether they are in To or Cc and how many others it went to, and lists the names the email greets or asks by name (`asked_names`). Code matches those against the person's name, whole name parts only (\"Alexis\" never counts for \"Alex\", and a nickname misses, which means no draft), so mail that greets someone else (\"Good morning, Brennan, could you sign ...\") is never theirs, whatever the model makes of it as a whole. When it names nobody, the model's `asked_of_them` decides, false for a question to the group at large. One that only copies them is never drafted for. Either is recorded `not_needed` with the reason `asks_someone_else`. It runs on `DELEGATION_CLASSIFIER_MODEL`, else the routing model. A sender whose address Gmail couldn't authenticate is handled as a stranger whatever the roster says — anyone can put a colleague's or a client's address in From — so they get the stranger's bar, a holding reply and the stranger limits; the card still says who they claim to be, and that the address isn't verified.\n\nThe reply is written by the same ghostwriter, in the person's voice, but from a fixed intent the module builds rather than words the person typed. Because the intent lets it restate the person's own earlier words, which words are theirs is never written inside the thread, where a sender could imitate any marker with a look-alike: every message there is labelled alike, and the person's own words come in a separate `<writer_said>` block after the thread, taken only from mail their own mailbox sent. Nothing inside the thread can close the thread block or open another. The intent: acknowledge the sender; say again only what the person's *own* earlier messages in the thread already said; commit to nothing new — no yes or no, date, time, price, fact or promise — and say they will get back to them; and put every question it could not answer from their words in **open questions**. A stranger always gets a short holding reply. The lint still strips any link or address that isn't the person's own. The reply goes to the sender (never `Reply-To`) and, on a group email, to everyone else it went to as Cc (reply to all, never the person's own addresses or the Executive); a stranger's holding reply goes to the sender alone. The card says when others were on the email, and its `draft_to` lists everyone, which Send checks.\n\nThe order: record the message, classify, reserve a slot in the shared daily limit, write, save the draft in Gmail (from the alias the mail went to, when it went to one) and store its id, then create the card (idempotent on the message) and mark it drafted. Nothing that fails along the way loses the message. A failure that may pass — the classifier or the writer failing, Gmail refusing the draft, a card that couldn't be made (its draft is deleted first, so no draft is left without a card), any other error with that one message — leaves it for a later scan (`retry`), and it is given up on only after three tries; one message's trouble never holds up the rest. A daily limit reached while it was being read leaves it for later without counting as a try.\n\n### The reply cards\n\nA card is a `delegation_reply` decision whose class is **its approver's alone** (`DecisionClassSpec.approver_only`): only the person it was drafted for sees or resolves it on any decisions route — a team member's card answers 404 to the principal too — and it is never an alert: alerts feed chat turns, which would put other people's mail into memory. It carries the sender with who they are to the person and whether Gmail could verify the address (SPF/DKIM/DMARC, through `fact_confirmation.headers_authenticated`), the subject, what they wrote, the draft, the open questions and its warnings. `GET /delegation/replies` lists the open ones from the database alone, so Today never waits on Google.\n\n- **Send** approves the card, which sends its draft exactly as it is in their mailbox (see *Send on your tap*). **Edit** changes the reply's words right on the card (`PUT /delegation/replies/{id}/text`, `card_drafts.edit`): only its own person, from a caller the API can tie to them (as for Send), never while it is being sent on its own; a reply in their Drafts is rewritten there too (`update_draft_text`, every header kept), and only while it is still the version the card last saw, so a change made in the mailbox is never overwritten. A card edit counts as edited (`approved_with_edit`, and **Do it like this next time** keeps it). **Open in Gmail** (or **Open in Outlook**), shown only when the reply is in their Drafts, opens it there.\n- **Dismiss** rejects the card; the class's after-reject step then deletes the draft if nobody edited it — its message id is still the one it was saved with, since Gmail gives an edited draft a new one, and the Outlook client makes a draft's message id `<id>.<changeKey>` so an edit there changes it too — and keeps it otherwise. What happened is recorded even when Gmail fails.\n- Each scan first **settles** what Gmail already settled: a draft sent from Gmail, a draft deleted there, a reply the person wrote themselves, a thread that is gone, or a card left for 7 days (its draft stays in Gmail). Each is a compare-and-set close with the reason. A newer message from someone else flags the card instead. A card being sent at that moment is left alone.\n\n### Send on your tap\n\n`delegation.reply_send` is the only thing in Act as me that sends, and all it can send is the draft on a card, by its id: `DelegateGmail.send_draft` posts `{\"id\": …}` to Gmail's `drafts.send`, and `DelegateOutlook.send_draft` posts an empty body to that draft's Graph `send`, and nothing else, so no text, recipient or header is ever passed. It has two doors: `send_approved_reply`, reached only from `POST /decisions/{id}/approve` — a class only the card's own person may resolve — and `send_on_its_own`, reached only from the inbox watcher under Handle it for me (below). AST tests pin both call sites, so no model, chat turn, workflow, scheduled job or MCP call can. A tap is checked like this: At send time it checks everything again:\n\n1. **Who is asking.** The caller is the card's person and the API knows it: signed callers are on and the request carries that person's signed assertion (or the operator's, under local login), or the API runs for local login and answers this computer only. Anything else is a 409 `caller_signing_required` — with only the shared secret, whoever holds it could send as the owner — so on a server Send needs signed sign-ins.\n2. **The switches.** Act as me and Draft replies to my inbox are on, and no client slot is active.\n3. **The mailbox.** Their mailbox is connected.\n4. **The draft.** It still exists, in the same thread, and they haven't replied there themselves since; otherwise the card closes.\n5. **Who it goes to.** To, Cc and Bcc hold between 1 and 10 addresses, never the Executive's own, and it is from one of their own addresses.\n6. **What changed.** Recipients that differ from the card's, or a newer message from someone else, need a second yes: the first tap gets a 409 `confirm` naming the recipients and the reason, and the person approves again with what they were shown.\n\nThen it claims the card (`claim_for_execution`, proposed → executing, a compare-and-set, so a double tap sends once) and reads the draft once more: `drafts.send` sends whatever the draft is when Gmail gets the request, so if it was edited since the checks read it — in another tab, by a delegate — nothing is sent and the card comes back (`draft_changed`). Then it sends, and records the result: `approved_with_edit` when the draft was edited in Gmail, the sent message's id, the draft row's `sent_message_id`, and a private `delegation_reply_sent` row. A refusal that proves nothing went — a 4xx, a lapsed sign-in, a rate limit, a draft already gone — hands the card back. A failure that leaves it unclear — a timeout, a 5xx — leaves it `executing` and says to check the Sent folder, and the next scans ask Gmail: their message in the thread means it was sent; anything else is judged on the second scan that sees it: the draft still there and nothing sent means it was not (Gmail deletes a draft it sends), and the card comes back, flagged; the draft gone and nothing sent means it was deleted. Nothing is ever retried on its own. Sending is the person's own act, so it works while the Executive is paused.\n\n### Limits and failures\n\nAt most 5 drafts a scan; `DELEGATION_INBOX_MAX_DRAFTS_PER_DAY` (default 20) a day, inside the shared `DELEGATION_MAX_DRAFTS_PER_DAY` it shares with chat; 200 classifications, 2 drafts per sender (1 for a stranger) and 10 for strangers in all per day; and never more than 25 open cards. A lapsed Gmail sign-in sets the status and is looked at again every 30 minutes; a rate limit, an error reaching Gmail or a crash backs off from 5 minutes, doubling up to 2 hours. Neither turns the switch off: the Settings card shows the status in plain words.\n\n## Handle it for me\n\nA third switch under Act as me, **Handle it for me** (`delegation.handle_it`), lets the inbox watcher send some of its replies itself instead of leaving them on a card. It is one row per person in `delegation_handle_it` (`enabled`, `mode`); no row means off. One setting says how much goes without them, the way quality does on the Agent Council (`handle_it.RULES`): **Easy ones** (`careful`) sends only replies to people they know (someone on their team, a contact or someone they have written to) of at most 400 characters when the classifier is at least 0.9 sure; **People I know** (`balanced`), where it starts, sends replies to people they know up to 1200 characters at 0.8; **Most mail** (`bold`) also answers strangers, up to 2000 characters, and lets a link or an amount through when the classifier is at least 0.9 sure. Everything else waits on a card as before, so turning it on never drafts less. A table from before the setting gets the `mode` column on its next open (`schema._add_handle_it_mode`): someone who had strangers set to send keeps that as Bold, everyone else gets Balanced. Only the person turns it on (`PUT /delegation/handle-it`), from a session the API knows is theirs: the same rule Send uses (`delegation.verified.caller_refusal`), so with only the shared secret it answers 409 `caller_signing_required`. Turning it on needs Act as me and Draft replies to my inbox on, and turning the inbox watcher off (or Act as me, which turns it off) turns it off too.\n\n**In training** (`delegation.training`). Like someone new, each Act as me job can be put in training on its own, from that job's card on the Act as me page, the way Take the lead has it: **Write drafts as me** and **Handle it for me** each pick Off / In training / On (Handle it's In training is Replies in training, with a *Train follow-ups too* box for Follow-ups), and **Suggested actions** picks Always ask / In training; what it learned is listed on each tab for its own jobs (Act as me: *What it's learned*, drafts and suggested actions; Handle it for me: *Who it's allowed to handle*, replies and follow-ups), each item named by its job (`PUT /delegation/training`, one row per person and setting in `delegation_training`, absent means not in training). In training it asks first and learns who and how from what the person approves; what it learns is a `take_the_lead_allowed` row (feature `act_as_me`, the person's id), theirs alone.\n\n- **Replies.** Every reply waits on its card (`handle_it_reason` `training`) whatever the dial says, and a reply card adds **Send + allow**: it sends that reply on the person's own tap, exactly as Send does, then allows replies to that sender (key `act_as_me|person:<id>|reply|<address>`). While Handle it for me is on, a reply to an allowed sender goes on its own under the dial's limits (a stranger they allowed included) and every check above (the topics that always wait, links and amounts, new recipients, once a thread a day, the daily limit); it's checked again at send time, so a sender removed since waits. Take the lead as you lifts nothing in training: putting Replies or Follow-ups in training turns it off, and it can't be turned on while they are (409 `in_training`).\n- **Follow-ups.** Every follow-up waits (`follow_up_training`); Send + allow on a follow-up card allows follow-ups to exactly the people it went to (`…|follow_up|<sorted addresses>`), whoever they are, under every other follow-up check.\n- **Suggested actions.** An action card (below) adds **Approve + allow**: it does the actions on the tap, then allows each one that happened (a message to that person, `…|message|person:<id>`; a meeting with exactly those people, the person left out, `…|invite|people:<ids>`). A new contact is never allowed. A card proposed later whose every action is allowed is carried out at once, with no tap (`action_cards.run_on_its_own`, `gate_mode` `auto_execute`, status `executed`), only if plain code finds nothing against it (`on_its_own_refusal`): still in training, Act as me on, a server that ties the switch to the person, nothing sensitive, no link or amount, a message of at most 1200 characters, and at most 10 actions carried out this way a day (checked one card at a time); anything refused is handed back to wait on its card as before. An invite carried out this way is never booked as approved by the person: the meeting gate decides as for any meeting nobody tapped, so a time taken from someone's mail can't land on a calendar unasked. The tool result and chip say what was done. The message text in such an action is model-written from the mail and goes without anyone reading it; the allowance covers who and what kind, not the words, which is why sensitive topics, links, amounts and long messages are held back.\n- **Drafts.** Nothing is sent. When the person changes a reply's draft in their mailbox before tapping Send (plain or + allow) and ticks **Do it like this next time**, what they sent is kept (its new text, quoted replies dropped, at most 1000 characters, `…|style|<address>`), and the ghostwriter gets it in its user turn as `<writer_example>` when it next writes to that person, from the inbox, a follow-up or a chat draft to that one person: style only, never its facts, and nothing in it can open or close a tag.\n\nSend + allow and Approve + allow are refused before anything is done unless their setting is in training (422 `cant_allow`) and the person's list has room (409 `learned_full`, at most 200 a person); allowing failing afterwards never undoes the send. Putting Replies or Follow-ups in, or Suggested actions out, of training only holds more back and works without signed sign-ins; anything else needs a caller the API knows is that person. What it learned is the person's alone: listed on `GET /delegation` (`training.learned`, each with its `setting`), removed with `DELETE /delegation/learned/{id}`, and for the owner also in Take the lead's \"What it's learned\" list; it never reaches anyone else's list or Take the lead's prompts. A dial left on In training by an older version (mode `training`) moves to People I know with Replies and Follow-ups in training (`schema._move_training_off_the_dial`).\n\n**No model decides whether a reply goes.** The watcher's two model calls are unchanged and tool-less, so text in an email can at most change the verdict and the draft. After the draft is written, `handle_it.refusal` — plain code — decides, and anything it refuses becomes the usual card with the reason kept on it (`handle_it_reason`). It refuses when:\n\n- it's off, or the sender is a stranger and the setting isn't Bold, or on a server signed sign-ins are off (`signing_ok`: signed callers, or local login);\n- Gmail couldn't authenticate the sender, whatever the roster says;\n- the email isn't a question, request, scheduling, introduction or follow-up, or the classifier was less sure than the setting needs (0.9 on Easy ones, 0.8 otherwise);\n- the reply goes to anyone the email didn't already go to (its From, To and Cc, less the person's own and the Executive's addresses), leaves out the sender, or goes to more than 10;\n- the email's subject, the sender's new words, or the reply touch money, contracts, legal, hiring, pay, layoffs, the board, investors, mergers, the press, health, or credentials and secrets (passwords, logins, tokens, API keys); or the reply carries an amount, a percentage or a link (a scheme, `www.`, a bare host with a path such as `bit.ly/…`, or a bare host on a common top-level domain) unless it's Bold and at least 0.9 sure, or runs over the setting's length (400, 1200 or 2000 characters);\n- the draft carries any flag but *others on the thread* or *Executive on the thread* (they asked if it's an AI, recipients were trimmed, …);\n- it already sent one in this thread in the last day, or the person's last message in the thread was itself sent on its own (no auto-reply ping-pong);\n- the day's limit is reached (`DELEGATION_HANDLE_IT_MAX_SENDS_PER_DAY`, default 20, within the watcher's drafts limit), or it can't be counted. Any error in the rules counts as a refusal.\n\nA reply the rules allow gets a card with `gate_mode` `auto_execute`, and the watcher sends it at once through `reply_send.send_on_its_own`, the second and last door into the send path (an AST test pins both callers: the approve route and the watcher). It runs the same send-time checks as a tap — switches, mailbox, draft, recipients, the claim and the last re-read — with no caller, and adds its own: the card must be `auto_execute`, Handle it for me still on with the setting still allowing that sender (or, for a follow-up, that recipient), signing still on, the once-a-thread-a-day rule and the daily limit counted again, and the draft untouched since it was saved (an edit in Gmail means the person has taken it over: `draft_changed`, the card waits for them). Every refusal hands the card back to the person (`decision_ledger.hand_back`, a compare-and-set to `propose`), with the reason kept on it when there are words for it, and a failure never stops the scan. Every card it left for the person says why on Today (`waited_because` on `GET /delegation/replies`). A reply sent on its own finishes as `executed` (not approved), is recorded in `delegation_handled` (for the per-thread and daily rules) and writes a private `delegation_reply_handled` row; an unconfirmed one is settled by the reconciler the same way. No History note is taken from it, since notes come only from the person's own words. It runs inside the watcher's scan, so it stops while the Executive is paused.\n\n**Follow-ups as you** (`delegation.follow_ups`). While Handle it for me is on, the watcher's scan also looks at the person's own sent mail, at most once an hour (`LOOK_EVERY`), for an email of theirs that asked something (a question mark in their own words), is 3 to 10 days old, went to at most 10 people other than the Executive, and is still the last message in its thread. Plain code picks it; each gets one follow-up ever (its `delegation_inbox_messages` row), at most two a look, within the drafts limit. The ghostwriter, tool-less as always, writes a short nudge in their voice from the thread, saved as a draft in that thread to exactly the people the email went to. `handle_it.follow_up_refusal` — plain code — decides whether it goes: by the setting it never goes on Easy ones, goes to their team and contacts on People I know and to anyone they wrote to on Most mail (`follow_up_refused` otherwise: `follow_up_level`); it also refuses on any change of recipients, a sensitive topic, an amount or a link, more than 600 characters, a flag, and the same per-thread and daily counts as replies. It goes through `send_on_its_own` on an ordinary `delegation_reply` card marked `source: follow_up`, which rechecks the setting for that recipient. A refused one waits on Today as **Follow-up waiting**, and closes by itself (its untouched draft deleted) when anyone answers in the thread first.\n\n**What it sent** is the person's alone: `GET /delegation/handled` lists the last 7 days (who, subject, the reply, the questions it left them and a link to the thread in their mailbox), and the Handle it for me tab shows it with how many went today, under its picker.\n\n### Take the lead as you\n\nOn Settings → Act as me, Handle it for me is one dial: **Off**, **Easy ones**, **People I know**, **Most mail** and, for the owner, **Everything**, which uses **Take the lead** (`PUT /delegation/take-the-lead`, one row `person:<id>` in `take_the_lead`; turning it on turns Handle it for me on). While it is on, `handle_it.refusal` drops the setting's limits: strangers, the classifier's confidence, amounts, and the length up to a 4000-character ceiling. A reply with a link still waits for a tap (refusal `link`). In their place it checks the company's and the person's own added rules (`take_the_lead.reply_hit`, refusal `lead_rule`). Everything Handle it always keeps still holds: signed sign-ins, an authenticated sender, a reply kind, exactly the thread's people, the topics that always wait, draft flags, never twice in a row, one a thread a day and the daily limit. Follow-ups under it may go to anyone the person wrote to, with the same sensitive, amount, link and length checks plus the added rules. `reply_send.send_on_its_own` accepts the card while both switches are on. Each person adds and removes their own rules (`/delegation/take-the-lead/rules`). Removing one needs a caller the API can tie to them.\n\n\n## AI line on replies\n\nReplies written as a person can end with **\"Drafted and sent by my AI assistant.\"** (`delegation.disclosure.LINE`), by two switches that are each person's own (`PUT /delegation/disclosure`, one row per person in `delegation_disclosure`, NULL following the install): **Handle it**, on by default (`AI_DISCLOSURE_HANDLE_IT`), for a reply Handle it for me will send on its own, which nobody reads before it goes; and **Approved sends**, off by default (`AI_DISCLOSURE_APPROVED_SENDS`), for one that waits on a card for them to send, since they read it first. The line is written into the reply when it is drafted (`disclosure.sign`, in `inbox._consider` and `follow_ups`), once the plain-code checks have decided whether it goes on its own, so the card, the mailbox draft and what is sent are the same words and Send's draft-changed checks see them; a switch changed later applies to the next reply, and a reply drafted to go on its own that is handed back keeps its line for the person to edit. `AI_DISCLOSURE` off turns both off and hides the card. Turning a switch on only adds the line, so it needs no signed sign-in; turning one off does. Each tab shows its own switch under Advanced (**AI line on drafts you send** on Act as me, **AI line on replies it sends** on Handle it for me), and turning off the Handle it line asks first.\n\n## The mailbox client\n\n`delegation.gmail.DelegateGmail` talks to the Gmail REST API directly and is **never registered with the MCP gateway**, so the model reaches the mailbox only through the typed handler. The credential is one file per person in `DELEGATION_GOOGLE_CREDENTIALS_DIR`, named from a hash of the address (0600 in a 0700 directory), minted by `scripts/connect-own-gmail.py` on the Executive's own OAuth client with the scopes `gmail.readonly` and `gmail.compose`. It never lives in `WORKSPACE_MCP_CREDENTIALS_DIR`, where workspace-mcp picks a credential by address. Besides reading threads and saving drafts it lists the inbox and checks whether they have written to an address, reads one message or draft, lists the person's send-as addresses and deletes a draft. Its **one send method**, `send_draft`, sends an existing draft by its id and nothing else — never `messages.send`, which sends any text it is given — and unit tests pin the method set, the endpoint, the request body and its single caller. A failed request says whether it may have been carried out anyway (a timeout after connecting, a 5xx), which is what the send path needs to know. A parsed message carries when it arrived, whether it is bulk, a bounce or a calendar invite, and whether Gmail's authentication results vouch for its sender.\n\n`gmail_status` answers `connected`, `not_configured`, `needs_reconnect` (Google refused the saved sign-in — an app in Testing mode has its tokens expire after 7 days; a rate limit, though Gmail may send it as a 403, is an `error` to retry, not a reconnect), `mismatch`, `no_email`, `shared_mailbox` or `error`. `shared_mailbox` means the person's address *is* the Executive's; it is refused before asking Google, because then everything the Executive writes would look like theirs. The gateway closes the other door: every `google_workspace__*` call must act as the Executive's own account, and a `user_google_email` naming anyone else is refused and audited (see Integrations).\n\n### Outlook\n\nA person may connect an Outlook mailbox instead (work, school or personal), with `scripts/connect-own-outlook.py`: a device-code sign-in on the Executive's own Entra app (`MS365_MCP_CLIENT_ID`, tenant `MS365_MCP_TENANT_ID` or `common`) asking for `User.Read`, `Mail.ReadWrite`, `Mail.Send` and `offline_access`. It writes the same per-person file with `\"provider\": \"microsoft\"`, so a person has one mailbox for Act as me, and `gmail_for` hands back `delegation.outlook.DelegateOutlook`, which keeps `DelegateGmail`'s methods, return types and errors, so every caller above runs unchanged. It talks to Microsoft Graph directly, never through the Microsoft 365 MCP server the Executive's own Outlook uses, and is never registered with the gateway. Microsoft rotates the refresh token on use; the new one is written back into the file (atomically, keeping every other key, and only if the file still holds the old one). Graph is asked for immutable ids, so a sent draft keeps its id; a thread is Outlook's `conversationId`. Gmail's labels are mapped onto what the callers read: `SENT` only for mail in their Sent Items folder (a From line set to their address by someone else never counts), `DRAFT`, `INBOX`, and Focused Inbox's Other read as a tab. A sender counts as authenticated only when the topmost `Authentication-Results` — the one Exchange wrote, above anything the sender added — holds exactly one DMARC verdict, a pass for From's own domain, and Exchange Online Protection's own `compauth=` verdict, so a header the sender wrote on mail EOP never stamped doesn't count. `delete_draft` refuses anything that isn't a draft, and deletes with the draft's etag (`If-Match`), so a draft sent in between — it keeps its id — is left alone. No client secret is ever written into a person's file, and Graph has no signature setting to read.\n\n## Privacy\n\nWhat a person's mailbox touches is theirs. For the principal that means private to the principal, as every private row is. For a team member it means theirs alone, the principal included: an audit row carries `private_to_person` (set by `audit.rows_for_person` around the inbox watcher, a card's Send and Dismiss and their settings changes, and by `people_tools.audit_row_owner` on a turn that read their mail) and is left out of every audit read — the log, a session's timeline, a row by id, the brief — with only the usage totals counting it; their reply cards are theirs alone (above); and the owner's view of their use is counts only (drafts and sends in 30 days, and whether their inbox watcher is on). The conversation itself becomes its owner's alone before the mailbox is first read: `ghostwrite_email` marks the session `mail_private` (`session_store.mark_mail_private`, creating a channel adapter's row early, with its owner) and refuses to read the mailbox if that can't be stored or the conversation already belongs to someone else (which it then leaves unmarked); from then on only its owner may open it (`chat._session_access`), and working-style learning skips it. Every later turn there starts private (`settings.pin_turn_delegation` reads the flag and fails closed, setting `touched_mail`), so a follow-up answered from history alone is still private to its owner and teaches no memory, and the web chat's rows before the turn (the inbound message and the knowledge lookup) are theirs too. It does not start locked down: the lockdown is `read_mail`, set only by a turn that reads the mailbox or notes itself, and it is never carried into the next turn, because history keeps only the speaker's words and the Executive's replies, never the mail a tool returned. Their next message is them asking again, having read that reply, so everything runs again there. Anyone else speaking in it is not offered Act as me.\n\nOnce `touched_mail` is set, every audit row the turn writes is private (`people_tools.audit_row_private_to_principal`), and a team member's is theirs alone: the tool row (its input and result redacted, since `ghostwrite` is a sensitive tool name), the reply's `chat_turn` row that carries the preview, the model-call rows, and the background passes, which run under `private_rows`. The Honcho peer and department syncs are skipped, because peer memory is read on other people's turns. No memory is learned from the turn at all: the episodic, open-loop and working-style passes are skipped too, since its reply quotes a draft built from other people's mail. The `delegation_*` audit events are always private and carry metadata only — ids, counts and flags, never the draft or the thread. The inbox watcher is private the same way: every row a scan or a card action writes is its person's alone, and it starts no chat turn, alert, scheduled action or workflow run and teaches no memory.\n\nThe turn also keeps one door shut (`delegation.lockdown`). Anyone can put text in the inbox, and that text could try to steer the model, so from the round that calls `ghostwrite_email` or one of the mailbox reads — a round's tools run together — until the turn ends, the dispatch guard refuses only what opens the open internet or reaches everyone: outside fetches (`read_document`, research, the watchlist, `load_mcp_server`, and any MCP `call_tool` outside the private-turn set of reads and recipient-checked sends), `run_script` and `run_python_job`, workflows (they run later, unattended, and may fetch or script), broadcasts, department messages and alerts, and changes to who is on the roster or holds authority (`archive_person`, `set_department_head`, `resolve_roster_request`), and text that steers later turns (`schedule_followup`, whose intent runs unattended when due, and goals and decision outcomes, shown to every later turn). Everything else the person asks for runs, because it is fenced on its own: DMs and `message_person` reach only the roster, invites name attendees by person id, the Executive's own email checks every recipient against the roster, standing facts and profile edits keep only the person's own words, and a workflow drafted in chat is saved only once a person confirms it. `upsert_person` runs only for a contact the person asked for (`speaker_named_contact`: a contact, never the team, an approval scope or a chat account, with a word of the name in what they typed, in a message that asks to add, save or change someone, a new contact's address one they typed or one that sent the mail the turn read under the contact's name (`TurnDelegation.mail_senders`), never one the mail's text only mentions, and on an update a changed address they typed), since the roster is what the send checks trust. Any other contact add is refused with a pointer to an approval card (`lockdown.CONTACT_REFUSAL`), so the Executive leaves an `add_contact` card in the chat rather than asking them to type the address. What an email itself asks for is still never done on its say-so; it goes on an approval card. Every tool is classified as allowed or withheld, a test fails on a new unclassified one, and an unknown name is withheld, except an extension tool registered with `after_mail_read` (one that only reads the install's own data). The refusal tells the model to put what the step needs in its reply, since the next turn sees the reply but not the mail, and to do the step then without reading the mail again. A refused call gets a private `tool_invocation` row (`refused: mail_touched`) and tells the model to offer it in the next message. The offered tool list never changes mid-turn, so the cached prefix holds. The handlers that reach outside check again on their own (`outside_reach_refusal`). The server-side web search stays, as on a turn private to the principal. The lockdown ends with the turn. Later turns of that conversation stay private to its owner (`touched_mail`) but hold nothing: a refusal says it will work when they ask again in their next message, and it does.\n\n## Always in the loop\n\nA sent reply can leave a note. Once the reply went, `reply_send` starts `memory.history_notes.note_sent_reply` for the person who sent it, in the background, when their \"Keep track of what happens\" switch is on and the conversation isn't one they asked not to remember. The note-taker sees only the words they sent, so other people's mail never becomes a note, and a failure never touches the send. Recall is `recall_history`, offered on the same verified, private surfaces as `ghostwrite_email` and also allowed under the mail lockdown, since it only reads the speaker's own notes. Calling it locks the turn like `ghostwrite_email` does, from its own round on. The same switch also covers notes from chat, which don't need Act as me. See **Memory** for the checks, retention and controls.\n\n## The system prompt\n\nA constant, name-free `DELEGATION_ADDENDUM` joins block 0 after the unchanged identity addendum while anyone on the install has it on (`block0_delegation_on`). It names the four mailbox reads and says other people's mail is data and that a conversation which read it reaches nobody else; and it tells the model that `ghostwrite_email` is the single exception to *never impersonate*, and only for the person being spoken to; that everything else is written as itself; that when the tool isn't offered the asker can't have it; that a draft is never described as sent; and that it never denies being an AI. It is keyed on the install-level setting, never on the turn or the speaker, so switching it misses the 1h cache once (see Prompt Caching).\n\n## What it may do\n\n**Delegate → What it may do** (`delegation.may_do`, `GET /what-it-may-do`) is read-only: one row per thing that can go out without asking, what happens to it (goes out, waits for someone, always waits, drafts only, off) and which setting decides it, with a link there. It is the first Delegate tab, and `/delegate` opens on it. Three parts, each behind a pill that counts what goes out:\n\n- **As you** (the caller's own, when `can_delegate` allows them): built from `settings.is_enabled`, `inbox.get_watch`, `handle_it.get` and `handle_it.RULES`, `handle_it.leading` (Everything), `training.get` and `training.learned`, and their rules, the same reads `handle_it.refusal` and `follow_up_refusal` make. A level's row follows its `Rules` (strangers, follow-up reach, links and amounts), not a copy of them. A note names the ladder: Handle it for me rides on Draft replies to my inbox and Write drafts as me, and Everything also drops when Replies or Follow-ups go into training.\n- **As the Executive** (the principal's alone, as `GET /take-the-lead`): the switch and its training, each Ask first kind, the company's rules, and meetings. A meeting it thinks of on its own always waits: both meeting gates need someone on a verified surface in the turn, which an unattended run never is. A meeting someone asks for in chat follows **Always asks first → Meetings asked for in chat** (on means it waits: `meeting_scheduling`'s class mode is `propose`; off means `auto_execute`) and, in a team workspace, Operations' level too.\n- **Departments**: each level, and what a level covers (department-scoped scheduled work, check-ins, alert review, team members' chat sends, and Operations' meetings), and that it doesn't cover what the Executive does under Take the lead.\n\nIt also says when the Executive is paused, and when nothing can be sent as anyone because signed sign-ins are off. Nothing on it writes or reads mail. A contact, someone not on People, or a request with no caller (outside local login) gets 403.\n\n## How far it goes as you\n\nOne setting replaces the switches that used to turn each other off out of sight. The UI shows it as two pickers (`ReachCard.tsx`): **What it writes as you** (`WritesCard`) on the Act as me tab and **What it sends on its own** (`SendsCard`) on the Handle it for me tab; What it may do links each row to its own picker. Its steps, each adding to the one before: **Off**, **Drafts when I ask** (Write drafts as me), **Drafts for my inbox** (Draft replies to my inbox), then the Handle it for me steps that send, **Easy ones**, **People I know** and **Most mail** (`careful`, `balanced`, `bold`), and for the owner **Everything** (Take the lead as you). Act as me shows the first three as **Off**, **When I ask** and **For my inbox too** (any sending step reads as For my inbox too there). Handle it for me shows **Off** (saved as the inbox step) and the sending steps, and opens only once Act as me is at For my inbox too, with a button that turns that on; moving Act as me below it says Handle it for me stops too. `PUT /delegation/reach` (`{step}`) moves it, and `reach_of` reads the step back from the switches, so the stored switches stay the source of truth and every gate reads them as before.\n\nGoing down turns the switches above the target off, highest first (`_lead_off`, then Handle it, then the inbox watcher, then Write drafts as me), so nothing is ever on above a switch that's off; the UI says what stops and asks before it saves. A lower sending level only holds more back and is set directly, so it needs no signed sign-in. Going up calls each switch's own route in order, so every check it makes still applies: the mailbox connected, signed sign-ins for sending, the owner alone and not in training for Everything. The first that refuses stops the move at a whole step and answers with that route's error. **In training** (Replies and Follow-ups together, with **Train follow-ups too** to split them) and, at Everything, **Your rules** sit under the Handle it for me picker, and **Learn from my edits** (drafts training) under the Act as me one; neither picker changes training.\n\n## Surfaces\n\n- **Settings → Act as me** (`ActAsMeCard`, hidden unless `GET /delegation` answers, so a team member sees it once the owner lets them): the mailbox connection (`provider` says which) with both connect commands (Gmail and Outlook) and **Check again**, **What it writes as you** (above), with the inbox watcher's status under For my inbox too (in plain words, when it last checked, **Check now** and **Also save inbox replies in my Gmail Drafts**), and **How I write**: length and tone, a greeting per audience (`{first}` is their first name), the sign-off, habits and never-rules in fields that grow to show every line, the signature with **Refresh from Gmail** and **Don't add my signature** (or **Add my Gmail signature** when none is added; on Outlook only **Don't add my signature**, with why), and each example quoted with **Remove examples**. The owner also gets **Let team members use it** where the install allows it, with each team member who has it on listed by name and counts only.\n- **Today → Replies waiting** (`RepliesWaiting`, the top of the left column; hidden unless `GET /delegation/replies` answers with cards): each card shows who wrote and who they are to you, whether their address was verified, the subject, **They wrote** as plain text, your draft, **Decide before sending** (the open questions) and its warnings, with **Send** (a confirm naming who it goes to, and a second one when that or the thread changed), **Edit** (a text box on the card with Save and Cancel), **Open in Gmail** or **Open in Outlook** when the reply is in their Drafts, and **Dismiss**.\n- **Setup status**: a **Your own mailbox (Act as me)** light (`your_gmail`), amber while the inbox watcher can't reach the mailbox, is being rate-limited or has 25 replies waiting.\n- **Delegate** (main menu): **What it may do** (above, where `/delegate` lands), **Act as me** (where `/settings/act-as-me` lands), **Handle it for me** (which step the dial is at, with **Change in Act as me**, then **What it sent**: how many went today and what it sent this week, as you) and **Take the lead** (the switch, then **Always asks first**, shown even while the switch is off and ending in **Meetings asked for in chat**, and the company's rules, as the Executive). Each switch that turns another off says so beside it. The pause is on **Settings → Your Executive**.\n- **API**: `GET`/`PUT /delegation`, `GET`/`PUT`/`DELETE /delegation/voice`, `POST /delegation/voice/learn`, `POST /delegation/voice/describe`, `POST /delegation/voice/signature`, `PUT /delegation/inbox` (`{enabled?, mailbox_drafts?}`), `POST /delegation/inbox/check`, `GET /delegation/replies`, `PUT /delegation/replies/{id}/text`, `PUT /delegation/handle-it`, `PUT /delegation/reach` (`{step}`, the dial), `PUT /delegation/training`, `DELETE /delegation/learned/{id}` and `GET /delegation/handled` — the caller's own delegation only — and `PUT /delegation/team`, the owner's switch (see API Reference). `GET /what-it-may-do` is the read-only summary above. Send is `POST /decisions/{id}/approve`; Dismiss is `POST /decisions/{id}/reject`.\n- **Evals**: a scenario's `delegation:` block runs the turn against an in-memory mailbox (`evals.mailbox.ScenarioMailbox`) and hands the saved drafts to the judge (`delegation_001`–`003`). A `type: inbox` scenario runs the watcher's two model calls on one thread: whether it drafts must match the scenario, and a draft is judged on saying nothing the person hadn't, copying no link or address, and listing every open question (`delegation_inbox_001`–`007`; the last checks a draft never claims anything was sent).\n\nActing within rules the person sets and standing in for them are later, separate changes, each behind its own switch, off by default.",+ "markdown": "The **delegation** module (`openexecutive.delegation`) is **Act as me**: the one place the Executive writes *as* a person instead of as itself. Everywhere else it has its own Google account and bots and signs as itself. Here — when the person asks, or, with a second switch, for mail in their inbox that needs them — it writes an email in their voice and saves it as a **draft in their own mailbox** — Gmail or Outlook — for them to review and send. The one thing it ever sends is one of those inbox drafts, exactly as it is in their mailbox: when the person taps **Send** on its card, or, with a third switch, **Handle it for me**, on its own when plain-code rules allow it (below); chat never sends. The principal can turn it on for themselves, and so can each team member once the owner lets them. It is off by default, and off changes nothing: the prompts, tool lists and prompt caches are byte-identical to an install without it.\n\n## Who can have it, and when it is offered\n\n`delegation.settings.can_delegate(person)` is the single rule for who may turn it on: the principal (a non-archived team member flagged `is_principal`), and any other non-archived team member — never a contact — once team members may have it (`team_members_enabled`). That takes two things: the install allows it (`DELEGATION_TEAM_MEMBERS`, default off, which offers the owner the switch) and the owner turned on **Let team members use it** (`PUT /delegation/team`, principal only, one row in `delegation_team`). Turning the owner's switch off takes it away from every team member from their next message, and their inbox watchers stop at their next check; their own switches, drafts and cards are kept. Everything is keyed by `person_id`. A person turns it on for themselves (`PUT /delegation`); nobody turns it on for anyone else. The setting is one row per person in `delegation_settings`, and a missing, unreadable or zero row all mean off.\n\nAt the start of every chat turn (`Executive.stream_chat` and the committee path) `pin_turn_delegation(session, speaker_text)` runs next to the workspace-mode pin and records a `TurnDelegation` on the session. `ghostwrite_email` is **offered** only when all of these hold:\n\n- the speaker may have it and turned it on — read fresh every turn, so turning it off applies from the next message;\n- the speaker is on a surface that verified it is them — the principal through `people_tools.is_principal_on_verified_surface`, a team member through `teammate_on_verified_surface` (the web app signed in, their own Slack or Discord, never an email turn) — and a web turn also carried a signed-in caller (`Session.web_caller_signed_in`, set from `x-caller-email`) or runs under local login — a request with no caller header is not a sign-in and never gets it (whoever holds the shared secret is trusted as the UI proxy that stamps that header, as on every principal-only route);\n- the conversation is private to the speaker: the web chat, a Slack or Discord DM, a verified private Telegram chat, or a chat its channel adapter verified the sender of and marked private (`Session.speaker_verified` + `Session.private_chat`) — never a shared channel or thread, where the draft's preview or the matching threads would be posted for everyone and other people's messages sit in the model's context;\n- the turn is neither unattended (the scheduler's proactive run) nor private to the principal (the email poller's turns), so inbound text can never reach it. The MCP server, workflows, reflection and research never carry it at all.\n\nThe mailbox connection is deliberately **not** part of the offer: the handler checks it on every call and says how to fix it, so the cached tool prefix never flips when a token lapses. The pin lives in a context variable for the turn's task as well as on the session, so two turns running at once on one session (a second browser tab) each read their own. It also carries the speaker's own words for the turn (a new email may go to an address they just typed — the turn's message joins the history only once the turn ends), a per-turn draft count, and `touched_mail` (see Privacy). `own_words` reads those words back for every own-words check (addresses here, facts and task assignments elsewhere): it first removes the hydrated `<outbound_reply_context>` backstory by its exact, anchored shape, so a look-alike closing tag quoted inside it cannot pass the rest off as the speaker's, then drops other adapter tag blocks, and returns nothing for a message carrying an attachment.\n\n## The tool: `ghostwrite_email`\n\nIt lives in its own registry (`orchestrator.delegation_tools.DELEGATION_TOOLS` / `DELEGATION_TOOL_HANDLERS`), **never** `_ALL_SKILL_TOOLS`, so no other toolkit can carry it. On a turn it is offered to, the agent loop adds it to the pool *before* the sort and builds that turn's handler map from both registries; on any other turn a call to it is an unknown tool. The handler re-checks the pin and the surface anyway, then:\n\n1. **Caps** — at most 5 drafts per turn, and `DELEGATION_MAX_DRAFTS_PER_DAY` (default 50, at most 1000) per person per UTC day, shared with the inbox watcher (`delegation.caps`). It is counted from `delegation_drafts`, one row of ids per draft saved from either place, with a count kept in the process as a floor in case a row was lost. Each slot is taken before the first await — a round's tool calls run concurrently, so otherwise every call in it would pass the caps before any counted — and handed back if nothing was drafted. If the rows can't be read it refuses rather than guess.\n2. **Marks the turn** — sets `TurnDelegation.touched_mail` *before* its first read of the mailbox.\n3. **Checks the mailbox** — `gmail_status` asks Google or Microsoft whose mailbox the credential opens and compares it with the person's People email, on every call: a roster email can change, and a client slot swaps the roster.\n4. **Finds the thread** — by `thread_id` (checked against the mailbox's own id shape), or a Gmail-style search (`find`; on Outlook, words, `from:`, `to:`, `cc:`, `subject:` and `newer_than:` are kept and other Gmail operators dropped). Several matches return `{status: \"choose\", candidates}` (subject, sender and date — no message text) and draft nothing; none returns `not_found`.\n5. **Sets the recipients in code**, never from the model. A reply goes to the last inbound message's `From` — never its `Reply-To` (a different one is flagged `reply_to_ignored`) — with the thread's other recipients only on `reply_all`. A new email or a forward may go to any well-formed address: it is only a draft, waiting in their own mailbox, where they see who it is to before they send it. An address that is neither on the roster (contacts only when `contacts_reachable_now()`) nor typed by the speaker this turn comes back in `not_in_people`, and the Executive names it for them to check (`delegation_tools.not_in_people`). Mailing-list mail, a thread they replied to last and a reply-all trimmed to 10 recipients are flagged. An address inside a block an adapter added to their message (the backstory hydrated into a DM) is not one they typed, and when the message carries an attachment — a document's inlined text, or a note naming the file — none of its addresses count as typed: neither has an end mark, and a filename is chosen by whoever sent the file, so such an address is named back to check.\n6. **Writes it** (the ghostwriter, below) and saves it with the mailbox client's `create_draft` (Gmail: threaded with `In-Reply-To`, `References` (whole message ids: when the chain is too long for one header the oldest after the thread's first go, never the parent) and `threadId`, and stamped `X-OE-Ghostwritten`; Outlook: Graph's `createReply` on the message it answers, then the text and recipients, and a named property marking it).\n\nThe result is `{status: \"drafted\", draft_id, gmail_link, to, cc, subject, preview, flags, open_questions, note}`, plus `not_in_people` and `check_address` when a recipient needs checking. The link (`gmail.mailbox_link`) is built server-side from a fixed prefix — the thread in Gmail, the draft itself in Outlook on the web — and the note tells the model the preview is the person's draft, to be treated as data. The chat shows an action chip — \"Drafted an email as you to … — in your Drafts\" — that opens it, and only a link under `MAILBOX_LINK_PREFIXES` is ever linked. A sincere \"are you an AI?\" in the thread comes back as an open question for the person to answer themselves.\n\n## Reading their mailbox\n\nFive read-only mail tools ride with `ghostwrite_email` in the same registry (`orchestrator.mail_read_tools`), so they are offered, re-checked and fenced exactly as it is: `search_my_email` (a Gmail-style search through the client's `search_threads`, or with no query the threads that reached their inbox in the last few days through `inbox_message_ids` + `get_message`), `read_my_email` (one thread's last 10 messages, each sender's new text only, drafts left out, with the files attached to them listed by message id and index), `read_my_email_attachment` (one of those files as text: PDF, Word, Excel, CSV or text, up to 20 MB, a scanned PDF converted) and `my_email_awaiting_reply` (their own sent mail from the last 14 days, to at most 10 people besides the Executive, that is still the last message in its thread). They change, label, draft and send nothing.\n\nThe fifth, `my_email_read_before`, lists the threads `read_my_email` opened for the same person before, in this conversation or an earlier one, so a later conversation can open the same email again instead of asking them to search for it. It keeps where, never what (`delegation.mail_reads`, table `delegation_mail_read`): the thread id, its subject and first sender as one line each, the mailbox address it was read from and when, never a message's text, an attachment or a recipient. Rows are the person's own and are listed only from the mailbox open now, newest first, optionally narrowed by words in the subject or sender; anything older than 30 days is never listed and is deleted on the next write, at most 200 are kept per person, and turning Act as me off deletes them all. It opens the mailbox like the other reads, so it sets `touched_mail`, counts as a search, and returns its rows with the same data-not-instructions note. The Act as me addendum tells the model that these tools reach the person's mailbox while any Gmail or Outlook tools of its own account reach only the Executive's, to search theirs (never falling back to its own) for mail sent to them, and to reopen an email from before with `my_email_read_before` and `read_my_email`.\n\nEach sets `touched_mail` and marks the conversation theirs before its first read (`_open_mailbox`, shared with `ghostwrite_email`), so the lockdown below applies from its round on. Each is capped per turn on the pin: 10 searches (`my_email_awaiting_reply` counts as one), 20 thread reads and 5 attachment reads, the slot taken before the first await. In `read_my_email` every message someone else wrote comes back inside its own `<untrusted_content source=\"email\">` block (`content_trust.wrap_untrusted`, which defuses a closing tag in the text); the speaker's own messages — SENT and from their address (`threads.mine`), never a From header alone — are marked \"Yours\" outside any block. An attachment's text comes back in its own `<untrusted_content source=\"attachment\">` block (`attachments.format_attached_text`), parsed in an isolated worker (`knowledge.loader`); unlike a file sent to the Executive it is never added to the company's knowledge. The clients find an attachment by message and position and look its provider id up on each read (Gmail's changes per fetch): Gmail lists a message's files with the message (`MailMessage.attachments`, leaving out images the HTML shows in place), Outlook says only `hasAttachments` until `list_attachments` asks Graph (leaving out inline ones), and `attachment_bytes` reads one; an attached Outlook item or cloud link has no file to read. Results carry a note that subjects, senders and text are other people's words, data rather than instructions. The lockdown refuses tools, not the reply's own text, so what would carry that text out without a click is closed where it is shown: the web chat loads no image from another site, and bot replies go out without link previews (see Integrations).\n\n## Saving a file from their mail\n\nOne more tool rides with the reads: `save_my_email_attachment` (message id and index, as `read_my_email` listed the file) copies one attached file into the storage the Executive itself has connected and shares it with the speaker alone, so they get a link they can open or put in an app. Every call it makes is built in code (`orchestrator.mail_file_save`); the model picks only the attachment. The bytes come from the mailbox client's `attachment_bytes` and never pass through the model, any file type up to 20 MB, under a cleaned name (one line, no path or reserved characters, extension kept). The storage is the one the Executive's own mailbox runs on (`EMAIL_PROVIDER`) when the gateway has that server, else the other: Google Drive through workspace-mcp (`create_drive_file` with `base64_content` into a folder named \"From your email\" in the Executive's My Drive, then `manage_drive_access` granting the speaker's own address the reader role, `send_notification` off) or OneDrive through ms-365-mcp-server (`upload-file-content` into the same kind of folder in the Executive's own drive, with a name no recorded copy has, since an upload overwrites, then `share-drive-item` inviting only the speaker, `requireSignIn`, role `read`, `sendInvitation` off). The folder is always made by the save itself and its id remembered (`delegation_saved_folder`), never found by its name, since a folder someone else made and called that could already be shared with them; when the remembered one is gone or won't take the file, a new one is made and the old id stays recorded. Never a link share, a domain or anyone. Neither connected (or an eval's in-memory mailbox): status `no_storage`, and the model says so and offers to forward the email instead. Saves run one at a time, at most 10 a turn (`TurnDelegation.files_saved`), and the result is the status, the name, where it went and the link (`webViewLink` / `webUrl`); the chat chip says only that a file was saved, never the sender's file name.\n\nIt copies only when the speaker asked in their own words this turn: what they typed (`own_words`, no quoted backstory or attached file's text) must hold one of save, saved, upload or OneDrive, or Drive as a place (\"to my Drive\", \"in Drive\", \"Google Drive\"), checked before a slot is spent or the mailbox opened; otherwise it refuses (`not_asked`) and tells the model to ask them. It stays allowed after the turn read mail (`MAIL_TOUCHED_ALLOWED_TOOLS`): its gateway calls are admitted past the lockdown only as the very objects the handler built (`mcp_gateway.code_built_call`, for its seven Drive and OneDrive tools: folder create, file create or upload, the speaker's share, and OneDrive's `list-drives`), so a model's own `call_tool` on that turn is still refused, and every other gateway gate still runs on them (the acting account, URL fetches, sheet formulas, the share gates' roster check, writes kept to the Executive's own drives).\n\nEach copy is recorded before it is shared (`delegation.saved_files`, table `delegation_saved_files`: the person, the storage, the file id, its name and when; never content or the mail it came from), and the folder in `delegation_saved_folder`. The gateway reads that table on every Google Workspace and Microsoft 365 call: on a turn whose speaker is not the file's owner (the owner is the speaker only when Act as me was offered to them, so a shared chat, a workflow or the poller sees none), a call naming a recorded file id, raw or percent-encoded (OneDrive's `download-bytes` path is decoded by Graph), is refused, and a result, filtered against the table as it stands after the call so a copy recorded while a listing ran is caught too, loses each list entry or line naming one, with any id left masked. It matches ids as text, so a result that names such a file without its id (a notification quoting its title) still shows the name, and a copy someone makes is a new file. The folders are guarded harder, on every turn and for every speaker, the owner too: a model call whose arguments name any recorded folder id, or an OneDrive item path through the folder (`root:/From your email/x.pdf:` or `<folder id>:/x.pdf:`), is refused, so nobody can share, move, rename, copy, list or delete the folder from chat, and folder ids are dropped from or masked in every result; only the save's own code-built calls touch it. When a copy is made but its row can't be written, it is not shared, the save reports `failed` and logs an error, and the copy's id is hidden from every turn, the owner's included, for the life of the process. When the table can't be read, the file tools (`_FILE_TOOL_RE`: Drive, folder, file, Docs, Sheets, Slides and presentation tools, attachment bytes) are refused (fail closed) while mail and calendar run. The rows are kept when Act as me is turned off: the copies stay in the Executive's storage, and the rows keep them out of other people's turns.\n\n## Reading their calendar\n\nA third switch under Act as me, **Read my calendar** (`delegation.calendar`, table `delegation_calendar`: one row per person, absent or unreadable meaning off), lets the Executive read the person's own calendar, read-only. It rides on the same per-person sign-in as their mailbox: `calendar.readonly` on Google, `Calendars.Read` on Microsoft, added when they run the connect script with `--calendar` (`scripts/connect-own-gmail.py`, `scripts/connect-own-outlook.py`). Those scopes are optional, so a mail-only sign-in keeps working for mail; the mailbox clients note the scopes the token refresh reports, and `list_events` raises `CalendarNotGranted` before calling the calendar when the scope is missing (or when the calendar answers 403). Only the person turns it on (`PUT /delegation/calendar`), only while Act as me is on and a one-hour read works; a sign-in without the calendar is refused with `calendar_not_granted` and the command to run. Turning Act as me off turns it off. Changes are audited privately (`delegation_calendar_changed`).\n\n`my_calendar` sits with the mailbox reads, offered and fenced the same way: it refuses while the switch is off (before anything is opened), then takes a search slot, opens the mailbox privately (`_open_mailbox`, so `touched_mail` and the lockdown apply: an invite's title is in the words of whoever sent it) and lists the events from `start` (default today) for `days` days (1 to 31) in the workspace time zone, recurring events expanded and cancelled ones left out: title, start, end, all-day, location, organizer, attendees (25 at most) and the person's own answer, each on one line, with a data-not-instructions note. Google's `events.list` on the primary calendar and Graph's `calendarView` (times asked for in UTC) are its only calls; it changes nothing and keeps nothing. The first week's brief also lists today's meetings from it on the principal's own delivery (see Today).\n\n## Forwarding and reminders\n\n`ghostwrite_email` also forwards: with `forward` (a thread id) and `to`, it drafts a forward of the thread's latest message, or of the earlier one `forward_message_id` names (the one with the files, say, when their own reply came after it), `intent` becoming the short note above it (the ghostwriter writes only the note; the forwarded email's subject, someone else's words, is never put in the intent). Recipients follow the new-email rule (`_new_recipients`: the roster, or addresses the speaker typed this turn). Gmail's draft quotes a forward header and the original's own words under the note and attaches the original's files, up to 10 and 20 MB (`FORWARD_MAX_FILES`, `FORWARD_MAX_BYTES`; any left off are flagged `attachments_left_off`); Outlook uses Graph's `createForward`, which keeps the original and its files, with the note as its comment and the body never patched. It is still only a draft.\n\n`remind_me(text, when)` (`orchestrator.reminder_tools`) rides with the same tools and checks, but opens no mailbox, so it never marks or locks a turn (`MAILBOX_TOOL_NAMES` are the ones that do). It stores the text once cleaned — one line, anything a chat app could turn into a link (a URL of any scheme, an address, a domain-like word, a host and port, an IP address) replaced with \"[link]\", at most 300 characters — with its time (stored in UTC) in `delegation_reminders` (5 a turn, 25 waiting, a year ahead, refused when the person has no channel). When it is due the scheduler sends that text to the person alone, as \"Reminder you set on <date>: …\", running nothing (see Scheduler); the Slack and Discord DMs it may go by turn link previews off. The chat chip shows the text as it will be sent. A reminder that comes due in the person's quiet hours or leave (when `OUTBOUND_RESPECT_QUIET_HOURS` is on) waits unclaimed and goes once they end, rather than being suppressed and lost. It is allowed after mail is read and in later turns of that conversation: it reaches only the speaker, as plain text. `schedule_followup`, which runs a turn with tools and is listed to everyone, stays refused there.\n\n## Approval cards\n\nA turn that read someone's mail may not message anyone, invite anyone or change the roster (see the lockdown above), yet what the mail asks for is often right. `propose_actions` (`orchestrator.action_card_tools`) leaves the speaker a card instead: up to five actions, each spelled out exactly as it will happen, done only when they tap Approve. It rides with the other Act as me tools and checks (`_writer`), opens no mailbox, and is allowed after mail is read because it does nothing on the turn.\n\n- **Kinds.** `invite` (a meeting with people on the roster), `message` (a direct message to someone on the roster, as written) and `add_contact` (a new contact; the principal's cards only, since contacts are theirs). A team member's card can't name a contact. Each action is checked when the card is made (`delegation.action_cards.check`) and again when it is carried out, so an archived person or a time that has passed fails that action alone.\n- **Whose.** A card is a `delegation_actions` decision for the speaker, `approver_only` like a reply card: only they see it (`GET /delegation/actions`) or resolve it, a team member's answers 404 to the principal too, and it is never an alert. The same actions still waiting are that card, not a new one. 3 cards a turn, 25 waiting, dropped after 7 days.\n- **Approve.** In the chat, under the reply that left it (the `propose_actions` chip carries the card's `decision_id`, and `ChatActionCards` shows the card while it waits), and on the Briefing's Needs you list, with a box per action. Approve (`POST /decisions/{id}/approve`, `edits.only`) needs the card's person signed in (`verified.caller_refusal`) with Act as me on; the card is claimed first so it runs once, then each ticked action runs as stored with no model call, in an unattended session (the principal's with contact egress) under `rows_for_person`, so every audit row it writes is theirs and nothing reaches the team's activity rail: `message_person` (a direct message or nothing; never its Briefing-alert fallback, which more people read), `create_calendar_event`, or a contact row. Approving also needs the person still allowed Act as me (`can_delegate`) and switched on. An invite is booked straight away when the person approving is the one the meeting gate would ask (`calendar_tools.approved_by`), and otherwise goes to that approver as usual, so a card never widens anyone's authority. Per-action results (`done`, `waiting`, `failed`, `skipped`) are kept on the decision and shown on the card. Dismiss rejects it and does nothing else. With Suggested actions in training the card adds Approve + allow, and a card of actions all allowed is carried out on its own (see In training above).\n- **Channels.** A card can come from any surface Act as me runs on; it is approved in the web app, since the chat apps have no buttons here.\n\n## The ghostwriter\n\n`delegation.ghostwriter.compose` writes the text. The Executive decides *what* to say (`intent`); this call decides *how* the person would say it, and it is deliberately small:\n\n- a constant `GHOSTWRITER_PROMPT` plus the person's voice block as the system prompt;\n- the thread (each message cut to its sender's own words, every line scrubbed, all labelled alike), then the writer's own earlier words in it (`<writer_said>`, from their sent mail only), the intent and the recipients' names in the user turn — no company profile, memory or roster;\n- with Always in the loop on, `<writer_noted>`: what the writer's own notes say they told these same people in earlier Act as me replies (`memory.history_drafts.notes_for_draft`: only notes from mail **every** recipient of the new draft was on, so nothing told to one person reaches another; chat notes name no recipient and never qualify; at most 8, newest first, the person's own words or their correction, with dates). The prompt's rule 6 makes it a consistency check, never content: a draft that contradicts it is still written as the intent says, and the conflict becomes an open question on the card, which only the writer sees. Both the chat tool and the inbox watcher pass it;\n- **no tools** but the forced `compose_reply` return, so text in the thread can ask for anything and there is nothing to do it with.\n\nIt is not a Council agent — the Council's edit routes have no principal check — and runs on `DELEGATION_COMPOSER_MODEL` (default: the default model), logged as `ghostwriter` usage. `lint` then runs in code on what comes back: a link or an email address survives only if it appears in the intent, the signature or the recipients, so a link planted in the thread is removed and flagged; the Executive's own name is flagged; and the body is capped, cut at a paragraph, line or word break in its last fifth. A draft with nothing left after that is refused. The signature from the person's Gmail settings (or the one already stored, for Outlook) is appended.\n\n## How I write\n\n`delegation.voice` learns how a person writes *their own* email (`attunement.style` learns how the Executive should write *to* someone). `POST /delegation/voice/learn` reads up to 40 recent sent messages, keeps only what they wrote (quoted replies stripped with the email poller's `sender_new_text`), skips automatic mail, every thread chat drafted into, and every sent message that began as a draft written for them (`delegation_drafts.sent_message_id`), and makes one forced-tool call (`record_voice_profile`). Code validates every field before it is stored:\n\n- greetings per audience (their team, their contacts, anyone else), a sign-off of at most two lines, and a usual length and tone (a backslash-n the model wrote instead of a line break is read as one, keeping the first lines that fit, which also repairs a profile stored before that rule);\n- up to 8 habits and 6 things to avoid, through the same deny-list as working-style rules — no actions, links, handles, amounts, tool names or names of people; the conversation review (`memory.chat_review`) adds one when the person states how they write in a chat (`add_conversation_rule`, `updated_by=conversation`; never on a locked or full list, and an edit or lock made meanwhile wins);\n- up to 3 short exemplars, each checked to be verbatim from a sample, with addresses and phone numbers masked — and none while a client slot is active, so one client's mail never lands in another's state.\n\nThe signature comes from Gmail's `sendAs` settings, not the model (Outlook gives apps no way to read one, so a learn keeps the stored signature and `POST /delegation/voice/signature` answers 409 `signature_unavailable` rather than clearing it), as plain text with its lines kept (`gmail.html_to_text`: a `<br>` always ends a line, and a block tag, opening or closing, ends one when it has text, so Gmail's layout of a first line followed by one `<div>` per line comes out line by line). `POST /delegation/voice/signature` reads it again without relearning: nothing else changes and a locked profile stays locked, so it picks up a changed Gmail signature and undoes **Don't add my signature**. A person can also describe their style in their own words: `POST /delegation/voice/describe` applies the description to the profile they have through the same forced tool (a separate system prompt, no exemplars) and the same validation, keeps their signature and writing examples, and returns the result with a short sample reply for them to review. It saves nothing and needs no mailbox; Save stores it as an ordinary edit. The person can edit the profile, lock it (a locked profile is never relearned) and reset it, and every change is kept in `delegation_voice_history`. One learn runs at a time per person, and a lock or an edit made while it runs wins: the learned profile is dropped (`changed`).\n\n## Draft replies to my inbox\n\nA second switch under Act as me, **Draft replies to my inbox** (`delegation.inbox`), has the Executive watch the person's own inbox and write a first reply to mail that needs them. The reply waits on a private card on Today; nothing is sent until they tap **Send** (below). Where the reply lives is the person's choice, **Also save replies in my Gmail Drafts** (`mailbox_drafts`, off by default): off, it lives on the card alone (`delegation.card_drafts`: the card keeps the draft's recipients, subject and thread headers as `draft_spec`, and Send makes the mailbox draft from exactly that just before the send-time checks, taking it back out if they refuse), so their Drafts folder doesn't fill with replies they may never send; on, it is also saved in their Drafts as before. The switch is one row per person in `delegation_inbox_watch`. Turning it on needs Act as me on and their mailbox connected, and sets `watch_since` to now every time, so it never drafts for mail that arrived before; turning Act as me off turns it off too. Off means no mailbox call and no row written, with one exception: a send the person started that the mailbox never confirmed is still followed through until it is settled.\n\n### When it looks\n\nA throttled hook in the scheduler tick (`_maybe_scan_inbox`, after the pause, company-profile and rotation gates) checks each person whose switch is on every `DELEGATION_INBOX_POLL_MINUTES` (default 5). It is not a scheduled action, because those are listed on `/scheduled` for everyone and anyone may cancel them. One scan task runs at a time, one scan per person, and none while a client slot is active. **Check now** on the Settings card runs the same scan. Every row a scan writes is private and the person's own (`audit.rows_for_person`: a team member's rows are hidden from the principal too, see Privacy), and the process log carries counts and codes, never an address or a line of mail. The scan never marks mail read or changes a label.\n\n### What it drafts for\n\nA scan first settles the open cards (below), and stops with `backlog_full` once 25 are waiting, counting the ones it makes. It then lists the inbox since `watch_since` (`inbox_message_ids`) — not chats, not mail from the person, and not the promotions, social, updates or forums tabs (on Outlook: the Focused inbox only) — up to 100 messages, and takes the newest message of each thread that still needs a look, at most 10: settled threads and threads with an open card are passed over first, so a burst of mail, or a pause for a limit or a back-off, never hides older threads for good. `delegation_inbox_messages` is its durable cursor: one row per message (`UNIQUE(person_id, message_id)`) with what happened to it, the reason, how many tries it took, and the draft and card ids. It stores a hash of the sender's address, never the address. A message is skipped, with the reason recorded, when:\n\n- it came before `watch_since`, or more than three days ago;\n- it is from the person or one of their send-as addresses, from the Executive, or one of this module's own drafts;\n- it is automatic — `Auto-Submitted`, a bulk or auto-reply `Precedence`, a bounce, a calendar invite or a no-reply sender — or from a mailing list, or in a Gmail tab, spam or trash;\n- the person is not in To or Cc, or it has more than 10 recipients;\n- the person replied last, or a draft already sits in the thread.\n\nThree kinds are left unrecorded, so a later scan looks again: mail under 10 minutes old (mail the person answers straight away never gets a card), mail in a thread whose card is still open, and mail a daily limit holds back.\n\n### Deciding, then writing\n\nTwo model calls, and code decides between them. The classifier (`delegation.inbox_classifier`) is one forced-tool call, `classify_email`, returning whether the email needs a personal reply, what kind it is and how sure it is. It sees a few one-lined header lines and the sender's own new words (at most 3000 characters, every line scrubbed) inside one `<email>` block marked as data, and it has no other tools, context or memory, so an email can ask for anything and there is nothing to do it with. A reply is drafted only for a question, a request, scheduling, an introduction or a follow-up, and only when the confidence clears a bar that rises the less the sender is known: 0.6 for their team or a contact (the principal's contacts count only for the principal: a team member's mail is weighed by the team and their own sent mail), 0.7 for someone they have written to before (`has_written_to`, a search of their sent mail), 0.85 for a stranger. Pitches, notes of thanks, FYIs, notifications, newsletters and phishing get nothing, and so does any failure. An email that also went to other people is drafted for only when the person is in To and it asks them themselves: the classifier is told their name, whether they are in To or Cc and how many others it went to, and lists the names the email greets or asks by name (`asked_names`). Code matches those against the person's name, whole name parts only (\"Alexis\" never counts for \"Alex\", and a nickname misses, which means no draft), so mail that greets someone else (\"Good morning, Brennan, could you sign ...\") is never theirs, whatever the model makes of it as a whole. When it names nobody, the model's `asked_of_them` decides, false for a question to the group at large. One that only copies them is never drafted for. Either is recorded `not_needed` with the reason `asks_someone_else`. It runs on `DELEGATION_CLASSIFIER_MODEL`, else the routing model. A sender whose address Gmail couldn't authenticate is handled as a stranger whatever the roster says — anyone can put a colleague's or a client's address in From — so they get the stranger's bar, a holding reply and the stranger limits; the card still says who they claim to be, and that the address isn't verified.\n\nThe reply is written by the same ghostwriter, in the person's voice, but from a fixed intent the module builds rather than words the person typed. Because the intent lets it restate the person's own earlier words, which words are theirs is never written inside the thread, where a sender could imitate any marker with a look-alike: every message there is labelled alike, and the person's own words come in a separate `<writer_said>` block after the thread, taken only from mail their own mailbox sent. Nothing inside the thread can close the thread block or open another. The intent: acknowledge the sender; say again only what the person's *own* earlier messages in the thread already said; commit to nothing new — no yes or no, date, time, price, fact or promise — and say they will get back to them; and put every question it could not answer from their words in **open questions**. A stranger always gets a short holding reply. The lint still strips any link or address that isn't the person's own. The reply goes to the sender (never `Reply-To`) and, on a group email, to everyone else it went to as Cc (reply to all, never the person's own addresses or the Executive); a stranger's holding reply goes to the sender alone. The card says when others were on the email, and its `draft_to` lists everyone, which Send checks.\n\nThe order: record the message, classify, reserve a slot in the shared daily limit, write, save the draft in Gmail (from the alias the mail went to, when it went to one) and store its id, then create the card (idempotent on the message) and mark it drafted. Nothing that fails along the way loses the message. A failure that may pass — the classifier or the writer failing, Gmail refusing the draft, a card that couldn't be made (its draft is deleted first, so no draft is left without a card), any other error with that one message — leaves it for a later scan (`retry`), and it is given up on only after three tries; one message's trouble never holds up the rest. A daily limit reached while it was being read leaves it for later without counting as a try.\n\n### The reply cards\n\nA card is a `delegation_reply` decision whose class is **its approver's alone** (`DecisionClassSpec.approver_only`): only the person it was drafted for sees or resolves it on any decisions route — a team member's card answers 404 to the principal too — and it is never an alert: alerts feed chat turns, which would put other people's mail into memory. It carries the sender with who they are to the person and whether Gmail could verify the address (SPF/DKIM/DMARC, through `fact_confirmation.headers_authenticated`), the subject, what they wrote, the draft, the open questions and its warnings. `GET /delegation/replies` lists the open ones from the database alone, so Today never waits on Google.\n\n- **Send** approves the card, which sends its draft exactly as it is in their mailbox (see *Send on your tap*). **Edit** changes the reply's words right on the card (`PUT /delegation/replies/{id}/text`, `card_drafts.edit`): only its own person, from a caller the API can tie to them (as for Send), never while it is being sent on its own; a reply in their Drafts is rewritten there too (`update_draft_text`, every header kept), and only while it is still the version the card last saw, so a change made in the mailbox is never overwritten. A card edit counts as edited (`approved_with_edit`, and **Do it like this next time** keeps it). **Open in Gmail** (or **Open in Outlook**), shown only when the reply is in their Drafts, opens it there.\n- **Dismiss** rejects the card; the class's after-reject step then deletes the draft if nobody edited it — its message id is still the one it was saved with, since Gmail gives an edited draft a new one, and the Outlook client makes a draft's message id `<id>.<changeKey>` so an edit there changes it too — and keeps it otherwise. What happened is recorded even when Gmail fails.\n- Each scan first **settles** what Gmail already settled: a draft sent from Gmail, a draft deleted there, a reply the person wrote themselves, a thread that is gone, or a card left for 7 days (its draft stays in Gmail). Each is a compare-and-set close with the reason. A newer message from someone else flags the card instead. A card being sent at that moment is left alone.\n\n### Send on your tap\n\n`delegation.reply_send` is the only thing in Act as me that sends, and all it can send is the draft on a card, by its id: `DelegateGmail.send_draft` posts `{\"id\": …}` to Gmail's `drafts.send`, and `DelegateOutlook.send_draft` posts an empty body to that draft's Graph `send`, and nothing else, so no text, recipient or header is ever passed. It has two doors: `send_approved_reply`, reached only from `POST /decisions/{id}/approve` — a class only the card's own person may resolve — and `send_on_its_own`, reached only from the inbox watcher under Handle it for me (below). AST tests pin both call sites, so no model, chat turn, workflow, scheduled job or MCP call can. A tap is checked like this: At send time it checks everything again:\n\n1. **Who is asking.** The caller is the card's person and the API knows it: signed callers are on and the request carries that person's signed assertion (or the operator's, under local login), or the API runs for local login and answers this computer only. Anything else is a 409 `caller_signing_required` — with only the shared secret, whoever holds it could send as the owner — so on a server Send needs signed sign-ins.\n2. **The switches.** Act as me and Draft replies to my inbox are on, and no client slot is active.\n3. **The mailbox.** Their mailbox is connected.\n4. **The draft.** It still exists, in the same thread, and they haven't replied there themselves since; otherwise the card closes.\n5. **Who it goes to.** To, Cc and Bcc hold between 1 and 10 addresses, never the Executive's own, and it is from one of their own addresses.\n6. **What changed.** Recipients that differ from the card's, or a newer message from someone else, need a second yes: the first tap gets a 409 `confirm` naming the recipients and the reason, and the person approves again with what they were shown.\n\nThen it claims the card (`claim_for_execution`, proposed → executing, a compare-and-set, so a double tap sends once) and reads the draft once more: `drafts.send` sends whatever the draft is when Gmail gets the request, so if it was edited since the checks read it — in another tab, by a delegate — nothing is sent and the card comes back (`draft_changed`). Then it sends, and records the result: `approved_with_edit` when the draft was edited in Gmail, the sent message's id, the draft row's `sent_message_id`, and a private `delegation_reply_sent` row. A refusal that proves nothing went — a 4xx, a lapsed sign-in, a rate limit, a draft already gone — hands the card back. A failure that leaves it unclear — a timeout, a 5xx — leaves it `executing` and says to check the Sent folder, and the next scans ask Gmail: their message in the thread means it was sent; anything else is judged on the second scan that sees it: the draft still there and nothing sent means it was not (Gmail deletes a draft it sends), and the card comes back, flagged; the draft gone and nothing sent means it was deleted. Nothing is ever retried on its own. Sending is the person's own act, so it works while the Executive is paused.\n\n### Limits and failures\n\nAt most 5 drafts a scan; `DELEGATION_INBOX_MAX_DRAFTS_PER_DAY` (default 20) a day, inside the shared `DELEGATION_MAX_DRAFTS_PER_DAY` it shares with chat; 200 classifications, 2 drafts per sender (1 for a stranger) and 10 for strangers in all per day; and never more than 25 open cards. A lapsed Gmail sign-in sets the status and is looked at again every 30 minutes; a rate limit, an error reaching Gmail or a crash backs off from 5 minutes, doubling up to 2 hours. Neither turns the switch off: the Settings card shows the status in plain words.\n\n## Handle it for me\n\nA third switch under Act as me, **Handle it for me** (`delegation.handle_it`), lets the inbox watcher send some of its replies itself instead of leaving them on a card. It is one row per person in `delegation_handle_it` (`enabled`, `mode`); no row means off. One setting says how much goes without them, the way quality does on the Agent Council (`handle_it.RULES`): **Easy ones** (`careful`) sends only replies to people they know (someone on their team, a contact or someone they have written to) of at most 400 characters when the classifier is at least 0.9 sure; **People I know** (`balanced`), where it starts, sends replies to people they know up to 1200 characters at 0.8; **Most mail** (`bold`) also answers strangers, up to 2000 characters, and lets a link or an amount through when the classifier is at least 0.9 sure. Everything else waits on a card as before, so turning it on never drafts less. A table from before the setting gets the `mode` column on its next open (`schema._add_handle_it_mode`): someone who had strangers set to send keeps that as Bold, everyone else gets Balanced. Only the person turns it on (`PUT /delegation/handle-it`), from a session the API knows is theirs: the same rule Send uses (`delegation.verified.caller_refusal`), so with only the shared secret it answers 409 `caller_signing_required`. Turning it on needs Act as me and Draft replies to my inbox on, and turning the inbox watcher off (or Act as me, which turns it off) turns it off too.\n\n**In training** (`delegation.training`). Like someone new, each Act as me job can be put in training on its own, from that job's card on the Act as me page, the way Take the lead has it: **Write drafts as me** and **Handle it for me** each pick Off / In training / On (Handle it's In training is Replies in training, with a *Train follow-ups too* box for Follow-ups), and **Suggested actions** picks Always ask / In training; what it learned is listed on each tab for its own jobs (Act as me: *What it's learned*, drafts and suggested actions; Handle it for me: *Who it's allowed to handle*, replies and follow-ups), each item named by its job (`PUT /delegation/training`, one row per person and setting in `delegation_training`, absent means not in training). In training it asks first and learns who and how from what the person approves; what it learns is a `take_the_lead_allowed` row (feature `act_as_me`, the person's id), theirs alone.\n\n- **Replies.** Every reply waits on its card (`handle_it_reason` `training`) whatever the dial says, and a reply card adds **Send + allow**: it sends that reply on the person's own tap, exactly as Send does, then allows replies to that sender (key `act_as_me|person:<id>|reply|<address>`). While Handle it for me is on, a reply to an allowed sender goes on its own under the dial's limits (a stranger they allowed included) and every check above (the topics that always wait, links and amounts, new recipients, once a thread a day, the daily limit); it's checked again at send time, so a sender removed since waits. Take the lead as you lifts nothing in training: putting Replies or Follow-ups in training turns it off, and it can't be turned on while they are (409 `in_training`).\n- **Follow-ups.** Every follow-up waits (`follow_up_training`); Send + allow on a follow-up card allows follow-ups to exactly the people it went to (`…|follow_up|<sorted addresses>`), whoever they are, under every other follow-up check.\n- **Suggested actions.** An action card (below) adds **Approve + allow**: it does the actions on the tap, then allows each one that happened (a message to that person, `…|message|person:<id>`; a meeting with exactly those people, the person left out, `…|invite|people:<ids>`). A new contact is never allowed. A card proposed later whose every action is allowed is carried out at once, with no tap (`action_cards.run_on_its_own`, `gate_mode` `auto_execute`, status `executed`), only if plain code finds nothing against it (`on_its_own_refusal`): still in training, Act as me on, a server that ties the switch to the person, nothing sensitive, no link or amount, a message of at most 1200 characters, and at most 10 actions carried out this way a day (checked one card at a time); anything refused is handed back to wait on its card as before. An invite carried out this way is never booked as approved by the person: the meeting gate decides as for any meeting nobody tapped, so a time taken from someone's mail can't land on a calendar unasked. The tool result and chip say what was done. The message text in such an action is model-written from the mail and goes without anyone reading it; the allowance covers who and what kind, not the words, which is why sensitive topics, links, amounts and long messages are held back.\n- **Drafts.** Nothing is sent. When the person changes a reply's draft in their mailbox before tapping Send (plain or + allow) and ticks **Do it like this next time**, what they sent is kept (its new text, quoted replies dropped, at most 1000 characters, `…|style|<address>`), and the ghostwriter gets it in its user turn as `<writer_example>` when it next writes to that person, from the inbox, a follow-up or a chat draft to that one person: style only, never its facts, and nothing in it can open or close a tag.\n\nSend + allow and Approve + allow are refused before anything is done unless their setting is in training (422 `cant_allow`) and the person's list has room (409 `learned_full`, at most 200 a person); allowing failing afterwards never undoes the send. Putting Replies or Follow-ups in, or Suggested actions out, of training only holds more back and works without signed sign-ins; anything else needs a caller the API knows is that person. What it learned is the person's alone: listed on `GET /delegation` (`training.learned`, each with its `setting`), removed with `DELETE /delegation/learned/{id}`, and for the owner also in Take the lead's \"What it's learned\" list; it never reaches anyone else's list or Take the lead's prompts. A dial left on In training by an older version (mode `training`) moves to People I know with Replies and Follow-ups in training (`schema._move_training_off_the_dial`).\n\n**No model decides whether a reply goes.** The watcher's two model calls are unchanged and tool-less, so text in an email can at most change the verdict and the draft. After the draft is written, `handle_it.refusal` — plain code — decides, and anything it refuses becomes the usual card with the reason kept on it (`handle_it_reason`). It refuses when:\n\n- it's off, or the sender is a stranger and the setting isn't Bold, or on a server signed sign-ins are off (`signing_ok`: signed callers, or local login);\n- Gmail couldn't authenticate the sender, whatever the roster says;\n- the email isn't a question, request, scheduling, introduction or follow-up, or the classifier was less sure than the setting needs (0.9 on Easy ones, 0.8 otherwise);\n- the reply goes to anyone the email didn't already go to (its From, To and Cc, less the person's own and the Executive's addresses), leaves out the sender, or goes to more than 10;\n- the email's subject, the sender's new words, or the reply touch money, contracts, legal, hiring, pay, layoffs, the board, investors, mergers, the press, health, or credentials and secrets (passwords, logins, tokens, API keys); or the reply carries an amount, a percentage or a link (a scheme, `www.`, a bare host with a path such as `bit.ly/…`, or a bare host on a common top-level domain) unless it's Bold and at least 0.9 sure, or runs over the setting's length (400, 1200 or 2000 characters);\n- the draft carries any flag but *others on the thread* or *Executive on the thread* (they asked if it's an AI, recipients were trimmed, …);\n- it already sent one in this thread in the last day, or the person's last message in the thread was itself sent on its own (no auto-reply ping-pong);\n- the day's limit is reached (`DELEGATION_HANDLE_IT_MAX_SENDS_PER_DAY`, default 20, within the watcher's drafts limit), or it can't be counted. Any error in the rules counts as a refusal.\n\nA reply the rules allow gets a card with `gate_mode` `auto_execute`, and the watcher sends it at once through `reply_send.send_on_its_own`, the second and last door into the send path (an AST test pins both callers: the approve route and the watcher). It runs the same send-time checks as a tap — switches, mailbox, draft, recipients, the claim and the last re-read — with no caller, and adds its own: the card must be `auto_execute`, Handle it for me still on with the setting still allowing that sender (or, for a follow-up, that recipient), signing still on, the once-a-thread-a-day rule and the daily limit counted again, and the draft untouched since it was saved (an edit in Gmail means the person has taken it over: `draft_changed`, the card waits for them). Every refusal hands the card back to the person (`decision_ledger.hand_back`, a compare-and-set to `propose`), with the reason kept on it when there are words for it, and a failure never stops the scan. Every card it left for the person says why on Today (`waited_because` on `GET /delegation/replies`). A reply sent on its own finishes as `executed` (not approved), is recorded in `delegation_handled` (for the per-thread and daily rules) and writes a private `delegation_reply_handled` row; an unconfirmed one is settled by the reconciler the same way. No History note is taken from it, since notes come only from the person's own words. It runs inside the watcher's scan, so it stops while the Executive is paused.\n\n**Follow-ups as you** (`delegation.follow_ups`). While Handle it for me is on, the watcher's scan also looks at the person's own sent mail, at most once an hour (`LOOK_EVERY`), for an email of theirs that asked something (a question mark in their own words), is 3 to 10 days old, went to at most 10 people other than the Executive, and is still the last message in its thread. Plain code picks it; each gets one follow-up ever (its `delegation_inbox_messages` row), at most two a look, within the drafts limit. The ghostwriter, tool-less as always, writes a short nudge in their voice from the thread, saved as a draft in that thread to exactly the people the email went to. `handle_it.follow_up_refusal` — plain code — decides whether it goes: by the setting it never goes on Easy ones, goes to their team and contacts on People I know and to anyone they wrote to on Most mail (`follow_up_refused` otherwise: `follow_up_level`); it also refuses on any change of recipients, a sensitive topic, an amount or a link, more than 600 characters, a flag, and the same per-thread and daily counts as replies. It goes through `send_on_its_own` on an ordinary `delegation_reply` card marked `source: follow_up`, which rechecks the setting for that recipient. A refused one waits on Today as **Follow-up waiting**, and closes by itself (its untouched draft deleted) when anyone answers in the thread first.\n\n**What it sent** is the person's alone: `GET /delegation/handled` lists the last 7 days (who, subject, the reply, the questions it left them and a link to the thread in their mailbox), and the Handle it for me tab shows it with how many went today, under its picker.\n\n### Take the lead as you\n\nOn Settings → Act as me, Handle it for me is one dial: **Off**, **Easy ones**, **People I know**, **Most mail** and, for the owner, **Everything**, which uses **Take the lead** (`PUT /delegation/take-the-lead`, one row `person:<id>` in `take_the_lead`; turning it on turns Handle it for me on). While it is on, `handle_it.refusal` drops the setting's limits: strangers, the classifier's confidence, amounts, and the length up to a 4000-character ceiling. A reply with a link still waits for a tap (refusal `link`). In their place it checks the company's and the person's own added rules (`take_the_lead.reply_hit`, refusal `lead_rule`). Everything Handle it always keeps still holds: signed sign-ins, an authenticated sender, a reply kind, exactly the thread's people, the topics that always wait, draft flags, never twice in a row, one a thread a day and the daily limit. Follow-ups under it may go to anyone the person wrote to, with the same sensitive, amount, link and length checks plus the added rules. `reply_send.send_on_its_own` accepts the card while both switches are on. Each person adds and removes their own rules (`/delegation/take-the-lead/rules`). Removing one needs a caller the API can tie to them.\n\n\n## AI line on replies\n\nReplies written as a person can end with **\"Drafted and sent by my AI assistant.\"** (`delegation.disclosure.LINE`), by two switches that are each person's own (`PUT /delegation/disclosure`, one row per person in `delegation_disclosure`, NULL following the install): **Handle it**, on by default (`AI_DISCLOSURE_HANDLE_IT`), for a reply Handle it for me will send on its own, which nobody reads before it goes; and **Approved sends**, off by default (`AI_DISCLOSURE_APPROVED_SENDS`), for one that waits on a card for them to send, since they read it first. The line is written into the reply when it is drafted (`disclosure.sign`, in `inbox._consider` and `follow_ups`), once the plain-code checks have decided whether it goes on its own, so the card, the mailbox draft and what is sent are the same words and Send's draft-changed checks see them; a switch changed later applies to the next reply, and a reply drafted to go on its own that is handed back keeps its line for the person to edit. `AI_DISCLOSURE` off turns both off and hides the card. Turning a switch on only adds the line, so it needs no signed sign-in; turning one off does. Each tab shows its own switch under Advanced (**AI line on drafts you send** on Act as me, **AI line on replies it sends** on Handle it for me), and turning off the Handle it line asks first.\n\n## The mailbox client\n\n`delegation.gmail.DelegateGmail` talks to the Gmail REST API directly and is **never registered with the MCP gateway**, so the model reaches the mailbox only through the typed handler. The credential is one file per person in `DELEGATION_GOOGLE_CREDENTIALS_DIR`, named from a hash of the address (0600 in a 0700 directory), minted by `scripts/connect-own-gmail.py` on the Executive's own OAuth client with the scopes `gmail.readonly` and `gmail.compose`. It never lives in `WORKSPACE_MCP_CREDENTIALS_DIR`, where workspace-mcp picks a credential by address. Besides reading threads and saving drafts it lists the inbox and checks whether they have written to an address, reads one message or draft, lists the person's send-as addresses and deletes a draft. Its **one send method**, `send_draft`, sends an existing draft by its id and nothing else — never `messages.send`, which sends any text it is given — and unit tests pin the method set, the endpoint, the request body and its single caller. A failed request says whether it may have been carried out anyway (a timeout after connecting, a 5xx), which is what the send path needs to know. A parsed message carries when it arrived, whether it is bulk, a bounce or a calendar invite, and whether Gmail's authentication results vouch for its sender.\n\n`gmail_status` answers `connected`, `not_configured`, `needs_reconnect` (Google refused the saved sign-in — an app in Testing mode has its tokens expire after 7 days; a rate limit, though Gmail may send it as a 403, is an `error` to retry, not a reconnect), `mismatch`, `no_email`, `shared_mailbox` or `error`. `shared_mailbox` means the person's address *is* the Executive's; it is refused before asking Google, because then everything the Executive writes would look like theirs. The gateway closes the other door: every `google_workspace__*` call must act as the Executive's own account, and a `user_google_email` naming anyone else is refused and audited (see Integrations).\n\n### Outlook\n\nA person may connect an Outlook mailbox instead (work, school or personal), with `scripts/connect-own-outlook.py`: a device-code sign-in on the Executive's own Entra app (`MS365_MCP_CLIENT_ID`, tenant `MS365_MCP_TENANT_ID` or `common`) asking for `User.Read`, `Mail.ReadWrite`, `Mail.Send` and `offline_access`. It writes the same per-person file with `\"provider\": \"microsoft\"`, so a person has one mailbox for Act as me, and `gmail_for` hands back `delegation.outlook.DelegateOutlook`, which keeps `DelegateGmail`'s methods, return types and errors, so every caller above runs unchanged. It talks to Microsoft Graph directly, never through the Microsoft 365 MCP server the Executive's own Outlook uses, and is never registered with the gateway. Microsoft rotates the refresh token on use; the new one is written back into the file (atomically, keeping every other key, and only if the file still holds the old one). Graph is asked for immutable ids, so a sent draft keeps its id; a thread is Outlook's `conversationId`. Gmail's labels are mapped onto what the callers read: `SENT` only for mail in their Sent Items folder (a From line set to their address by someone else never counts), `DRAFT`, `INBOX`, and Focused Inbox's Other read as a tab. A sender counts as authenticated only when the topmost `Authentication-Results` — the one Exchange wrote, above anything the sender added — holds exactly one DMARC verdict, a pass for From's own domain, and Exchange Online Protection's own `compauth=` verdict, so a header the sender wrote on mail EOP never stamped doesn't count. `delete_draft` refuses anything that isn't a draft, and deletes with the draft's etag (`If-Match`), so a draft sent in between — it keeps its id — is left alone. No client secret is ever written into a person's file, and Graph has no signature setting to read.\n\n## Privacy\n\nWhat a person's mailbox touches is theirs. For the principal that means private to the principal, as every private row is. For a team member it means theirs alone, the principal included: an audit row carries `private_to_person` (set by `audit.rows_for_person` around the inbox watcher, a card's Send and Dismiss and their settings changes, and by `people_tools.audit_row_owner` on a turn that read their mail) and is left out of every audit read — the log, a session's timeline, a row by id, the brief — with only the usage totals counting it; their reply cards are theirs alone (above); and the owner's view of their use is counts only (drafts and sends in 30 days, and whether their inbox watcher is on). The conversation itself becomes its owner's alone before the mailbox is first read: `ghostwrite_email` marks the session `mail_private` (`session_store.mark_mail_private`, creating a channel adapter's row early, with its owner) and refuses to read the mailbox if that can't be stored or the conversation already belongs to someone else (which it then leaves unmarked); from then on only its owner may open it (`chat._session_access`), and working-style learning skips it. Every later turn there starts private (`settings.pin_turn_delegation` reads the flag and fails closed, setting `touched_mail`), so a follow-up answered from history alone is still private to its owner and teaches no memory, and the web chat's rows before the turn (the inbound message and the knowledge lookup) are theirs too. It does not start locked down: the lockdown is `read_mail`, set only by a turn that reads the mailbox or notes itself, and it is never carried into the next turn, because history keeps only the speaker's words and the Executive's replies, never the mail a tool returned. Their next message is them asking again, having read that reply, so everything runs again there. Anyone else speaking in it is not offered Act as me.\n\nOnce `touched_mail` is set, every audit row the turn writes is private (`people_tools.audit_row_private_to_principal`), and a team member's is theirs alone: the tool row (its input and result redacted, since `ghostwrite` is a sensitive tool name), the reply's `chat_turn` row that carries the preview, the model-call rows, and the background passes, which run under `private_rows`. The Honcho peer and department syncs are skipped, because peer memory is read on other people's turns. No memory is learned from the turn at all: the episodic, open-loop and working-style passes are skipped too, since its reply quotes a draft built from other people's mail. The `delegation_*` audit events are always private and carry metadata only — ids, counts and flags, never the draft or the thread. The inbox watcher is private the same way: every row a scan or a card action writes is its person's alone, and it starts no chat turn, alert, scheduled action or workflow run and teaches no memory.\n\nThe turn also keeps one door shut (`delegation.lockdown`). Anyone can put text in the inbox, and that text could try to steer the model, so from the round that calls `ghostwrite_email` or one of the mailbox reads — a round's tools run together — until the turn ends, the dispatch guard refuses only what opens the open internet or reaches everyone: outside fetches (`read_document`, research, the watchlist, `load_mcp_server`, and any MCP `call_tool` outside the private-turn set of reads and recipient-checked sends), `run_script` and `run_python_job`, workflows (they run later, unattended, and may fetch or script), broadcasts, department messages and alerts, and changes to who is on the roster or holds authority (`archive_person`, `set_department_head`, `resolve_roster_request`), and text that steers later turns (`schedule_followup`, whose intent runs unattended when due, and goals and decision outcomes, shown to every later turn). Everything else the person asks for runs, because it is fenced on its own: DMs and `message_person` reach only the roster, invites name attendees by person id, the Executive's own email checks every recipient against the roster, standing facts and profile edits keep only the person's own words, and a workflow drafted in chat is saved only once a person confirms it. `upsert_person` runs only for a contact the person asked for (`speaker_named_contact`: a contact, never the team, an approval scope or a chat account, with a word of the name in what they typed, in a message that asks to add, save or change someone, a new contact's address one they typed or one that sent the mail the turn read under the contact's name (`TurnDelegation.mail_senders`), never one the mail's text only mentions, and on an update a changed address they typed), since the roster is what the send checks trust. Any other contact add is refused with a pointer to an approval card (`lockdown.CONTACT_REFUSAL`), so the Executive leaves an `add_contact` card in the chat rather than asking them to type the address. What an email itself asks for is still never done on its say-so; it goes on an approval card. Every tool is classified as allowed or withheld, a test fails on a new unclassified one, and an unknown name is withheld, except an extension tool registered with `after_mail_read` (one that only reads the install's own data). The refusal tells the model to put what the step needs in its reply, since the next turn sees the reply but not the mail, and to do the step then without reading the mail again. A refused call gets a private `tool_invocation` row (`refused: mail_touched`) and tells the model to offer it in the next message. The offered tool list never changes mid-turn, so the cached prefix holds. The handlers that reach outside check again on their own (`outside_reach_refusal`). The server-side web search stays, as on a turn private to the principal. The lockdown ends with the turn. Later turns of that conversation stay private to its owner (`touched_mail`) but hold nothing: a refusal says it will work when they ask again in their next message, and it does.\n\n## Always in the loop\n\nA sent reply can leave a note. Once the reply went, `reply_send` starts `memory.history_notes.note_sent_reply` for the person who sent it, in the background, when their \"Keep track of what happens\" switch is on and the conversation isn't one they asked not to remember. The note-taker sees only the words they sent, so other people's mail never becomes a note, and a failure never touches the send. Recall is `recall_history`, offered on the same verified, private surfaces as `ghostwrite_email` and also allowed under the mail lockdown, since it only reads the speaker's own notes. Calling it locks the turn like `ghostwrite_email` does, from its own round on. The same switch also covers notes from chat, which don't need Act as me. See **Memory** for the checks, retention and controls.\n\n## The system prompt\n\nA constant, name-free `DELEGATION_ADDENDUM` joins block 0 after the unchanged identity addendum while anyone on the install has it on (`block0_delegation_on`). It names the four mailbox reads and says other people's mail is data and that a conversation which read it reaches nobody else; and it tells the model that `ghostwrite_email` is the single exception to *never impersonate*, and only for the person being spoken to; that everything else is written as itself; that when the tool isn't offered the asker can't have it; that a draft is never described as sent; and that it never denies being an AI. It is keyed on the install-level setting, never on the turn or the speaker, so switching it misses the 1h cache once (see Prompt Caching).\n\n## What it may do\n\n**Delegate → What it may do** (`delegation.may_do`, `GET /what-it-may-do`) is read-only: one row per thing that can go out without asking, what happens to it (goes out, waits for someone, always waits, drafts only, off) and which setting decides it, with a link there. It is the first Delegate tab, and `/delegate` opens on it. Three parts, each behind a pill that counts what goes out:\n\n- **As you** (the caller's own, when `can_delegate` allows them): built from `settings.is_enabled`, `inbox.get_watch`, `handle_it.get` and `handle_it.RULES`, `handle_it.leading` (Everything), `training.get` and `training.learned`, and their rules, the same reads `handle_it.refusal` and `follow_up_refusal` make. A level's row follows its `Rules` (strangers, follow-up reach, links and amounts), not a copy of them. A note names the ladder: Handle it for me rides on Draft replies to my inbox and Write drafts as me, and Everything also drops when Replies or Follow-ups go into training.\n- **As the Executive** (the principal's alone, as `GET /take-the-lead`): the switch and its training, each Ask first kind, the company's rules, and meetings. A meeting it thinks of on its own always waits: both meeting gates need someone on a verified surface in the turn, which an unattended run never is. A meeting someone asks for in chat follows **Always asks first → Meetings asked for in chat** (on means it waits: `meeting_scheduling`'s class mode is `propose`; off means `auto_execute`) and, in a team workspace, Operations' level too.\n- **Departments**: each level, and what a level covers (department-scoped scheduled work, check-ins, alert review, team members' chat sends, and Operations' meetings), and that it doesn't cover what the Executive does under Take the lead.\n\nIt also says when the Executive is paused, and when nothing can be sent as anyone because signed sign-ins are off. Nothing on it writes or reads mail. A contact, someone not on People, or a request with no caller (outside local login) gets 403.\n\n## How far it goes as you\n\nOne setting replaces the switches that used to turn each other off out of sight. The UI shows it as two pickers (`ReachCard.tsx`): **What it writes as you** (`WritesCard`) on the Act as me tab and **What it sends on its own** (`SendsCard`) on the Handle it for me tab; What it may do links each row to its own picker. Its steps, each adding to the one before: **Off**, **Drafts when I ask** (Write drafts as me), **Drafts for my inbox** (Draft replies to my inbox), then the Handle it for me steps that send, **Easy ones**, **People I know** and **Most mail** (`careful`, `balanced`, `bold`), and for the owner **Everything** (Take the lead as you). Act as me shows the first three as **Off**, **When I ask** and **For my inbox too** (any sending step reads as For my inbox too there). Handle it for me shows **Off** (saved as the inbox step) and the sending steps, and opens only once Act as me is at For my inbox too, with a button that turns that on; moving Act as me below it says Handle it for me stops too. `PUT /delegation/reach` (`{step}`) moves it, and `reach_of` reads the step back from the switches, so the stored switches stay the source of truth and every gate reads them as before.\n\nGoing down turns the switches above the target off, highest first (`_lead_off`, then Handle it, then the inbox watcher, then Write drafts as me), so nothing is ever on above a switch that's off; the UI says what stops and asks before it saves. A lower sending level only holds more back and is set directly, so it needs no signed sign-in. Going up calls each switch's own route in order, so every check it makes still applies: the mailbox connected, signed sign-ins for sending, the owner alone and not in training for Everything. The first that refuses stops the move at a whole step and answers with that route's error. **In training** (Replies and Follow-ups together, with **Train follow-ups too** to split them) and, at Everything, **Your rules** sit under the Handle it for me picker, and **Learn from my edits** (drafts training) under the Act as me one; neither picker changes training.\n\n## Surfaces\n\n- **Settings → Act as me** (`ActAsMeCard`, hidden unless `GET /delegation` answers, so a team member sees it once the owner lets them): the mailbox connection (`provider` says which) with both connect commands (Gmail and Outlook) and **Check again**, **What it writes as you** (above), with the inbox watcher's status under For my inbox too (in plain words, when it last checked, **Check now** and **Also save inbox replies in my Gmail Drafts**), and **How I write**: length and tone, a greeting per audience (`{first}` is their first name), the sign-off, habits and never-rules in fields that grow to show every line, the signature with **Refresh from Gmail** and **Don't add my signature** (or **Add my Gmail signature** when none is added; on Outlook only **Don't add my signature**, with why), and each example quoted with **Remove examples**. The owner also gets **Let team members use it** where the install allows it, with each team member who has it on listed by name and counts only.\n- **Today → Replies waiting** (`RepliesWaiting`, the top of the left column; hidden unless `GET /delegation/replies` answers with cards): each card shows who wrote and who they are to you, whether their address was verified, the subject, **They wrote** as plain text, your draft, **Decide before sending** (the open questions) and its warnings, with **Send** (a confirm naming who it goes to, and a second one when that or the thread changed), **Edit** (a text box on the card with Save and Cancel), **Open in Gmail** or **Open in Outlook** when the reply is in their Drafts, and **Dismiss**.\n- **Setup status**: a **Your own mailbox (Act as me)** light (`your_gmail`), amber while the inbox watcher can't reach the mailbox, is being rate-limited or has 25 replies waiting.\n- **Delegate** (main menu): **What it may do** (above, where `/delegate` lands), **Act as me** (where `/settings/act-as-me` lands), **Handle it for me** (which step the dial is at, with **Change in Act as me**, then **What it sent**: how many went today and what it sent this week, as you) and **Take the lead** (the switch, then **Always asks first**, shown even while the switch is off and ending in **Meetings asked for in chat**, and the company's rules, as the Executive). Each switch that turns another off says so beside it. The pause is on **Settings → Your Executive**.\n- **API**: `GET`/`PUT /delegation`, `GET`/`PUT`/`DELETE /delegation/voice`, `POST /delegation/voice/learn`, `POST /delegation/voice/describe`, `POST /delegation/voice/signature`, `PUT /delegation/inbox` (`{enabled?, mailbox_drafts?}`), `POST /delegation/inbox/check`, `GET /delegation/replies`, `PUT /delegation/replies/{id}/text`, `PUT /delegation/handle-it`, `PUT /delegation/reach` (`{step}`, the dial), `PUT /delegation/training`, `DELETE /delegation/learned/{id}` and `GET /delegation/handled` — the caller's own delegation only — and `PUT /delegation/team`, the owner's switch (see API Reference). `GET /what-it-may-do` is the read-only summary above. Send is `POST /decisions/{id}/approve`; Dismiss is `POST /decisions/{id}/reject`.\n- **Evals**: a scenario's `delegation:` block runs the turn against an in-memory mailbox (`evals.mailbox.ScenarioMailbox`) and hands the saved drafts to the judge (`delegation_001`–`003`). A `type: inbox` scenario runs the watcher's two model calls on one thread: whether it drafts must match the scenario, and a draft is judged on saying nothing the person hadn't, copying no link or address, and listing every open question (`delegation_inbox_001`–`007`; the last checks a draft never claims anything was sent).\n\nActing within rules the person sets and standing in for them are later, separate changes, each behind its own switch, off by default.","mermaid": "flowchart TD\n Ask[\"Principal or team member, verified<br/>'reply to Dana as me: yes'\"] --> Pin[\"pin_turn_delegation<br/>may have it? on? verified? private? attended?\"]\n Pin -->|\"offered\"| Loop[\"Executive tool loop<br/>with ghostwrite_email\"]\n Pin -->|\"not offered\"| Self[\"writes as itself<br/>(unknown tool this turn)\"]\n Loop --> Tool[\"ghostwrite_email handler<br/>caps, mailbox check, recipients in code\"]\n Tool -->|\"touched_mail\"| Private[\"turn's rows and conversation<br/>theirs alone, no memory\"]\n Tool --> Client[\"DelegateGmail or DelegateOutlook<br/>REST, outside the MCP gateway\"]\n Tick[\"Scheduler tick or Check now<br/>Draft replies to my inbox on\"] --> Scan[\"inbox scan, rows theirs alone<br/>skip rules, limits, ledger\"]\n Scan --> Client\n Client --> Box[(\"The person's own Gmail or Outlook\")]\n Scan --> Classify[\"classifier, no tools<br/>needs a reply? kind, confidence\"]\n Classify -->|\"worth a draft\"| Gw\n Voice[(\"delegation_voice<br/>How I write\")] --> Gw[\"ghostwriter<br/>no tools: voice + intent + thread\"]\n Tool --> Gw\n Gw --> Lint[\"lint: links and addresses<br/>only the person's own\"]\n Lint --> Draft[\"create_draft, threaded\"]\n Draft --> Box\n Draft --> Chip[\"chat chip: open the draft<br/>chat never sends\"]\n Draft --> Card[\"Today: Replies waiting<br/>their own card\"]\n Card -->|\"Send, confirmed\"| SendPath[\"reply_send: checks again,<br/>claim, send the draft by id\"]\n SendPath --> Box\n class Ask entry\n class Pin compute\n class Loop compute\n class Self compute\n class Tool compute\n class Private compute\n class Client compute\n class Tick entry\n class Scan compute\n class Classify compute\n class Box external\n class Voice storage\n class Gw compute\n class Lint compute\n class Draft hot\n class Chip entry\n class Card entry\n class SendPath hot","generated_at": "2026-10-15T19:07:34Z"}diff --git a/packages/core/openexecutive/architecture/prebuilt/memory.json b/packages/core/openexecutive/architecture/prebuilt/memory.jsonindex 628d65e1..e51a74ac 100644--- a/packages/core/openexecutive/architecture/prebuilt/memory.json+++ b/packages/core/openexecutive/architecture/prebuilt/memory.json@@ -1,7 +1,7 @@{"section_id": "memory","title": "Memory System",- "markdown": "The Executive's durable memory is an episodic SQLite store at `./episodic_memory.db`, managed by `openexecutive.memory.episodic`. It holds four tables:\n\n- `decisions` — choices made, with `domain`, `summary`, `rationale`, `outcome`, and `tags`. `outcome` is filled in when the principal says how a decision turned out — the `record_decision_outcome` chat tool (principal on a verified surface only) or the Memories page. The weekly review reads this table twice: the week's decisions (`decisions_since`) and up to three older than 30 days with no outcome yet (`decisions_awaiting_outcome`), which it asks about.\n- `initiatives` — tracked efforts with a `status` and `summary` (idempotent upserts).\n- `advice_given` — query/advice pairs per domain.\n- `scheduled_actions` — a dispatch queue, treated separately from recall memory. `cancel_scheduled_action` guards its UPDATE on `status = 'pending'`, so a cancel never overwrites a row the scheduler claimed a moment earlier.\n\n### What gets extracted, and when\n\n`episodic.extract_and_store` runs after a turn and asks a utility-fast model for decisions, initiatives and advice. Every candidate must carry a `user_commitment_quote` that appears verbatim in the principal's own message (`_is_valid_user_commitment`) — the turn's speaker text (`memory_text` when the entry point supplies one, else the prompt), so a quoted Executive email or a briefing card's body inside the prompt cannot satisfy it — the model has repeatedly tried to log the Executive's *recommendations* as the user's commitments, and that quote is the hard gate against it.\n\nA turn reaches the extractor if `should_extract(speaker_text, session=...)` is true, which means only that the principal said something on a surface that proved it was them — there is deliberately **no length floor**. There used to be one, on the combined user+assistant length, and on a live tenant it selected almost exactly the wrong turns: 9 of 16 exchanges were blocked, and the 9 held every instruction the principal gave, while the 7 admitted were long analytical exchanges with no commitment in them. The extractor ran 13 times and stored nothing.\n\nMoving that floor to the user's side would relocate the bug, not fix it. The canonical executive decision is a long analysis answered with \"Approve option B.\" (17 chars) or \"Do B.\" (5), and any floor high enough to skip \"Done\" (4) also skips those — \"Do B.\" and \"Done\" differ by one character and mean opposite things. Length cannot separate a decision from an acknowledgement; the verbatim-quote check can, so `_is_valid_user_commitment` is the gate that decides. The price is one utility-fast call on turns that propose nothing.\n\nThat quote check is only meaningful when `user_message` holds the **principal's** words, and on a chat channel it does not — `Executive.chat()` is reached from Slack, Discord, Telegram, Google Chat and the email poller. A teammate's line would be written to `decisions` with no speaker attached, indistinguishable from the principal's own; an inbound email body is text the sender chose, so a self-quote is free. Removing the length floor is what makes this bite — short channel traffic used to fall under it incidentally — so `should_extract` asks the untrusted-content policy (`orchestrator.content_trust.principal_speaking`) whether the principal is speaking. It names the principal's surfaces rather than inferring them: the web chat (signed in as the principal — or, on an install with no principal on the People page yet, a request that carried no sign-in; a signed-in email on nobody's entry, such as an archived teammate still allowed to sign in, is not the principal), the CLI (`Session.from_cli`), the principal's own Slack or Discord or a private Telegram chat with a valid webhook secret (`people_tools.is_principal_on_verified_surface`), and email from the principal's primary address that Gmail's own `Authentication-Results` marks `dmarc=pass` (`Session.email_authenticated`). Everything else fails closed: a teammate (on the web too), an unrostered sender, the principal's address on mail Gmail did not authenticate, Google Chat, the MCP server (its caller names themselves), unattended runs, and an unreadable roster. The rule used to be \"no `origin_channel` means the principal's own surface\", and the email poller left `origin_channel` empty, so every stranger's email ran through the extractor with its body — headers, quoted chain and all — as the principal's words, and whatever it stored rendered on every later turn. The poller now tags its sessions `origin_channel=\"email\"`, and the gate no longer reads an empty channel as trust.\n\nThe extractor also reads only the words **outside** every `<untrusted_content>` block (`schedule_extraction` runs `content_trust.strip_untrusted` first): an attached document's text is inlined in that block, so a sentence the principal did not type can never be quoted back as their commitment, and a turn that is nothing but an attachment is not extracted at all.\n\nEach pass writes a `memory_extraction` audit row — in a `finally`, so a pass that crashed is recorded too, with the exception type as its `failure` reason: how many items the model proposed, how many were stored, a `malformed` count so a pass where the model returned only garbage does not read as one that found nothing, and a `{kind, reason}` record per drop — `bad_quote` and `missing_field` for an item the model proposed, `not_a_list`, `item_not_a_dict` and `payload_not_a_dict` for a shape that was never a usable item. Every proposed item is either stored or dropped, so `proposed == stored + item drops` is the arithmetic that says whether anything was lost silently. The tool payload is not schema-checked anywhere, so a malformed shape is counted as a drop rather than raised — it used to abort the whole pass, discarding the other two kinds with it and suppressing the row, which read exactly like \"extraction never ran\". Without it, \"the model found nothing\" and \"the model found things and every one was rejected\" are indistinguishable from outside the database — which is why the failure above survived undetected and took a SQLite session on the tenant to find. A `proposed>0, stored=0` streak is the signal to watch.\n\nThe validator rejects a paraphrase, and the model paraphrases: on one install two of three real commitments were lost that way, the quote beginning \"SVN's engagement covers only …\" where the person had typed something else. So a `bad_quote` drop earns exactly one corrective call. The model is shown the rejected items and the quotes it gave, told to copy the span character-for-character (typos and casing included) or return empty arrays, and the tool is forced where the provider supports tool choice. Every retry item is validated first; a still-invalid one adds no second drop and is counted `still_invalid`. A valid item is then classified in order: its label matches a pending drop record → a recovery, stored and the record released; else its quote (terminal punctuation ignored) already supports a stored item of that kind → a re-send, ignored and counted `repeated`, so a model that re-sends everything cannot double-count `stored`; else a new proposal, stored and counted — a reworded label cannot be told from a different item, and crediting it would erase the very `bad_quote` census the row exists to show, so its original drop stands. Recovery is checked before re-send because two commitments can rest on one sentence. Malformed shapes at any level — a kind that is not a list, an item or payload that is not a dict, a response with no tool call — are counted `malformed`, so a retry that returned garbage does not read like one that obediently returned nothing. The row's `retry` block (`rejected`, `recovered`, `repeated`, `still_invalid`, `malformed`, `failure`) is always present, zeros when nothing was rejected; `rejected` is set from the complete drop list when the row is written, so neither a store failure before the retry nor a cancellation during it can zero it. The arithmetic above still holds after the retry. An exception on the retry is recorded as the retry's own `failure` and leaves the first pass's results untouched; the cost is one utility-model call, only on turns that dropped something. `memory_extraction` is a declared event type, so the audit page's filter can select it.\n\n### Standing facts (corrections that persist everywhere)\n\nA fifth table, `facts` (`openexecutive.memory.facts`, created on first write), holds facts and corrections the principal stated and asked to keep — \"Maple House is 48 units, not 52\". Before it, a chat correction's only durable home was Honcho peer memory: optional, best-effort (its prefetch times out or errors under load), re-injected only into that person's later chat turns, and never read by the briefs, the scheduled runs or the alert review. The episodic extractor cannot hold one either: it stores only decisions backed by a commitment quote, and a fact is not a commitment.\n\n- **Written from chat, by the principal or an attributed teammate.** `remember_fact` stores one (subject, statement, optional wrong value) and `forget_fact` retires one. The principal on a verified surface may do both. A teammate on the People list (a `team` row, not archived, not a contact) on a verified surface (the web app signed in, their own Slack or Discord; `fact_tools._teammate_speaker`) may call `remember_fact` only; email, Google Chat and unrostered senders are refused. Both tools are withheld from every unattended run and every turn private to the principal. Every call, `forget_fact` included (retiring a fact changes what later prompts treat as true just as writing one does), also needs `source_quote`: at least two words and eight characters, found in what the speaker typed this turn (`delegation.settings.own_words` over the pinned `TurnDelegation.speaker_text`). The `<outbound_reply_context>` backstory a Slack or Discord reply is hydrated with is stripped first, and a message with an attachment is refused outright. The quote alone only proves the principal asked, so everything `remember_fact` stores and renders (the statement, the subject shown as `[fact N] subject:`, and a previous value shown as `(corrects: …)`) is tied to their words too. An omitted previous value falls back to the replaced fact's own statement. Every figure must be a number they wrote, compared at its magnitude: `$180k` matches `180,000`, but `180m` never lets `$180k` through. Every name must also appear in what they typed: a capitalised word, or any word holding a non-ASCII letter, other than the statement's very first word (a statement is one fact, so splitting a document's names into one-word sentences exempts nothing). So must every month, weekday or quarter. A name the model writes in lower case is not caught: the gate narrows what a real quote can carry in; it does not prove a paraphrase. A real quote therefore cannot carry a document's figure, name or date in with it (\"Cedar Court's lease expires in March\" after \"remember what the lease doc says\"), while a paraphrase of what they said still passes. So the model cannot store its own inference, a document's figure or text quoted back at the principal as something they said. Every audit row the tools write, and the chat loop's `skill:` dispatch row for them (whose input quotes the principal verbatim), is private to the principal (`executive._private_tool_row`). Those rows tie a fact to the principal's session and turn, which `GET /memories/facts` hides from teammates, and a teammate can read any non-private audit row. The handlers run in a worker thread (`asyncio.to_thread`, which carries the turn's context), and the chat and committee paths, the alert review, the morning brief's synthesis and the end-of-day, weekly-review and reflection workflows read the block the same way, so SQLite, the profile file and its lock never block the event loop the SSE streams share. The principal's own email may ask too: the change is checked the same way, then held until they confirm it by replying to a one-time token sent to their own address (see Integrations → Standing facts by email).\n- **Provenance and attribution.** Each row keeps the quote, the channel (`web` or the adapter), `session_id`, `turn_id`, the recording person and the time, plus `recorded_by_role` (`principal` or `teammate`) and, for a teammate, `recorded_by_name` as the People list had it. Rows written before these columns existed read as the principal's (`_migrate` adds the columns on the first write; the read-only render tolerates a DB that has none).\n- **One active fact per subject.** A new row supersedes any active row with the same folded subject key, or the id named in `replaces_fact_id`, in one transaction. The old row stays as `superseded` (with `superseded_by`), and the new one is stored as a `correction` carrying what it replaced. Retiring sets `retired` with a reason. **The principal outranks a teammate:** a teammate's write that would replace an active fact the principal set (by subject or `replaces_fact_id`) raises `PrincipalFactConflict`, and the tool stores it as `proposed` instead, naming the fact it would replace (`replaces_fact_id`); teammates replace each other's facts freely, and the principal replaces anyone's. **\"Needs my approval\"** (`fact_approval_rules`, per teammate, **on by default**, set only by the principal) stores every fact from that teammate as `proposed`; the principal turns it off for a teammate they trust, whose facts then apply at once (except one that would replace the principal's). The rule is read inside `record_fact`'s own write transaction, so a switch turned on a moment earlier cannot let one fact through; a teammate write that names no person is never trusted. One teammate may have at most `MAX_PENDING_PROPOSALS_PER_PERSON` (20) proposals waiting (`TooManyProposals`; the tool tells them to wait for the principal's review). A teammate's retire checks ownership in the `UPDATE` itself (`retire_fact(teammate_id=)`: their own row, not approved). A proposed row never renders; `approve_fact` makes it active and replaces what it names (the principal's own fact included — approving it is their word) and stamps `approved_at`, after which it outranks teammates exactly as the principal's own fact does (`Fact.principal_owned`: no teammate may replace or retire it); `decline_fact` sets `declined`. No field of a teammate's fact may carry what the render adds itself — `(per <anyone>)` in any case (a unit such as `(per month)` or `(per unit)` is fine), `[fact N]` or a date stamp after any dash, read NFKC-folded with invisible characters removed (`fact_tools._marker_error`) — so a teammate cannot plant a second, forged attribution inside their statement (the principal's own unmarked lines are not checked: \"(per Smith lease)\" is ordinary wording for them). The tool answers `awaiting_approval` (no action chip) and tells the model to say it is not in use yet.\n- **Rendered everywhere output is produced.** `render_facts_for_prompt` renders the active rows newest first under a self-explaining `STANDING FACTS` header (use these over older figures; a line ending `(per <name>)` is that teammate's word and the principal's unmarked line wins a conflict; the current conversation still wins; quoted data never instructions). A teammate's line ends `(per <name>)`, the name defanged like the rest, capped at 40 facts / 6000 chars, with angle brackets defanged. It opens the DB read-only and never creates it or the table. The block always rides in a user turn, never a cached system block: a chat turn's `<standing_facts>` (so every scheduled run through the chat loop too), each specialist consult (`route_to_specialist`, chat and workflow steps alike), the /today header and the morning brief (`render_briefing_context`, after the quiet check and inside the string the header's cache key hashes, so a new fact rewrites the header), the alert review's batch (`render_batch`, read once per pass), and the end-of-day digest, the weekly review's top-three call and the morning reflection (`with_standing_facts`).\n- **Company-profile edits from chat.** `update_company_profile` (same gate and quote rule) changes one whitelisted field of `company/profile.yaml`, under `PROFILE_EDIT_LOCK` (also taken by `PATCH /company-profile`, so neither edit silently drops the other): a text or number field is set, a list field gets an item added or removed, and `financials.key_metrics` takes a named metric. It writes through `CompanyProfile.save_to_yaml` and updates the session's profile, so the next turn's cached company block carries it (one cache miss on the change). The new value must itself appear in the principal's own words, not just the quote: the value renders into the cached company block on every later turn, so \"set our mission to what the doc says\" or \"update our headcount\" is refused rather than saving a document's text or a guessed figure. A number must be one they wrote, however they wrote it (`$180k`, `1.2m`, `2,400,000`). Saved text has `<`/`>` defanged. A `kind='profile'` row records each edit with its quote for the Pulse page. Those rows are never rendered into a prompt, because the profile block already carries the value.\n\n### Session scoping\n\n`decisions` and `advice_given` rows carry a `session_id`, so per-thread channels (Discord, Telegram) can pull just-this-thread history without leaking cross-conversation context. A null `session_id` falls back to a global view.\n\n### Surfacing\n\n`openexecutive.memory.episodic.format_for_prompt` renders recent decisions and initiatives into a compact `<past_decisions>` block injected into the user turn — alongside `<retrieved_context>` and peer memory — never into a cached system block. Each decision names where it was recorded when that was a channel — `- 2026-09-01 [finance] (via email): …`, from the prefix of its `session_id` (`email:`, `slack:`, `discord:`, `telegram:`, `google_chat:`); a web or CLI decision has no tag. Rows extracted from mail before the untrusted-content policy, when any sender's body could be stored, therefore read as mail rather than as the principal's own word.\n\nScoped to a session, decisions and advice cover every conversation of a chat app's stream (`memory.conversation_ids.family_clause`): a Telegram chat or a DM is cut into conversations after two quiet hours or a /new (`memory.conversations`), and what an earlier conversation decided still renders in the next.\n\nThe chat route also injects a `<briefing>` block into the same user turn: a compact digest of the current open (unread) alerts, built by `openexecutive.briefing.context.format_open_alerts_for_prompt` (company-wide, `status=\"unread\"`, mirroring `/today`). This is what lets the Executive discuss a briefing item the principal clicked or named on `/today` (e.g. \"Gulf Coast Port Cyberattack\"). It is resolved in parallel with the other context fetches, omitted when there are no open alerts, and never placed in a cached system block.\n\nOn the Pulse page the Memory section shows the three lists as Decisions, Initiatives and Advice tabs, then a **Corrections** tab (`GET /memories/facts`: active standing facts and profile edits with their quote, channel and — for a teammate's — their name; proposals first under \"Waiting for your approval\" with **Approve** / **Decline** for the principal; the replaced, retired and declined history folded away; **Retire** on any fact for the principal and on their own not-yet-approved one for a teammate; and, for the principal, a per-teammate \"needs my approval\" switch), and a **History** tab for the person's own Always in the loop notes (see below). The header's Memories tile counts the three lists. What peer memory has learned about the signed-in person is theirs alone, so it is not on Pulse: it is on **Settings → About you** (see the peer memory section).\n\nThe same user turn carries a `<drive_memory>` block when the conversation has touched Google Drive (`openexecutive.memory.drive_reads`). Drive is reached only as live Google Workspace calls inside a turn and history keeps only prose, so without it a file found one turn was gone the next. `MCPGateway.call_tool` hands each `search_drive_files` and `get_drive_file_content` result to `record_drive_result`, which keeps, per session, every file found or opened (file id, name, type, link, and for an opened file its first 600 characters) and every search that matched nothing, with its query. `format_drive_memory` lists the 20 most recent files, so \"the file you found earlier\" resolves to a file id the Executive reopens rather than searching again, and the queries that found nothing (dropped once the same query later finds something). Rows are keyed on the session *and* the speaker, and shown only to that speaker in that session, because one session can span several people (an email thread, a Slack or Discord thread). Nothing is recorded or shown without a bound `current_session` and a rostered speaker, on a turn private to the principal, or on one that touched the speaker's own mailbox (Act as me). workspace-mcp writes file names into its output unescaped, so a name containing a newline can forge a result line. Only a Drive-shaped file id, type and `docs`/`drive.google.com` link are therefore kept; any other line is dropped, and the name is always quoted as the file's own content, not instructions. Each speaker keeps at most 100 files and 100 searches per session, older rows are pruned on write, and `session_store.delete_session` drops them all.\n\nA conversation can also become its owner's alone. When Act as me first reads the speaker's own mailbox in it, `session_store.mark_mail_private` sets `sessions.mail_private` (creating the row with its owner when a channel adapter hasn't written it yet), and from then on only the session's owner may open, continue or delete it — the principal included, when it is a team member's (`chat._session_access`). It is never cleared. Beside it `sessions.mail_read_at` keeps how many history messages the conversation held before the last turn that read the mail (`session_store.mail_read_at`; NULL on rows marked before the column): Act as me's hold on links and scripts in later turns lasts only while that turn is still in the history window (see Act as me). \n\nThe chat list has owner controls on the same row: `sessions.pinned_at` (pinned chats list first) and `sessions.title_locked` (set by `rename_session`, after which `update_session_title`, the automatic title, leaves the name alone). A `session_shares(session_id, person_id, shared_by_person_id, created_at)` row adds one team member to someone's chat (`list_shared_with_person`, `set_shares`, `leave_share`): they read and write in it with its owner, each of their messages saved with their own `sender_person_id`; a `mail_private` chat is never shared or opened that way, and deleting the chat drops its shares. `last_turn_sender` says who wrote the last turn, which is how redo stays with the person who asked. The chat list's preview puts `You:` only before the caller's own words. `rewind_last_turn` deletes a web chat's last turn (the last reply and the user messages after the reply before it) so it can be asked again; the next turn's history is re-read from these rows, so nothing else needs clearing. A search that matched nothing also gains a note in its tool result: say the exact query and that it found nothing, never that the file does not exist. This is a first step: Drive is still not indexed into the company collection.\n\n### System of record\n\nSQL is the system of record; the peer-memory service is a recall layer mirrored from it, not a replacement. When `store_decision` / `store_initiative` / `store_advice` insert a row whose `department` is non-empty and not `\"general\"`, the row is mirrored as a kind-tagged note into that department's peer via `append_department_note`. The mirror fires only after a successful INSERT, is fire-and-forget, and never rolls back the SQL row on peer-memory failure. `scheduled_actions` is never mirrored — it is a queue, not memory.\n\nThe episodic extractor still learns only from the principal's own words. Commitments and asks from everyone else on the roster are tracked as **open loops** (see Attunement) — `scheduled_actions` rows with `kind='open_loop'`, opened and closed by a separate quote-gated pass after each attributed turn. That pass depends on `chat_messages.sender_person_id`, which records who actually wrote each persisted user message. An open loop counts toward `list_awaiting_replies_by_person` only once it is due, and `list_scheduled_actions(exclude_internal=True)` filters `__internal__` rows in SQL so readers that want real sends are not starved by them. `mark_outbound_context_consumed` also resolves the Attunement outcome row for that DM as `replied` — a matched reply is the clearest sign proactive outreach landed — and a real change to an existing initiative (`store_initiative` / `update_initiative`, new status or summary) marks the updater's own check-in nudges `acted` — an update with no known updater, such as `PATCH /memories/initiatives/{id}`, credits nobody.\n\n### Workspace settings\n\nThe same database holds one row of settings that are not memory: `workspace_settings` (`openexecutive.memory.workspace_settings`) — the install's mode (`team` by default, or `solo` for one person using Open Executive just for themselves), the user's IANA time zone, the principal's role (`PrincipalRole`: `role_kind`, `role_title`, `reports_to`, `remit`, `measured_on`, all nullable; only solo mode reads it), and the company's own email domains (`company_domains`, a JSON list, or NULL to derive them from the principal's primary address — `people.identity` matches a teammate by local part on them; `validate_company_domains` lowercases, dedupes and sorts, allows at most 10 plain DNS names and refuses a free-mail provider's, and a stored value that no longer validates reads as NULL). It is a table of its own rather than a company-profile field because onboarding rebuilds the profile from scratch. Every read is fresh and read-only (a missing file or table reads as the defaults; a table from before the role or `company_domains` columns reads them as unset and is migrated additively by the next init or write). A read error (a locked database, say) also reads as the defaults, so `get_workspace` then says team; `read_stored_mode` is the strict read of the mode alone — None when the row cannot be read or holds no valid mode — for the scheduler's weekly-review check, which must not take a failed read for team. A session may carry an explicit `workspace_mode` override; otherwise the mode is read fresh at the start of each turn and pinned on the session for that turn only (`Session.turn_workspace_mode`, via `pin_turn_workspace_mode`), so every tool handler in the turn sees the mode its persona and tools were built in. `effective_workspace_mode` reads override, then the pin, then the setting; `effective_principal_role` reads a session's `principal_role` override, then the role pinned for the turn (`Session.turn_principal_role`, via `pin_turn_principal_role`), then the stored role. See Org for what solo changes and Scheduler for the time zone.\n\n### Act as me\n\n`initialize_db` also creates Act as me's per-person tables (`delegation.schema.ensure_schema`): `delegation_settings`, `delegation_voice` and `delegation_voice_history`. They hold a setting and a writing profile rather than memory, and nothing in them is mirrored to peer memory. A turn that touched the speaker's own mailbox teaches no memory: the episodic, open-loop and working-style passes are skipped along with the Honcho peer and department syncs, since its reply quotes a draft built from other people's mail. See **Act as Me (Delegation)**.\n\n### Always in the loop (notes of what you said)\n\nA person can keep private, dated notes of what they said, in chat with the Executive and in email replies it drafted for them: what they promised, agreed, declined, answered, asked for or shared. The switch is per person (\"Keep track of what happens\", `history_person_settings.reply_notes`, off by default, one switch for every channel). Any team member on the People list may turn it on (`history.can_keep_notes`: kind `team`, not archived, the principal included); Act as me isn't needed, though notes from email replies only come through it.\n\n- **Where notes come from: chat.** After each chat turn, on both the single-voice and the committee path, the Executive's post-turn block calls `memory.history_chat.schedule_chat_notes` next to the open-loop and style passes, except on a turn that touched the speaker's mailbox. It reads only what the speaker typed this turn (`delegation.settings.own_words`: no backstory an adapter added, nothing when a file came with it), never the reply and never anyone else's message: every channel calls the Executive with the one speaker's message, and what other people say to each other is never read. It runs only for a speaker the turn verified (`history_chat.verified_speaker`): the turn's `caller_person_id` is them, nobody started it by email or runs it unattended or for them, and the surface proved who they are (the web chat signed in or a local install, the principal or a team member on their own Slack or Discord, a private Telegram chat behind a valid webhook secret, or a channel whose adapter verified the sender itself and set `Session.speaker_verified`). A shared Slack or Discord thread counts: the notes stay private and are read back only where nobody else can see them. A message under 40 characters is skipped, and each person gets at most 40 passes a day, counted in `history_chat_passes` so the cap holds across workers and restarts. The pass uses a constant `CHAT_PROMPT` (requests to the assistant, questions and small talk are not notes), the same `record_notes` tool and the same `check_note` gate with the message as both body and allowed words; the note's channel is the inbound channel or `web`, its conversation the session id, and it names no counterpart.\n- **Where notes come from: email.** After `delegation.reply_send` sends a reply, it starts `memory.history_notes.note_sent_reply` in the background. The note-taker reads only the words the person sent (`email_poller.sender_new_text` strips quoted mail) and the recipients' names, cut to four words of name characters (`history_notes.short_name`): never the mail being answered, nor the subject, which others in the thread write too, so nothing another person wrote can become a note. One forced `record_notes` call with a constant prompt and no other tools returns at most three notes. Code then drops any note that says more than they did: the `quote` must appear word for word in what they sent, every figure in the summary must be in the quote, every name or date word must be in what they sent or the recipients' names, at least half its other content words must be theirs, the summary carries no link or address, and a `due_date` is kept only for something promised or agreed. Notes record events, never instructions, and carry `trust = high` because they rest on the person's own words.\n- **Whose they are.** Every note is private to its person (`visibility = private`). Nobody else reads it, the principal included; there is no shared note.\n- **How long they last.** The company default is 90 days (`history_settings.retention_days`, the principal's choice of 30, 90, 365 or until forgotten). A person may only choose a shorter time; shortening the company time clamps everyone's choice and re-dates live notes. A pinned note never expires; unpinning restarts its clock, and a later retention change counts from there. Reads skip expired notes and the scheduler's alert sweep deletes them (`history.sweep_expired`).\n- **What a person controls.** Through `/memories/history` they read, search, pin, correct and forget their own notes. On the Pulse page this is the **History** tab, last in the Memory section and shown only to someone with notes to see (signed in and on the People list): each note shows its kind, who it was with, the date, the person's own words, any due date and when it will be forgotten, and its menu holds **Correct** (a side panel; \"Use the original\" clears a correction), **Pin**, **Don't remember this** and **Forget**. \"Don't remember this\" forgets every note from that conversation and adds it to `history_excluded`, so it is never noted again. Settings → **Memory** holds the switch (\"Keep track of what happens\") and a shorter time for their own notes, and the company time, which the principal changes and everyone else reads. A chat note shows the channel alone (\"Slack\", \"Web chat\").\n- **Recall.** `recall_history` (`orchestrator.history_tools`) is offered only on a turn where the speaker may read their notes: verified as above, a team member who may keep notes, in a conversation private to them (`history_chat.private_chat`: the web chat, a Slack or Discord DM, a Telegram chat, or one its adapter marked `Session.private_chat`), with their switch on. Before any note is read the turn is set `touched_mail`, for the principal too, so its rows are private to the speaker, it teaches no memory and the mail lockdown holds from that round on. The conversation is also marked theirs alone (`session_store.mark_mail_private`), so every later turn in it is private the same way (the lockdown is that turn's alone) and, for a team member, the principal can't open it; recall refuses if that can't be stored. Notes come back in a `<history_notes>` block as history to cite: the date, the person's own words first, then how they were noted. With `due: true` it lists only notes with a due date, from a week overdue to two weeks ahead, soonest first (\"what's due today?\").\n- **In the owner's briefs.** The morning brief adds a FROM YOUR NOTES — DUE SOON block (`memory.history_brief.due_soon_block`: what the owner promised, agreed or asked of someone, from a week overdue to a week ahead, in the workspace's local dates) and the end-of-day digest a FROM YOUR NOTES — TODAY block (`noted_today_block`: what they promised, agreed, asked or declined since the last digest, then what is due tomorrow). Both only on the scheduler's delivery to the owner alone (`morning_brief.PRINCIPAL_DELIVERY`), never a run started from chat, whose tool result lands in the turn's shared audit row and peer memory; only when the owner may keep notes and has the switch on (`history_brief.owner_keeping_notes`), and only the owner's own notes. A run that used any is marked `private_to_principal`, so the shared run history keeps `PRIVATE_RUN_ARTIFACT` instead of its text, and the note ids with their state (overdue, today, soon) enter the brief's fingerprint, so one falling due un-suppresses an unchanged brief. Teammates get no brief, so their notes reach them only through recall and reminders.\n- **In Act as me drafts.** The ghostwriter gets a `<writer_noted>` block (`memory.history_drafts.notes_for_draft`): the writer's own notes from earlier Act as me replies that every recipient of the new draft was on, with their switch on. It keeps the draft consistent with them and turns a contradiction into an open question on the card; it never adds anything from them (see Act as me).\n- **Due-today reminders.** `memory.history_reminders.maybe_remind`, called from the scheduler tick every 15 minutes between 09:00 and 18:00 local time, sends each person with the switch on one message on a day something they promised or agreed to by email (`source = approved_reply`) falls due. Chat promises are left to open loops, which the nudge engine already chases. The message says only how many things are due, never what or to whom, and the channel senders' audit rows for it are private to the person (`audit.context.rows_for_person`; the owner's `private_rows`), which also keeps the send off the shared activity rail (`_record_send_to_activity` skips a send whose rows are private). The person asks \"what's due today?\" in a private conversation and `recall_history` answers. It goes to their own Slack or Discord DM, a private Telegram chat (`delivery_order` skips a negative group id, for the owner's briefs too) or their own email (`scheduler.runner.deliver_to_person`), never a shared channel. `history_reminders` holds one row per person per day, claimed before sending and never released, so two workers never both send and a half-failed send is never repeated; a failed one waits for the next due day.\n- **Not peer memory.** Notes never reach Honcho, episodic extraction, standing facts or another person's turn. The tables (`history_notes`, `history_settings`, `history_person_settings`, `history_excluded`, `history_chat_passes`, `history_reminders`, created by `history_schema.ensure_schema` from `initialize_db`) swap with a client slot and are cleared by a factory reset.\n\n### Conversation review (fixing what replies left undone)\n\n`memory.chat_review` looks back over a chat once it has been quiet `CHAT_REVIEW_QUIET_MINUTES` (30) and fixes what the replies left undone: \"I sent it\" answered with \"noted\" and the draft still waiting, \"drop that reminder\" answered with \"sure\" and the reminder still set. The claim check (`orchestrator.claim_check`, see Lifecycle) catches a false claim in the same turn; this catches the rest.\n\n- **What is recorded.** On both the single-voice and the committee path the post-turn block calls `record_turn` with the speaker's own words (`delegation.settings.own_words`), the reply and the tools the turn ran (`_stream_agent_loop(calls_out=)`). Only a verified speaker's turn is kept: the principal on a surface `people_tools` verifies, or a rostered teammate on their own signed-in web chat, Slack or Discord. An adapter's own `speaker_verified` is not enough; an email, an unattended run, a turn private to the principal, one that touched the speaker's mailbox and a message with an attachment are never kept. Rows live in `chat_review_turns` for 7 days, a turn graded a miss (below) for `MISS_KEEP_DAYS` (90); each row also keeps the audit `turn_id` of the turn, so the claim check's row can be joined back to it.\n- **When.** Each kept turn makes sure one `chat_review` `__internal__` action is waiting for the conversation (`channel_ref` = session id), due 30 minutes on. The runner marks it done and calls `run_scheduled`, which schedules a fresh one if a newer turn arrived meanwhile, else reviews the oldest unreviewed turns (at most 20, the rest in a review right after) and marks exactly those reviewed, so a chat is read in parts and never twice. `CHAT_REVIEW_MAX_PER_DAY` (10) caps each person's passes a day (`chat_review_days`), so one person's chats can't use up another's.\n- **The pass.** One small tool loop per person on `CHAT_REVIEW_MODEL` (default `ROUTING_MODEL`), at most 5 rounds and 8 changes, in its own task with a session rebuilt from the recorded surface and caller and a delegation pin holding their words, so each tool runs through the chat tool's own handler and checks: `list_open_loops` / `close_open_loop`, `remember_fact`, `list_followups` / `cancel_followup` / `move_followup`, `leave_out_of_brief`, plus `learn_reply_style` (a working-style rule), `learn_writing_style` (a habit or avoid line in their Act as me voice profile, only for someone who may use it) and `raise_in_brief` (one line for the next brief). Every change carries `source_quote` of at least four of the person's own words (`fact_tools._quote_error`), and the thing it changes (the loop's or follow-up's text, the fact, the brief item or line) must share two words with what they wrote (its only one, for a one-word target) A chat draft's state is left to the brief's own check of the mailbox's Drafts. The replies are shown as `<untrusted_content>` (they quote mail and documents) and tool results not at all, only the tools' names. `leave_out_of_brief` and `raise_in_brief` are the principal's only; dropping a fact and changing a goal are left to chat. It never sends, books, deletes or grants permission to act, and nothing it does is said in chat. One `chat_review` audit row per pass lists the changes.\n- **Grading (looking back at how it went).** Before the fix loop, the same pass grades each turn it reads with one forced-tool call (`grade_turns`) on the review model. The grader sees what the fix loop sees plus one SIGNALS line per turn, joined from where the product already records them (`turn_signals`): a 👍/👎 and its note on the saved reply (`chat_messages`, matched to the recorded reply by its first 120 characters, which also gives the Reflection screen the reply's `message_id`), a reply the person stopped (`stopped`), a turn they took back to ask again (a `session_rewound` audit row after a turn whose reply is no longer in the chat), a claim the reply made that no tool backed (a `claim_check` audit row with the turn's `turn_id`), and a tool whose recorded result reads as an error. Per turn it records `fine`, `miss` or `unclear`; for a miss, `wanted` (what the person wanted instead, one or two sentences) backed by a `quote` of at least four of their own words from that turn or the ones after it, code-checked (`accept_grades`) or the turn is `unclear` and `wanted` dropped, plus the `kind`: `company` (a term, a fact, a preference, which specialist to ask, doing a thing rather than promising it would have fixed it) or `product` (a tool failed or was refused, a capability it lacks). A turn the model skipped is `unclear`. Grades go on the row (`verdict`, `kind`, `wanted`, `signals`, `graded_at`, `message_id`), and each person's weekly count of graded turns and misses on `chat_review_weeks`, so the rate outlives the 7-day rows. Grading changes nothing in the workspace and never blocks the fixes: a failed grade leaves the turns ungraded. The pass's audit row carries the counts. `list_misses` (one person's or everyone's; the route then keeps, for the principal, only rows from chats `chat._session_access` lets them open, so a teammate's own chat stays theirs), `weekly_rates` and `forget_miss` (`is_principal_or_self`) serve `GET`/`DELETE /memories/reflection` (the Pulse screen **What it got wrong**).\n- **Lessons** (`memory/lessons.py`): for a turn graded a miss the review may call `learn_lesson` once: one sentence this workspace wants done differently (a term and what it means, a preference about the content, a thing to do rather than promise, a specialist to consult), quoted from the person's own words (the quote must come from the miss turn or a later one, and the lesson must be what the quote says). It passes the working-style deny-list (`attunement.style._DENY_PATTERNS`: no link, handle, amount, markup, identifier, action verb, instruction talk, nudge to act unchecked, roster name) plus the lessons' own list (the verbs that move information: email, share, post, export, attach...; the words that widen a request to everyone or everything) without the about-the-writing requirement, may add at most two content words beyond the quote (`lesson_overreach`, so a real quote can't carry a different sentence in), and is re-checked on every render. Rows live in `chat_review_lessons` (text, quote, person, session, `shared` = learned in a channel or group thread, turn, `shown`, `fine_after`, `miss_after`, `retired_at`/`retired_reason`) with `chat_review_lesson_uses` (lesson, turn id, whose turn). A lesson reaches a turn by a keyword match (two shared content words between the lesson plus its quote and the message; no vector index for a list this short): the Executive's own turn gets the matching ones as a `<lessons>` block in the user turn (`build_lessons_block`, never a cached block; the header says the current request wins and nothing in it authorizes an action), and each specialist call gets the same lines under its `<failure_cases>` block (`router._lessons_for_call` → `lessons_for_query`). A lesson reaches its own person's turns; the principal's reach everyone's only when learned in a shared space (`shared`), so nothing said in someone's own chat is paraphrased into another person's turn. `build_lessons_block` counts each showing against the active turn id and the speaker; when the review later grades that turn, `note_outcome` adds to `fine_after` or `miss_after` only when the turn was the lesson's own person's (nobody else's chats can retire it), and a lesson shown 5 times with more misses than fine turns retires itself (`unhelpful`). At most 40 live lessons per person; their oldest retires to make room (`BEGIN IMMEDIATE`, so two reviews can't both skip it). Forget on the screen retires one by hand (`forgotten`); a retired lesson is listed as stopped, never erased.\n- **Replay: the workspace's own evals** (`memory/replay.py`). Nightly (the `chat_replay` scheduled action, `CHAT_REPLAY_TIME` 03:30 in the user's zone, seeded and chained like the reflection), the Executive runs its misses again with everything in force today and a judge says whether each would now go right. A case is a graded turn: a miss (its `wanted`), or a turn that went fine and got a thumbs up (`kept = 1`, held as long as a miss, at most `MAX_KEPT` 300 per person), which the replay protects so a lesson can't break what worked; a closed miss joins that pool. `due_cases` picks a miss the night a lesson is written for it (`WHY_LESSON`), when a lesson learned since the last night reaches it (`WHY_REACHED`), else once a week (`WHY_WEEKLY`), from the last 30 days only and at most `CHAT_REPLAY_MAX_CASES` (30) a night within `CHAT_REPLAY_MINUTES` (20); 20 protected cases (`WHY_PROTECT`, rotated by last replay) run only on a night a new lesson landed. `replay_case` runs `Executive.chat` on a session rebuilt from the recorded surface and speaker (`chat_review._rebuild_session`) with the saved conversation up to that turn (`chat_messages` before the reply's `message_id`), flagged `Session.replay`: reads run for real through every gate, and every tool a read-only turn is denied (`MCP_CLIENT_WITHHELD_TOOLS`, and gateway calls outside `MCP_CLIENT_MCP_TOOLS`) returns \"done\" and lands in `Session.replay_calls` instead (`faked_handlers` / `faked_call_tool`, wrapped outermost in the agent loop); scripts, Python jobs, `load_mcp_server`, Act as me's tools, `recall_history` and extension tools are not offered at all; nothing a replay does is kept (no extraction, open loops, style, notes, review or Honcho mirror, and `build_lessons_block(count=False)` counts no showing). The judge (`CHAT_REPLAY_JUDGE_MODEL`, else `EVAL_JUDGE_MODEL`, else Sonnet; `evals.judges.judge_message`) reads the original date, the person's words and the conversation before, what they wanted (or the reply they liked), today's reply and the recorded actions, and answers `{passed, time_bound, notes}`, intent and action rather than figures; an unreadable answer is a fail. The gate (`_settle`): a miss that passes is `closed` with `closed_at`; a time-bound one becomes `evidence` and is not replayed again; a lesson for a miss that still fails on `LESSON_FAILS` (2) judged replays after it was learned retires (`replay`); a protected case that fails reopens a closed miss and counts a strike against each new lesson of the same person that reached it (a teammate's turn never retires the principal's shared lessons), which retires at `PROTECT_FAILS` (2) such strikes, so one judged turn, or one message written to fail the judge, is not enough. A case that didn't run (an error, the `CASE_SECONDS` timeout) is recorded with `ran = 0` and settles nothing. The judge's input is scrubbed like outside content (`content_trust._scrub`) with the prompt's own tag names renamed inside it. Every replay is a `chat_review_replays` row (the reply and recorded calls; dropped with its turn when a miss or chat is forgotten or purged, `chat_review._prune_replays`) and a `chat_review` audit row (actor `chat_replay`); each night a `chat_review_replay_runs` row, written before the first case (so a second runner sees nothing new) and filled in after, which is also what \"new since the last night\" means. The nightly Executive carries the scheduler's MCP gateway, so the reads a miss needs run as they did. The Reflection screen's number, \"of the N things that went wrong in the last 30 days, M would go right today\" (`summary_for`, over the misses the caller sees), and each miss's last replay come from these columns on `chat_review_turns` (`replay_state`, `replayed_at`, `closed_at`, `replay_count`, `replay_notes`). Off with `CHAT_REPLAY_ENABLED=false` or when the review itself is off.\n\n## Decision ledger\n\n`openexecutive.memory.decision_ledger` keeps one `decision_instances` row per gated action — a meeting the Executive proposes to book, an Act as me reply card — with how it was resolved, so each class has a reliability record. Every status change is a compare-and-set. A tap with an outside effect (sending an email) claims the row first (`claim_for_execution`, proposed → executing), so of two taps only one acts, and finishes it as `approved_unchanged`, `approved_with_edit` or `failed`, or hands it back (`release_claim`). A row whose class acted on its own with nobody tapping — `gate_mode` `auto_execute`, as Act as me's **Handle it for me** replies are — finishes as `executed` instead, with no resolver, so a reliability read never counts it as an approval. A send whose result is unclear stays `executing` for a reconciler and is never retried. A row still waiting can have its payload changed only by compare-and-set (`update_open_payload`, on `proposed` and, when given, on the payload as it was read): that is how an Act as me reply card takes the person's edit, or records the draft made for it at Send.",+ "markdown": "The Executive's durable memory is an episodic SQLite store at `./episodic_memory.db`, managed by `openexecutive.memory.episodic`. It holds four tables:\n\n- `decisions` — choices made, with `domain`, `summary`, `rationale`, `outcome`, and `tags`. `outcome` is filled in when the principal says how a decision turned out — the `record_decision_outcome` chat tool (principal on a verified surface only) or the Memories page. The weekly review reads this table twice: the week's decisions (`decisions_since`) and up to three older than 30 days with no outcome yet (`decisions_awaiting_outcome`), which it asks about.\n- `initiatives` — tracked efforts with a `status` and `summary` (idempotent upserts).\n- `advice_given` — query/advice pairs per domain.\n- `scheduled_actions` — a dispatch queue, treated separately from recall memory. `cancel_scheduled_action` guards its UPDATE on `status = 'pending'`, so a cancel never overwrites a row the scheduler claimed a moment earlier.\n\n### What gets extracted, and when\n\n`episodic.extract_and_store` runs after a turn and asks a utility-fast model for decisions, initiatives and advice. Every candidate must carry a `user_commitment_quote` that appears verbatim in the principal's own message (`_is_valid_user_commitment`) — the turn's speaker text (`memory_text` when the entry point supplies one, else the prompt), so a quoted Executive email or a briefing card's body inside the prompt cannot satisfy it — the model has repeatedly tried to log the Executive's *recommendations* as the user's commitments, and that quote is the hard gate against it.\n\nA turn reaches the extractor if `should_extract(speaker_text, session=...)` is true, which means only that the principal said something on a surface that proved it was them — there is deliberately **no length floor**. There used to be one, on the combined user+assistant length, and on a live tenant it selected almost exactly the wrong turns: 9 of 16 exchanges were blocked, and the 9 held every instruction the principal gave, while the 7 admitted were long analytical exchanges with no commitment in them. The extractor ran 13 times and stored nothing.\n\nMoving that floor to the user's side would relocate the bug, not fix it. The canonical executive decision is a long analysis answered with \"Approve option B.\" (17 chars) or \"Do B.\" (5), and any floor high enough to skip \"Done\" (4) also skips those — \"Do B.\" and \"Done\" differ by one character and mean opposite things. Length cannot separate a decision from an acknowledgement; the verbatim-quote check can, so `_is_valid_user_commitment` is the gate that decides. The price is one utility-fast call on turns that propose nothing.\n\nThat quote check is only meaningful when `user_message` holds the **principal's** words, and on a chat channel it does not — `Executive.chat()` is reached from Slack, Discord, Telegram, Google Chat and the email poller. A teammate's line would be written to `decisions` with no speaker attached, indistinguishable from the principal's own; an inbound email body is text the sender chose, so a self-quote is free. Removing the length floor is what makes this bite — short channel traffic used to fall under it incidentally — so `should_extract` asks the untrusted-content policy (`orchestrator.content_trust.principal_speaking`) whether the principal is speaking. It names the principal's surfaces rather than inferring them: the web chat (signed in as the principal — or, on an install with no principal on the People page yet, a request that carried no sign-in; a signed-in email on nobody's entry, such as an archived teammate still allowed to sign in, is not the principal), the CLI (`Session.from_cli`), the principal's own Slack or Discord or a private Telegram chat with a valid webhook secret (`people_tools.is_principal_on_verified_surface`), and email from the principal's primary address that Gmail's own `Authentication-Results` marks `dmarc=pass` (`Session.email_authenticated`). Everything else fails closed: a teammate (on the web too), an unrostered sender, the principal's address on mail Gmail did not authenticate, Google Chat, the MCP server (its caller names themselves), unattended runs, and an unreadable roster. The rule used to be \"no `origin_channel` means the principal's own surface\", and the email poller left `origin_channel` empty, so every stranger's email ran through the extractor with its body — headers, quoted chain and all — as the principal's words, and whatever it stored rendered on every later turn. The poller now tags its sessions `origin_channel=\"email\"`, and the gate no longer reads an empty channel as trust.\n\nThe extractor also reads only the words **outside** every `<untrusted_content>` block (`schedule_extraction` runs `content_trust.strip_untrusted` first): an attached document's text is inlined in that block, so a sentence the principal did not type can never be quoted back as their commitment, and a turn that is nothing but an attachment is not extracted at all.\n\nEach pass writes a `memory_extraction` audit row — in a `finally`, so a pass that crashed is recorded too, with the exception type as its `failure` reason: how many items the model proposed, how many were stored, a `malformed` count so a pass where the model returned only garbage does not read as one that found nothing, and a `{kind, reason}` record per drop — `bad_quote` and `missing_field` for an item the model proposed, `not_a_list`, `item_not_a_dict` and `payload_not_a_dict` for a shape that was never a usable item. Every proposed item is either stored or dropped, so `proposed == stored + item drops` is the arithmetic that says whether anything was lost silently. The tool payload is not schema-checked anywhere, so a malformed shape is counted as a drop rather than raised — it used to abort the whole pass, discarding the other two kinds with it and suppressing the row, which read exactly like \"extraction never ran\". Without it, \"the model found nothing\" and \"the model found things and every one was rejected\" are indistinguishable from outside the database — which is why the failure above survived undetected and took a SQLite session on the tenant to find. A `proposed>0, stored=0` streak is the signal to watch.\n\nThe validator rejects a paraphrase, and the model paraphrases: on one install two of three real commitments were lost that way, the quote beginning \"SVN's engagement covers only …\" where the person had typed something else. So a `bad_quote` drop earns exactly one corrective call. The model is shown the rejected items and the quotes it gave, told to copy the span character-for-character (typos and casing included) or return empty arrays, and the tool is forced where the provider supports tool choice. Every retry item is validated first; a still-invalid one adds no second drop and is counted `still_invalid`. A valid item is then classified in order: its label matches a pending drop record → a recovery, stored and the record released; else its quote (terminal punctuation ignored) already supports a stored item of that kind → a re-send, ignored and counted `repeated`, so a model that re-sends everything cannot double-count `stored`; else a new proposal, stored and counted — a reworded label cannot be told from a different item, and crediting it would erase the very `bad_quote` census the row exists to show, so its original drop stands. Recovery is checked before re-send because two commitments can rest on one sentence. Malformed shapes at any level — a kind that is not a list, an item or payload that is not a dict, a response with no tool call — are counted `malformed`, so a retry that returned garbage does not read like one that obediently returned nothing. The row's `retry` block (`rejected`, `recovered`, `repeated`, `still_invalid`, `malformed`, `failure`) is always present, zeros when nothing was rejected; `rejected` is set from the complete drop list when the row is written, so neither a store failure before the retry nor a cancellation during it can zero it. The arithmetic above still holds after the retry. An exception on the retry is recorded as the retry's own `failure` and leaves the first pass's results untouched; the cost is one utility-model call, only on turns that dropped something. `memory_extraction` is a declared event type, so the audit page's filter can select it.\n\n### Standing facts (corrections that persist everywhere)\n\nA fifth table, `facts` (`openexecutive.memory.facts`, created on first write), holds facts and corrections the principal stated and asked to keep — \"Maple House is 48 units, not 52\". Before it, a chat correction's only durable home was Honcho peer memory: optional, best-effort (its prefetch times out or errors under load), re-injected only into that person's later chat turns, and never read by the briefs, the scheduled runs or the alert review. The episodic extractor cannot hold one either: it stores only decisions backed by a commitment quote, and a fact is not a commitment.\n\n- **Written from chat, by the principal or an attributed teammate.** `remember_fact` stores one (subject, statement, optional wrong value) and `forget_fact` retires one. The principal on a verified surface may do both. A teammate on the People list (a `team` row, not archived, not a contact) on a verified surface (the web app signed in, their own Slack or Discord; `fact_tools._teammate_speaker`) may call `remember_fact` only; email, Google Chat and unrostered senders are refused. Both tools are withheld from every unattended run and every turn private to the principal. Every call, `forget_fact` included (retiring a fact changes what later prompts treat as true just as writing one does), also needs `source_quote`: at least two words and eight characters, found in what the speaker typed this turn (`delegation.settings.own_words` over the pinned `TurnDelegation.speaker_text`). The `<outbound_reply_context>` backstory a Slack or Discord reply is hydrated with is stripped first, and a message with an attachment is refused outright. The quote alone only proves the principal asked, so everything `remember_fact` stores and renders (the statement, the subject shown as `[fact N] subject:`, and a previous value shown as `(corrects: …)`) is tied to their words too. An omitted previous value falls back to the replaced fact's own statement. Every figure must be a number they wrote, compared at its magnitude: `$180k` matches `180,000`, but `180m` never lets `$180k` through. Every name must also appear in what they typed: a capitalised word, or any word holding a non-ASCII letter, other than the statement's very first word (a statement is one fact, so splitting a document's names into one-word sentences exempts nothing). So must every month, weekday or quarter. A name the model writes in lower case is not caught: the gate narrows what a real quote can carry in; it does not prove a paraphrase. A real quote therefore cannot carry a document's figure, name or date in with it (\"Cedar Court's lease expires in March\" after \"remember what the lease doc says\"), while a paraphrase of what they said still passes. So the model cannot store its own inference, a document's figure or text quoted back at the principal as something they said. Every audit row the tools write, and the chat loop's `skill:` dispatch row for them (whose input quotes the principal verbatim), is private to the principal (`executive._private_tool_row`). Those rows tie a fact to the principal's session and turn, which `GET /memories/facts` hides from teammates, and a teammate can read any non-private audit row. The handlers run in a worker thread (`asyncio.to_thread`, which carries the turn's context), and the chat and committee paths, the alert review, the morning brief's synthesis and the end-of-day, weekly-review and reflection workflows read the block the same way, so SQLite, the profile file and its lock never block the event loop the SSE streams share. The principal's own email may ask too: the change is checked the same way, then held until they confirm it by replying to a one-time token sent to their own address (see Integrations → Standing facts by email).\n- **Provenance and attribution.** Each row keeps the quote, the channel (`web` or the adapter), `session_id`, `turn_id`, the recording person and the time, plus `recorded_by_role` (`principal` or `teammate`) and, for a teammate, `recorded_by_name` as the People list had it. Rows written before these columns existed read as the principal's (`_migrate` adds the columns on the first write; the read-only render tolerates a DB that has none).\n- **One active fact per subject.** A new row supersedes any active row with the same folded subject key, or the id named in `replaces_fact_id`, in one transaction. The old row stays as `superseded` (with `superseded_by`), and the new one is stored as a `correction` carrying what it replaced. Retiring sets `retired` with a reason. **The principal outranks a teammate:** a teammate's write that would replace an active fact the principal set (by subject or `replaces_fact_id`) raises `PrincipalFactConflict`, and the tool stores it as `proposed` instead, naming the fact it would replace (`replaces_fact_id`); teammates replace each other's facts freely, and the principal replaces anyone's. **\"Needs my approval\"** (`fact_approval_rules`, per teammate, **on by default**, set only by the principal) stores every fact from that teammate as `proposed`; the principal turns it off for a teammate they trust, whose facts then apply at once (except one that would replace the principal's). The rule is read inside `record_fact`'s own write transaction, so a switch turned on a moment earlier cannot let one fact through; a teammate write that names no person is never trusted. One teammate may have at most `MAX_PENDING_PROPOSALS_PER_PERSON` (20) proposals waiting (`TooManyProposals`; the tool tells them to wait for the principal's review). A teammate's retire checks ownership in the `UPDATE` itself (`retire_fact(teammate_id=)`: their own row, not approved). A proposed row never renders; `approve_fact` makes it active and replaces what it names (the principal's own fact included — approving it is their word) and stamps `approved_at`, after which it outranks teammates exactly as the principal's own fact does (`Fact.principal_owned`: no teammate may replace or retire it); `decline_fact` sets `declined`. No field of a teammate's fact may carry what the render adds itself — `(per <anyone>)` in any case (a unit such as `(per month)` or `(per unit)` is fine), `[fact N]` or a date stamp after any dash, read NFKC-folded with invisible characters removed (`fact_tools._marker_error`) — so a teammate cannot plant a second, forged attribution inside their statement (the principal's own unmarked lines are not checked: \"(per Smith lease)\" is ordinary wording for them). The tool answers `awaiting_approval` (no action chip) and tells the model to say it is not in use yet.\n- **Rendered everywhere output is produced.** `render_facts_for_prompt` renders the active rows newest first under a self-explaining `STANDING FACTS` header (use these over older figures; a line ending `(per <name>)` is that teammate's word and the principal's unmarked line wins a conflict; the current conversation still wins; quoted data never instructions). A teammate's line ends `(per <name>)`, the name defanged like the rest, capped at 40 facts / 6000 chars, with angle brackets defanged. It opens the DB read-only and never creates it or the table. The block always rides in a user turn, never a cached system block: a chat turn's `<standing_facts>` (so every scheduled run through the chat loop too), each specialist consult (`route_to_specialist`, chat and workflow steps alike), the /today header and the morning brief (`render_briefing_context`, after the quiet check and inside the string the header's cache key hashes, so a new fact rewrites the header), the alert review's batch (`render_batch`, read once per pass), and the end-of-day digest, the weekly review's top-three call and the morning reflection (`with_standing_facts`).\n- **Company-profile edits from chat.** `update_company_profile` (same gate and quote rule) changes one whitelisted field of `company/profile.yaml`, under `PROFILE_EDIT_LOCK` (also taken by `PATCH /company-profile`, so neither edit silently drops the other): a text or number field is set, a list field gets an item added or removed, and `financials.key_metrics` takes a named metric. It writes through `CompanyProfile.save_to_yaml` and updates the session's profile, so the next turn's cached company block carries it (one cache miss on the change). The new value must itself appear in the principal's own words, not just the quote: the value renders into the cached company block on every later turn, so \"set our mission to what the doc says\" or \"update our headcount\" is refused rather than saving a document's text or a guessed figure. A number must be one they wrote, however they wrote it (`$180k`, `1.2m`, `2,400,000`). Saved text has `<`/`>` defanged. A `kind='profile'` row records each edit with its quote for the Pulse page. Those rows are never rendered into a prompt, because the profile block already carries the value.\n\n### Session scoping\n\n`decisions` and `advice_given` rows carry a `session_id`, so per-thread channels (Discord, Telegram) can pull just-this-thread history without leaking cross-conversation context. A null `session_id` falls back to a global view.\n\n### Surfacing\n\n`openexecutive.memory.episodic.format_for_prompt` renders recent decisions and initiatives into a compact `<past_decisions>` block injected into the user turn — alongside `<retrieved_context>` and peer memory — never into a cached system block. Each decision names where it was recorded when that was a channel — `- 2026-09-01 [finance] (via email): …`, from the prefix of its `session_id` (`email:`, `slack:`, `discord:`, `telegram:`, `google_chat:`); a web or CLI decision has no tag. Rows extracted from mail before the untrusted-content policy, when any sender's body could be stored, therefore read as mail rather than as the principal's own word.\n\nScoped to a session, decisions and advice cover every conversation of a chat app's stream (`memory.conversation_ids.family_clause`): a Telegram chat or a DM is cut into conversations after two quiet hours or a /new (`memory.conversations`), and what an earlier conversation decided still renders in the next.\n\nThe chat route also injects a `<briefing>` block into the same user turn: a compact digest of the current open (unread) alerts, built by `openexecutive.briefing.context.format_open_alerts_for_prompt` (company-wide, `status=\"unread\"`, mirroring `/today`). This is what lets the Executive discuss a briefing item the principal clicked or named on `/today` (e.g. \"Gulf Coast Port Cyberattack\"). It is resolved in parallel with the other context fetches, omitted when there are no open alerts, and never placed in a cached system block.\n\nOn the Pulse page the Memory section shows the three lists as Decisions, Initiatives and Advice tabs, then a **Corrections** tab (`GET /memories/facts`: active standing facts and profile edits with their quote, channel and — for a teammate's — their name; proposals first under \"Waiting for your approval\" with **Approve** / **Decline** for the principal; the replaced, retired and declined history folded away; **Retire** on any fact for the principal and on their own not-yet-approved one for a teammate; and, for the principal, a per-teammate \"needs my approval\" switch), and a **History** tab for the person's own Always in the loop notes (see below). The header's Memories tile counts the three lists. What peer memory has learned about the signed-in person is theirs alone, so it is not on Pulse: it is on **Settings → About you** (see the peer memory section).\n\nThe same user turn carries a `<drive_memory>` block when the conversation has touched Google Drive (`openexecutive.memory.drive_reads`). Drive is reached only as live Google Workspace calls inside a turn and history keeps only prose, so without it a file found one turn was gone the next. `MCPGateway.call_tool` hands each `search_drive_files` and `get_drive_file_content` result to `record_drive_result`, which keeps, per session, every file found or opened (file id, name, type, link, and for an opened file its first 600 characters) and every search that matched nothing, with its query. `format_drive_memory` lists the 20 most recent files, so \"the file you found earlier\" resolves to a file id the Executive reopens rather than searching again, and the queries that found nothing (dropped once the same query later finds something). Rows are keyed on the session *and* the speaker, and shown only to that speaker in that session, because one session can span several people (an email thread, a Slack or Discord thread). Nothing is recorded or shown without a bound `current_session` and a rostered speaker, on a turn private to the principal, or on one that touched the speaker's own mailbox (Act as me). workspace-mcp writes file names into its output unescaped, so a name containing a newline can forge a result line. Only a Drive-shaped file id, type and `docs`/`drive.google.com` link are therefore kept; any other line is dropped, and the name is always quoted as the file's own content, not instructions. Each speaker keeps at most 100 files and 100 searches per session, older rows are pruned on write, and `session_store.delete_session` drops them all.\n\nA conversation can also become its owner's alone. When Act as me first reads the speaker's own mailbox in it, `session_store.mark_mail_private` sets `sessions.mail_private` (creating the row with its owner when a channel adapter hasn't written it yet), and from then on only the session's owner may open, continue or delete it — the principal included, when it is a team member's (`chat._session_access`). It is never cleared. Beside it `sessions.mail_read_at` keeps how many history messages the conversation held before the last turn that read the mail (`session_store.mail_read_at`; NULL on rows marked before the column): Act as me's hold on links and scripts in later turns lasts only while that turn is still in the history window (see Act as me). \n\nThe chat list has owner controls on the same row: `sessions.pinned_at` (pinned chats list first) and `sessions.title_locked` (set by `rename_session`, after which `update_session_title`, the automatic title, leaves the name alone). A `session_shares(session_id, person_id, shared_by_person_id, created_at)` row adds one team member to someone's chat (`list_shared_with_person`, `set_shares`, `leave_share`): they read and write in it with its owner, each of their messages saved with their own `sender_person_id`; a `mail_private` chat is never shared or opened that way, and deleting the chat drops its shares. `last_turn_sender` says who wrote the last turn, which is how redo stays with the person who asked. The chat list's preview puts `You:` only before the caller's own words. `rewind_last_turn` deletes a web chat's last turn (the last reply and the user messages after the reply before it) so it can be asked again; the next turn's history is re-read from these rows, so nothing else needs clearing. A search that matched nothing also gains a note in its tool result: say the exact query and that it found nothing, never that the file does not exist. This is a first step: Drive is still not indexed into the company collection.\n\n### System of record\n\nSQL is the system of record; the peer-memory service is a recall layer mirrored from it, not a replacement. When `store_decision` / `store_initiative` / `store_advice` insert a row whose `department` is non-empty and not `\"general\"`, the row is mirrored as a kind-tagged note into that department's peer via `append_department_note`. The mirror fires only after a successful INSERT, is fire-and-forget, and never rolls back the SQL row on peer-memory failure. `scheduled_actions` is never mirrored — it is a queue, not memory.\n\nThe episodic extractor still learns only from the principal's own words. Commitments and asks from everyone else on the roster are tracked as **open loops** (see Attunement) — `scheduled_actions` rows with `kind='open_loop'`, opened and closed by a separate quote-gated pass after each attributed turn. That pass depends on `chat_messages.sender_person_id`, which records who actually wrote each persisted user message. An open loop counts toward `list_awaiting_replies_by_person` only once it is due, and `list_scheduled_actions(exclude_internal=True)` filters `__internal__` rows in SQL so readers that want real sends are not starved by them. `mark_outbound_context_consumed` also resolves the Attunement outcome row for that DM as `replied` — a matched reply is the clearest sign proactive outreach landed — and a real change to an existing initiative (`store_initiative` / `update_initiative`, new status or summary) marks the updater's own check-in nudges `acted` — an update with no known updater, such as `PATCH /memories/initiatives/{id}`, credits nobody.\n\n### Workspace settings\n\nThe same database holds one row of settings that are not memory: `workspace_settings` (`openexecutive.memory.workspace_settings`) — the install's mode (`team` by default, or `solo` for one person using Open Executive just for themselves), the user's IANA time zone, the principal's role (`PrincipalRole`: `role_kind`, `role_title`, `reports_to`, `remit`, `measured_on`, all nullable; only solo mode reads it), and the company's own email domains (`company_domains`, a JSON list, or NULL to derive them from the principal's primary address — `people.identity` matches a teammate by local part on them; `validate_company_domains` lowercases, dedupes and sorts, allows at most 10 plain DNS names and refuses a free-mail provider's, and a stored value that no longer validates reads as NULL). It is a table of its own rather than a company-profile field because onboarding rebuilds the profile from scratch. Every read is fresh and read-only (a missing file or table reads as the defaults; a table from before the role or `company_domains` columns reads them as unset and is migrated additively by the next init or write). A read error (a locked database, say) also reads as the defaults, so `get_workspace` then says team; `read_stored_mode` is the strict read of the mode alone — None when the row cannot be read or holds no valid mode — for the scheduler's weekly-review check, which must not take a failed read for team. A session may carry an explicit `workspace_mode` override; otherwise the mode is read fresh at the start of each turn and pinned on the session for that turn only (`Session.turn_workspace_mode`, via `pin_turn_workspace_mode`), so every tool handler in the turn sees the mode its persona and tools were built in. `effective_workspace_mode` reads override, then the pin, then the setting; `effective_principal_role` reads a session's `principal_role` override, then the role pinned for the turn (`Session.turn_principal_role`, via `pin_turn_principal_role`), then the stored role. See Org for what solo changes and Scheduler for the time zone.\n\n### Act as me\n\n`initialize_db` also creates Act as me's per-person tables (`delegation.schema.ensure_schema`): `delegation_settings`, `delegation_voice` and `delegation_voice_history`. They hold a setting and a writing profile rather than memory, and nothing in them is mirrored to peer memory. A turn that touched the speaker's own mailbox teaches no memory: the episodic, open-loop and working-style passes are skipped along with the Honcho peer and department syncs, since its reply quotes a draft built from other people's mail. See **Act as Me (Delegation)**.\n\n### Always in the loop (notes of what you said)\n\nA person can keep private, dated notes of what they said, in chat with the Executive and in email replies it drafted for them: what they promised, agreed, declined, answered, asked for or shared. The switch is per person (\"Keep track of what happens\", `history_person_settings.reply_notes`, off by default, one switch for every channel). Any team member on the People list may turn it on (`history.can_keep_notes`: kind `team`, not archived, the principal included); Act as me isn't needed, though notes from email replies only come through it.\n\n- **Where notes come from: chat.** After each chat turn, on both the single-voice and the committee path, the Executive's post-turn block calls `memory.history_chat.schedule_chat_notes` next to the open-loop and style passes, except on a turn that touched the speaker's mailbox. It reads only what the speaker typed this turn (`delegation.settings.own_words`: no backstory an adapter added, nothing when a file came with it), never the reply and never anyone else's message: every channel calls the Executive with the one speaker's message, and what other people say to each other is never read. It runs only for a speaker the turn verified (`history_chat.verified_speaker`): the turn's `caller_person_id` is them, nobody started it by email or runs it unattended or for them, and the surface proved who they are (the web chat signed in or a local install, the principal or a team member on their own Slack or Discord, a private Telegram chat behind a valid webhook secret, or a channel whose adapter verified the sender itself and set `Session.speaker_verified`). A shared Slack or Discord thread counts: the notes stay private and are read back only where nobody else can see them. A message under 40 characters is skipped, and each person gets at most 40 passes a day, counted in `history_chat_passes` so the cap holds across workers and restarts. The pass uses a constant `CHAT_PROMPT` (requests to the assistant, questions and small talk are not notes), the same `record_notes` tool and the same `check_note` gate with the message as both body and allowed words; the note's channel is the inbound channel or `web`, its conversation the session id, and it names no counterpart.\n- **Where notes come from: email.** After `delegation.reply_send` sends a reply, it starts `memory.history_notes.note_sent_reply` in the background. The note-taker reads only the words the person sent (`email_poller.sender_new_text` strips quoted mail) and the recipients' names, cut to four words of name characters (`history_notes.short_name`): never the mail being answered, nor the subject, which others in the thread write too, so nothing another person wrote can become a note. One forced `record_notes` call with a constant prompt and no other tools returns at most three notes. Code then drops any note that says more than they did: the `quote` must appear word for word in what they sent, every figure in the summary must be in the quote, every name or date word must be in what they sent or the recipients' names, at least half its other content words must be theirs, the summary carries no link or address, and a `due_date` is kept only for something promised or agreed. Notes record events, never instructions, and carry `trust = high` because they rest on the person's own words.\n- **Whose they are.** Every note is private to its person (`visibility = private`). Nobody else reads it, the principal included; there is no shared note.\n- **How long they last.** The company default is 90 days (`history_settings.retention_days`, the principal's choice of 30, 90, 365 or until forgotten). A person may only choose a shorter time; shortening the company time clamps everyone's choice and re-dates live notes. A pinned note never expires; unpinning restarts its clock, and a later retention change counts from there. Reads skip expired notes and the scheduler's alert sweep deletes them (`history.sweep_expired`).\n- **What a person controls.** Through `/memories/history` they read, search, pin, correct and forget their own notes. On the Pulse page this is the **History** tab, last in the Memory section and shown only to someone with notes to see (signed in and on the People list): each note shows its kind, who it was with, the date, the person's own words, any due date and when it will be forgotten, and its menu holds **Correct** (a side panel; \"Use the original\" clears a correction), **Pin**, **Don't remember this** and **Forget**. \"Don't remember this\" forgets every note from that conversation and adds it to `history_excluded`, so it is never noted again. Settings → **Memory** holds the switch (\"Keep track of what happens\") and a shorter time for their own notes, and the company time, which the principal changes and everyone else reads. A chat note shows the channel alone (\"Slack\", \"Web chat\").\n- **Recall.** `recall_history` (`orchestrator.history_tools`) is offered only on a turn where the speaker may read their notes: verified as above, a team member who may keep notes, in a conversation private to them (`history_chat.private_chat`: the web chat, a Slack or Discord DM, a Telegram chat, or one its adapter marked `Session.private_chat`), with their switch on. Before any note is read the turn is set `touched_mail`, for the principal too, so its rows are private to the speaker, it teaches no memory and the mail lockdown holds from that round on. The conversation is also marked theirs alone (`session_store.mark_mail_private`), so every later turn in it is private the same way (the lockdown is that turn's alone) and, for a team member, the principal can't open it; recall refuses if that can't be stored. Notes come back in a `<history_notes>` block as history to cite: the date, the person's own words first, then how they were noted. With `due: true` it lists only notes with a due date, from a week overdue to two weeks ahead, soonest first (\"what's due today?\").\n- **In the owner's briefs.** The morning brief adds a FROM YOUR NOTES — DUE SOON block (`memory.history_brief.due_soon_block`: what the owner promised, agreed or asked of someone, from a week overdue to a week ahead, in the workspace's local dates) and the end-of-day digest a FROM YOUR NOTES — TODAY block (`noted_today_block`: what they promised, agreed, asked or declined since the last digest, then what is due tomorrow). Both only on the scheduler's delivery to the owner alone (`morning_brief.PRINCIPAL_DELIVERY`), never a run started from chat, whose tool result lands in the turn's shared audit row and peer memory; only when the owner may keep notes and has the switch on (`history_brief.owner_keeping_notes`), and only the owner's own notes. A run that used any is marked `private_to_principal`, so the shared run history keeps `PRIVATE_RUN_ARTIFACT` instead of its text, and the note ids with their state (overdue, today, soon) enter the brief's fingerprint, so one falling due un-suppresses an unchanged brief. Teammates get no brief, so their notes reach them only through recall and reminders.\n- **In Act as me drafts.** The ghostwriter gets a `<writer_noted>` block (`memory.history_drafts.notes_for_draft`): the writer's own notes from earlier Act as me replies that every recipient of the new draft was on, with their switch on. It keeps the draft consistent with them and turns a contradiction into an open question on the card; it never adds anything from them (see Act as me).\n- **Due-today reminders.** `memory.history_reminders.maybe_remind`, called from the scheduler tick every 15 minutes between 09:00 and 18:00 local time, sends each person with the switch on one message on a day something they promised or agreed to by email (`source = approved_reply`) falls due. Chat promises are left to open loops, which the nudge engine already chases. The message says only how many things are due, never what or to whom, and the channel senders' audit rows for it are private to the person (`audit.context.rows_for_person`; the owner's `private_rows`), which also keeps the send off the shared activity rail (`_record_send_to_activity` skips a send whose rows are private). The person asks \"what's due today?\" in a private conversation and `recall_history` answers. It goes to their own Slack or Discord DM, a private Telegram chat (`delivery_order` skips a negative group id, for the owner's briefs too) or their own email (`scheduler.runner.deliver_to_person`), never a shared channel. `history_reminders` holds one row per person per day, claimed before sending and never released, so two workers never both send and a half-failed send is never repeated; a failed one waits for the next due day.\n- **Not peer memory.** Notes never reach Honcho, episodic extraction, standing facts or another person's turn. The tables (`history_notes`, `history_settings`, `history_person_settings`, `history_excluded`, `history_chat_passes`, `history_reminders`, created by `history_schema.ensure_schema` from `initialize_db`) swap with a client slot and are cleared by a factory reset.\n\n### Conversation review (fixing what replies left undone)\n\n`memory.chat_review` looks back over a chat once it has been quiet `CHAT_REVIEW_QUIET_MINUTES` (30) and fixes what the replies left undone: \"I sent it\" answered with \"noted\" and the draft still waiting, \"drop that reminder\" answered with \"sure\" and the reminder still set. The claim check (`orchestrator.claim_check`, see Lifecycle) catches a false claim in the same turn; this catches the rest.\n\n- **What is recorded.** On both the single-voice and the committee path the post-turn block calls `record_turn` with the speaker's own words (`delegation.settings.own_words`), the reply and the tools the turn ran (`_stream_agent_loop(calls_out=)`). Only a verified speaker's turn is kept: the principal on a surface `people_tools` verifies, or a rostered teammate on their own signed-in web chat, Slack or Discord. A channel whose adapter set `Session.speaker_verified` counts as a verified surface here too; an email, an unattended run, a turn private to the principal, one that touched the speaker's mailbox and a message with an attachment are never kept. Rows live in `chat_review_turns` for 7 days, a turn graded a miss (below) for `MISS_KEEP_DAYS` (90); each row also keeps the audit `turn_id` of the turn, so the claim check's row can be joined back to it.\n- **When.** Each kept turn makes sure one `chat_review` `__internal__` action is waiting for the conversation (`channel_ref` = session id), due 30 minutes on. The runner marks it done and calls `run_scheduled`, which schedules a fresh one if a newer turn arrived meanwhile, else reviews the oldest unreviewed turns (at most 20, the rest in a review right after) and marks exactly those reviewed, so a chat is read in parts and never twice. `CHAT_REVIEW_MAX_PER_DAY` (10) caps each person's passes a day (`chat_review_days`), so one person's chats can't use up another's.\n- **The pass.** One small tool loop per person on `CHAT_REVIEW_MODEL` (default `ROUTING_MODEL`), at most 5 rounds and 8 changes, in its own task with a session rebuilt from the recorded surface and caller and a delegation pin holding their words, so each tool runs through the chat tool's own handler and checks: `list_open_loops` / `close_open_loop`, `remember_fact`, `list_followups` / `cancel_followup` / `move_followup`, `leave_out_of_brief`, plus `learn_reply_style` (a working-style rule), `learn_writing_style` (a habit or avoid line in their Act as me voice profile, only for someone who may use it) and `raise_in_brief` (one line for the next brief). Every change carries `source_quote` of at least four of the person's own words (`fact_tools._quote_error`), and the thing it changes (the loop's or follow-up's text, the fact, the brief item or line) must share two words with what they wrote (its only one, for a one-word target) A chat draft's state is left to the brief's own check of the mailbox's Drafts. The replies are shown as `<untrusted_content>` (they quote mail and documents) and tool results not at all, only the tools' names. `leave_out_of_brief` and `raise_in_brief` are the principal's only; dropping a fact and changing a goal are left to chat. It never sends, books, deletes or grants permission to act, and nothing it does is said in chat. One `chat_review` audit row per pass lists the changes.\n- **Grading (looking back at how it went).** Before the fix loop, the same pass grades each turn it reads with one forced-tool call (`grade_turns`) on the review model. The grader sees what the fix loop sees plus one SIGNALS line per turn, joined from where the product already records them (`turn_signals`): a 👍/👎 and its note on the saved reply (`chat_messages`, matched to the recorded reply by its first 120 characters, which also gives the Reflection screen the reply's `message_id`), a reply the person stopped (`stopped`), a turn they took back to ask again (a `session_rewound` audit row after a turn whose reply is no longer in the chat), a claim the reply made that no tool backed (a `claim_check` audit row with the turn's `turn_id`), and a tool whose recorded result reads as an error. Per turn it records `fine`, `miss` or `unclear`; for a miss, `wanted` (what the person wanted instead, one or two sentences) backed by a `quote` of at least four of their own words from that turn or the ones after it, code-checked (`accept_grades`) or the turn is `unclear` and `wanted` dropped, plus the `kind`: `company` (a term, a fact, a preference, which specialist to ask, doing a thing rather than promising it would have fixed it) or `product` (a tool failed or was refused, a capability it lacks). A turn the model skipped is `unclear`. Grades go on the row (`verdict`, `kind`, `wanted`, `signals`, `graded_at`, `message_id`), and each person's weekly count of graded turns and misses on `chat_review_weeks`, so the rate outlives the 7-day rows. Grading changes nothing in the workspace and never blocks the fixes: a failed grade leaves the turns ungraded. The pass's audit row carries the counts. `list_misses` (one person's or everyone's; the route then keeps, for the principal, only rows from chats `chat._session_access` lets them open, so a teammate's own chat stays theirs), `weekly_rates` and `forget_miss` (`is_principal_or_self`) serve `GET`/`DELETE /memories/reflection` (the Pulse screen **What it got wrong**).\n- **Lessons** (`memory/lessons.py`): for a turn graded a miss the review may call `learn_lesson` once: one sentence this workspace wants done differently (a term and what it means, a preference about the content, a thing to do rather than promise, a specialist to consult), quoted from the person's own words (the quote must come from the miss turn or a later one, and the lesson must be what the quote says). It passes the working-style deny-list (`attunement.style._DENY_PATTERNS`: no link, handle, amount, markup, identifier, action verb, instruction talk, nudge to act unchecked, roster name) plus the lessons' own list (the verbs that move information: email, share, post, export, attach...; the words that widen a request to everyone or everything) without the about-the-writing requirement, may add at most two content words beyond the quote (`lesson_overreach`, so a real quote can't carry a different sentence in), and is re-checked on every render. Rows live in `chat_review_lessons` (text, quote, person, session, `shared` = learned in a channel or group thread, turn, `shown`, `fine_after`, `miss_after`, `retired_at`/`retired_reason`) with `chat_review_lesson_uses` (lesson, turn id, whose turn). A lesson reaches a turn by a keyword match (two shared content words between the lesson plus its quote and the message; no vector index for a list this short): the Executive's own turn gets the matching ones as a `<lessons>` block in the user turn (`build_lessons_block`, never a cached block; the header says the current request wins and nothing in it authorizes an action), and each specialist call gets the same lines under its `<failure_cases>` block (`router._lessons_for_call` → `lessons_for_query`). A lesson reaches its own person's turns; the principal's reach everyone's only when learned in a shared space (`shared`), so nothing said in someone's own chat is paraphrased into another person's turn. `build_lessons_block` counts each showing against the active turn id and the speaker; when the review later grades that turn, `note_outcome` adds to `fine_after` or `miss_after` only when the turn was the lesson's own person's (nobody else's chats can retire it), and a lesson shown 5 times with more misses than fine turns retires itself (`unhelpful`). At most 40 live lessons per person; their oldest retires to make room (`BEGIN IMMEDIATE`, so two reviews can't both skip it). Forget on the screen retires one by hand (`forgotten`); a retired lesson is listed as stopped, never erased.\n- **Replay: the workspace's own evals** (`memory/replay.py`). Nightly (the `chat_replay` scheduled action, `CHAT_REPLAY_TIME` 03:30 in the user's zone, seeded and chained like the reflection), the Executive runs its misses again with everything in force today and a judge says whether each would now go right. A case is a graded turn: a miss (its `wanted`), or a turn that went fine and got a thumbs up (`kept = 1`, held as long as a miss, at most `MAX_KEPT` 300 per person), which the replay protects so a lesson can't break what worked; a closed miss joins that pool. `due_cases` picks a miss the night a lesson is written for it (`WHY_LESSON`), when a lesson learned since the last night reaches it (`WHY_REACHED`), else once a week (`WHY_WEEKLY`), from the last 30 days only and at most `CHAT_REPLAY_MAX_CASES` (30) a night within `CHAT_REPLAY_MINUTES` (20); 20 protected cases (`WHY_PROTECT`, rotated by last replay) run only on a night a new lesson landed. `replay_case` runs `Executive.chat` on a session rebuilt from the recorded surface and speaker (`chat_review._rebuild_session`) with the saved conversation up to that turn (`chat_messages` before the reply's `message_id`), flagged `Session.replay`: reads run for real through every gate, and every tool a read-only turn is denied (`MCP_CLIENT_WITHHELD_TOOLS`, and gateway calls outside `MCP_CLIENT_MCP_TOOLS`) returns \"done\" and lands in `Session.replay_calls` instead (`faked_handlers` / `faked_call_tool`, wrapped outermost in the agent loop); scripts, Python jobs, `load_mcp_server`, Act as me's tools, `recall_history` and extension tools are not offered at all; nothing a replay does is kept (no extraction, open loops, style, notes, review or Honcho mirror, and `build_lessons_block(count=False)` counts no showing). The judge (`CHAT_REPLAY_JUDGE_MODEL`, else `EVAL_JUDGE_MODEL`, else Sonnet; `evals.judges.judge_message`) reads the original date, the person's words and the conversation before, what they wanted (or the reply they liked), today's reply and the recorded actions, and answers `{passed, time_bound, notes}`, intent and action rather than figures; an unreadable answer is a fail. The gate (`_settle`): a miss that passes is `closed` with `closed_at`; a time-bound one becomes `evidence` and is not replayed again; a lesson for a miss that still fails on `LESSON_FAILS` (2) judged replays after it was learned retires (`replay`); a protected case that fails reopens a closed miss and counts a strike against each new lesson of the same person that reached it (a teammate's turn never retires the principal's shared lessons), which retires at `PROTECT_FAILS` (2) such strikes, so one judged turn, or one message written to fail the judge, is not enough. A case that didn't run (an error, the `CASE_SECONDS` timeout) is recorded with `ran = 0` and settles nothing. The judge's input is scrubbed like outside content (`content_trust._scrub`) with the prompt's own tag names renamed inside it. Every replay is a `chat_review_replays` row (the reply and recorded calls; dropped with its turn when a miss or chat is forgotten or purged, `chat_review._prune_replays`) and a `chat_review` audit row (actor `chat_replay`); each night a `chat_review_replay_runs` row, written before the first case (so a second runner sees nothing new) and filled in after, which is also what \"new since the last night\" means. The nightly Executive carries the scheduler's MCP gateway, so the reads a miss needs run as they did. The Reflection screen's number, \"of the N things that went wrong in the last 30 days, M would go right today\" (`summary_for`, over the misses the caller sees), and each miss's last replay come from these columns on `chat_review_turns` (`replay_state`, `replayed_at`, `closed_at`, `replay_count`, `replay_notes`). Off with `CHAT_REPLAY_ENABLED=false` or when the review itself is off.\n\n## Decision ledger\n\n`openexecutive.memory.decision_ledger` keeps one `decision_instances` row per gated action — a meeting the Executive proposes to book, an Act as me reply card — with how it was resolved, so each class has a reliability record. Every status change is a compare-and-set. A tap with an outside effect (sending an email) claims the row first (`claim_for_execution`, proposed → executing), so of two taps only one acts, and finishes it as `approved_unchanged`, `approved_with_edit` or `failed`, or hands it back (`release_claim`). A row whose class acted on its own with nobody tapping — `gate_mode` `auto_execute`, as Act as me's **Handle it for me** replies are — finishes as `executed` instead, with no resolver, so a reliability read never counts it as an approval. A send whose result is unclear stays `executing` for a reconciler and is never retried. A row still waiting can have its payload changed only by compare-and-set (`update_open_payload`, on `proposed` and, when given, on the payload as it was read): that is how an Act as me reply card takes the person's edit, or records the draft made for it at Send.","mermaid": "flowchart TD\n Store[\"store_decision / store_initiative / store_advice\"]\n DB[\"episodic_memory.db<br/>decisions / initiatives<br/>advice_given / scheduled_actions\"]\n Fmt[\"format_for_prompt\"]\n Turn[\"User turn<br/>past_decisions block\"]\n Mirror[\"append_department_note\"]\n Peer[\"Department peer<br/>(Honcho)\"]\n Store --> DB\n DB --> Fmt\n Fmt --> Turn\n Store -->|\"dept set & not general\"| Mirror\n Mirror -->|\"fire-and-forget\"| Peer\n Tool[\"remember_fact / update_company_profile<br/>(principal, verified, quoted)\"]\n Facts[\"facts table<br/>active / superseded / retired\"]\n Every[\"STANDING FACTS block<br/>chat, specialists, briefs,<br/>alert review, workflows\"]\n Tool --> Facts\n Facts -->|\"render_facts_for_prompt\"| Every\n class Store entry\n class DB storage\n class Fmt compute\n class Turn hot\n class Peer external\n\n class Tool entry\n class Facts storage\n class Every hot","generated_at": "2026-10-16T21:00:00Z"}diff --git a/packages/core/openexecutive/delegation/settings.py b/packages/core/openexecutive/delegation/settings.pyindex 82efec81..d775d1bc 100644--- a/packages/core/openexecutive/delegation/settings.py+++ b/packages/core/openexecutive/delegation/settings.py@@ -341,14 +341,20 @@ _DM_SESSION_PREFIXES = {"slack": "slack:dm:", "discord": "discord:dm:"}def private_conversation(session: Any) -> bool:"""Whether only the speaker (and the Executive) can read this- conversation: the web chat, a Slack or Discord DM, or a Telegram chat- (``is_principal_on_verified_surface`` already accepts only a private one).+ conversation: the web chat, a Slack or Discord DM, a Telegram chat+ (``is_principal_on_verified_surface`` already accepts only a private one),+ or one a channel adapter marked so (``Session.private_chat``) for a+ sender it verified (``Session.speaker_verified``).Also the morning brief's rule for reading what is private to theprincipal from a chat turn (``workflows.morning_brief``). A web chatshared with teammates (``Session.shared_chat``) is read by all of them,so it isn't."""if getattr(session, "from_web_chat", False) is True:return getattr(session, "shared_chat", False) is not True+ if getattr(session, "private_chat", False) is True:+ # Whose conversation it is matters to callers that ask nothing else+ # (``correction_tools._scheduled_by``).+ return getattr(session, "speaker_verified", False) is Truechannel = str(getattr(session, "origin_channel", "") or "")if channel == "telegram":return Truediff --git a/packages/core/openexecutive/memory/chat_review.py b/packages/core/openexecutive/memory/chat_review.pyindex 2ba3ec80..9e890881 100644--- a/packages/core/openexecutive/memory/chat_review.py+++ b/packages/core/openexecutive/memory/chat_review.py@@ -213,9 +213,9 @@ def _quiet() -> timedelta:def _verified_person(session: Any, person_id: int | None) -> Any:"""The speaker's People row when this turn is one the review may act on:- the principal on a surface ``people_tools`` verifies, or a rostered- teammate on one. An adapter's own ``speaker_verified`` is not enough- (it grants Always in the loop's notes, nothing else). None otherwise."""+ the principal on a surface ``people_tools`` verifies (an adapter's own+ ``speaker_verified`` included), or a rostered teammate on one. None+ otherwise."""from openexecutive.memory.history_chat import verified_speakerfrom openexecutive.orchestrator.people_tools import (is_principal_on_verified_surface,diff --git a/packages/core/openexecutive/orchestrator/people_tools.py b/packages/core/openexecutive/orchestrator/people_tools.pyindex 5b859705..685a30d5 100644--- a/packages/core/openexecutive/orchestrator/people_tools.py+++ b/packages/core/openexecutive/orchestrator/people_tools.py@@ -323,13 +323,33 @@ def _audit(tool: str, kind: str, ok: bool, summary: str, details: dict[str, Any]# own user id, over an authenticated connection). Email (an unauthenticated# From header), Google Chat (its sender is matched by email for the department gate only), the CLI, the MCP server and# unattended runs (scheduler, workflows, alert review) don't. Telegram only-# sometimes — see `_is_verified_speaker_surface`.+# sometimes — see `_is_verified_speaker_surface`. A channel adapter this module+# doesn't know counts when it verified the sender itself+# (`Session.speaker_verified`, with the `caller_person_id` it resolved)._VERIFIED_SPEAKER_CHANNELS = frozenset({"slack", "discord"})+def _adapter_verified_turn(session: Any) -> bool:+ """The rest of what an adapter's ``speaker_verified`` needs to count, as+ ``history_chat.verified_speaker`` asks of it: a resolved caller, a turn+ someone is in that no email started, not private to the principal and+ not run on their behalf (an eval's ``delegation_override``)."""+ from openexecutive.delegation.settings import DelegationOverride++ return (+ getattr(session, "caller_person_id", None) is not None+ and not getattr(session, "email_from", "")+ and getattr(session, "unattended", False) is not True+ and getattr(session, "private_to_principal", False) is not True+ and not isinstance(getattr(session, "delegation_override", None), DelegationOverride)+ )++def _is_verified_speaker_surface(session: Any) -> bool:if bool(getattr(session, "from_web_chat", False)):return True+ if getattr(session, "speaker_verified", False) is True and _adapter_verified_turn(session):+ return Truechannel = str(getattr(session, "origin_channel", "") or "")if channel in _VERIFIED_SPEAKER_CHANNELS:return True@@ -516,33 +536,43 @@ def audit_row_private_to_principal(*payloads: Any) -> bool:return _names_a_contact(payloads)-def sent_by_principal(channel: str, channel_ref: str, sender: Any) -> bool:+def sent_by_principal(+ channel: str, channel_ref: str, sender: Any, *, speaker_verified: bool = False+) -> bool:"""Whether a message a chat adapter received on ``channel`` from``sender`` (the Person it resolved, or None) starts the principal's ownverified turn — what ``is_principal_on_verified_surface`` answers once theturn's session is bound. ``channel_ref`` is the id that session carries asits ``origin_channel_ref`` (Telegram's chat id decides whether it is- verified at all)."""+ verified at all). ``speaker_verified``: the adapter verified ``sender``+ itself, as it will say on the turn's session (``Session.speaker_verified``)."""if sender is None or getattr(sender, "is_principal", False) is not True:return Falseif getattr(sender, "archived", False) is True:return False- surface = SimpleNamespace(- from_web_chat=False, origin_channel=channel, origin_channel_ref=channel_ref+ return _is_verified_speaker_surface(_inbound_surface(channel, channel_ref, sender, speaker_verified))+++def _inbound_surface(channel: str, channel_ref: str, sender: Any, speaker_verified: bool) -> SimpleNamespace:+ """The surface an inbound message's turn will have, before its session exists."""+ return SimpleNamespace(+ from_web_chat=False,+ origin_channel=channel,+ origin_channel_ref=channel_ref,+ speaker_verified=speaker_verified,+ caller_person_id=getattr(sender, "id", None),)- return _is_verified_speaker_surface(surface)-def sent_by_teammate(channel: str, channel_ref: str, sender: Any) -> int | None:+def sent_by_teammate(+ channel: str, channel_ref: str, sender: Any, *, speaker_verified: bool = False+) -> int | None:"""The teammate (not the principal) a chat adapter's inbound message on``channel`` is from, when the channel proved who sent it — the personwhose own turn it starts (``teammate_turn_owner``) — else None."""if sender is None or getattr(sender, "id", None) is None:return None- surface = SimpleNamespace(- from_web_chat=False, origin_channel=channel, origin_channel_ref=channel_ref- )- if not _is_verified_speaker_surface(surface):+ if not _is_verified_speaker_surface(_inbound_surface(channel, channel_ref, sender, speaker_verified)):return Nonereturn team_member_id(int(sender.id))diff --git a/packages/core/openexecutive/orchestrator/session.py b/packages/core/openexecutive/orchestrator/session.pyindex edf5dca8..bf86d6ae 100644--- a/packages/core/openexecutive/orchestrator/session.py+++ b/packages/core/openexecutive/orchestrator/session.py@@ -81,12 +81,11 @@ class Session:caller_person_id: int | None = None# Set by a channel adapter that verified for itself that `caller_person_id`# is who sent this turn's message, on a channel the checks in- # `people_tools` don't know. Read only by Always in the loop- # (`memory.history_chat`, `orchestrator.history_tools`), never as a grant- # for anything else. `private_chat` adds that nobody but that person (and- # the Executive) can read the conversation, so their notes may be recalled.- # An adapter sets either only when it resolved `caller_person_id` from the- # sender identity it verified itself, never from anything the message says.+ # `people_tools` don't know. That channel then counts as a verified+ # surface (`people_tools._is_verified_speaker_surface`) for every gate+ # that asks, as Slack and Discord do: an adapter sets it only when it+ # resolved `caller_person_id` from a sender identity the platform+ # authenticated, never from anything the message says, and per turn.speaker_verified: bool = False# The sender's People entry on a channel that names its sender but isn't# one `people_tools` verifies (Google Chat, by the Google account email on@@ -95,6 +94,11 @@ class Session:# teammate gets their own department's authority. Never a grant for# anything else, and never set alongside `caller_person_id`.gate_sender_person_id: int | None = None+ # Set by a channel adapter when nobody but the speaker (and the+ # Executive) can read the conversation, e.g. a direct message+ # (`delegation.settings.private_conversation`, which also needs+ # `speaker_verified`). Act as me and recalled notes also need the+ # speaker's turn to be verified.private_chat: bool = False# The live alert board as the server derived it this turn, recorded by# `briefing.context.render_and_trust`. `ack_alert` refuses anything else ondiff --git a/packages/core/tests/unit/test_chat_review.py b/packages/core/tests/unit/test_chat_review.pyindex b46e91e3..70e3f035 100644--- a/packages/core/tests/unit/test_chat_review.py+++ b/packages/core/tests/unit/test_chat_review.py@@ -141,10 +141,12 @@ def test_an_unverified_turn_is_not_kept(roster: SimpleNamespace, extra: dict[strassert _record(roster.principal, session=session) is None-def test_an_adapters_own_verification_is_not_enough(roster: SimpleNamespace) -> None:- session = Session(session_id="s-1", origin_channel="google_chat", caller_person_id=roster.teammate.id,+def test_an_adapters_own_verification_counts(roster: SimpleNamespace) -> None:+ session = Session(session_id="s-1", origin_channel="otherchat", caller_person_id=roster.teammate.id,speaker_verified=True)- assert _record(roster.teammate, session=session) is None+ assert _record(roster.teammate, session=session) is not None+ unverified = Session(session_id="s-2", origin_channel="otherchat", caller_person_id=roster.teammate.id)+ assert _record(roster.teammate, session=unverified) is Nonedef test_a_message_with_an_attachment_is_not_kept(roster: SimpleNamespace) -> None:diff --git a/packages/core/tests/unit/test_delegation_settings.py b/packages/core/tests/unit/test_delegation_settings.pyindex 5e3f34ba..46a7773a 100644--- a/packages/core/tests/unit/test_delegation_settings.py+++ b/packages/core/tests/unit/test_delegation_settings.py@@ -144,6 +144,20 @@ def _web(person_id: int, *, signed_in: bool = True) -> Session:caller_person_id=r.principal), False),("principal on Telegram without a webhook secret",lambda r: Session(origin_channel="telegram", origin_channel_ref="5001", caller_person_id=r.principal), False),+ # A channel whose adapter verified the sender itself: like Slack, only+ # in a conversation it also marked private.+ ("principal in an adapter-verified private chat",+ lambda r: Session(session_id="otherchat:dm:1", origin_channel="otherchat",+ caller_person_id=r.principal, speaker_verified=True, private_chat=True), True),+ ("principal in an adapter-verified shared space",+ lambda r: Session(session_id="otherchat:space:1", origin_channel="otherchat",+ caller_person_id=r.principal, speaker_verified=True), False),+ ("an adapter's private chat it didn't verify the sender of",+ lambda r: Session(session_id="otherchat:dm:1", origin_channel="otherchat",+ caller_person_id=r.principal, private_chat=True), False),+ ("an adapter-verified chat started by an email",+ lambda r: Session(session_id="otherchat:dm:1", origin_channel="otherchat", email_from="[email protected]",+ caller_person_id=r.principal, speaker_verified=True, private_chat=True), False),("a teammate on the web", lambda r: _web(r.teammate), False),("an email turn about the principal's mail",lambda r: Session(caller_person_id=r.principal, private_to_principal=True), False),@@ -353,3 +367,16 @@ def test_the_setup_check_is_bounded(roster: SimpleNamespace, monkeypatch: pytestdef test_no_address_counts_as_typed_beside_an_attachment(attachment: str) -> None:assert typed_addresses(f"{attachment}\n\nemail [email protected] as me") == set()assert typed_addresses("email [email protected] as me") == {"[email protected]"}+++def test_an_adapters_private_chat_is_private_only_for_a_sender_it_verified() -> None:+ from openexecutive.delegation.settings import private_conversation++ def chat(**kw: object) -> Session:+ return Session(session_id="otherchat:dm:1", origin_channel="otherchat", caller_person_id=1, **kw) # type: ignore[arg-type]++ assert private_conversation(chat(private_chat=True, speaker_verified=True)) is True+ # Anyone writing into an unverified one could manage its follow-ups+ # (correction_tools._scheduled_by asks nothing else).+ assert private_conversation(chat(private_chat=True)) is False+ assert private_conversation(chat(speaker_verified=True)) is Falsediff --git a/packages/core/tests/unit/test_people_tools.py b/packages/core/tests/unit/test_people_tools.pyindex 7726edd1..d09fe494 100644--- a/packages/core/tests/unit/test_people_tools.py+++ b/packages/core/tests/unit/test_people_tools.py@@ -16,6 +16,7 @@ from typing import Anyimport pytestfrom openexecutive.agents import overrides as agent_overrides+from openexecutive.delegation.settings import DelegationOverridefrom openexecutive.departments import registry as dept_registryfrom openexecutive.departments import store as dept_storefrom openexecutive.memory import episodic as episodic_module@@ -375,6 +376,31 @@ def test_unverified_surfaces_cannot_change_the_roster(assert "Mallory" not in _names()+def test_owner_on_a_channel_its_adapter_verified_can_change_the_roster(owner_id: int) -> None:+ with _turn(Session(origin_channel="otherchat", caller_person_id=owner_id, speaker_verified=True)):+ result = _call(handle_upsert_person, {"full_name": "Cindy Lee"})+ assert result["status"] == "ok"++[email protected]("surface", [+ # No People entry resolved, or a turn an email started: the adapter's+ # flag vouches for neither.+ {"origin_channel": "otherchat", "speaker_verified": True, "caller_person_id": None},+ {"origin_channel": "otherchat", "speaker_verified": True, "email_from": "[email protected]"},+ {"origin_channel": "otherchat", "speaker_verified": True, "unattended": True},+ {"origin_channel": "otherchat", "speaker_verified": True, "private_to_principal": True},+ {"origin_channel": "otherchat", "speaker_verified": True, "delegation_override": DelegationOverride(enabled=True)},+], ids=["no_caller", "email", "unattended", "private_to_principal", "eval_override"])+def test_an_adapter_flag_alone_is_not_a_verified_surface(+ owner_id: int, surface: dict[str, Any]+) -> None:+ kwargs = {"caller_person_id": owner_id, **surface}+ with _turn(Session(**kwargs)):+ result = _call(handle_upsert_person, {"full_name": "Mallory"})+ assert result["status"] == "refused"+ assert "Mallory" not in _names()++def test_owner_in_a_private_telegram_chat_can_change_the_roster(owner_id: int, monkeypatch: pytest.MonkeyPatch) -> None:diff --git a/packages/core/tests/unit/test_private_turns.py b/packages/core/tests/unit/test_private_turns.pyindex e6c749b6..836a3e23 100644--- a/packages/core/tests/unit/test_private_turns.py+++ b/packages/core/tests/unit/test_private_turns.py@@ -898,6 +898,9 @@ def test_sent_by_teammate(roster: SimpleNamespace, monkeypatch: pytest.MonkeyPatassert sent_by_teammate("slack", "U_X", None) is None# A surface that proves nobody: Google Chat, or Telegram without the secret.assert sent_by_teammate("google_chat", "x", person(roster.teammate)) is None+ # Unless its adapter verified the sender itself, as the turn's session will say.+ assert sent_by_teammate("otherchat", "x", person(roster.teammate), speaker_verified=True) == roster.teammate+ assert sent_by_teammate("otherchat", "x", None, speaker_verified=True) is Noneunverified = get_settings().model_copy(update={"telegram_webhook_secret": None})monkeypatch.setattr("openexecutive.config.get_settings", lambda: unverified)assert sent_by_teammate("telegram", "5002", person(roster.teammate)) is None@@ -1909,3 +1912,11 @@ def test_contacts_follow_the_role_on_the_principals_turn_only(roster: SimpleNameassert _contacts_in_prompt(_private_turn(roster)) is Falseassert _contacts_in_prompt(_principal_web(roster)) is Trueassert _contacts_in_prompt(_teammate_web(roster)) is False+++def test_sent_by_principal_on_an_adapter_verified_channel(roster: SimpleNamespace) -> None:+ from openexecutive.orchestrator.people_tools import sent_by_principal++ owner = people_store.get_person(roster.principal)+ assert sent_by_principal("otherchat", "x", owner) is False+ assert sent_by_principal("otherchat", "x", owner, speaker_verified=True) is True