ApplyWise

Run policy gates + duplicate check, fill answers from the profile and local LLMs, and list unresolved fields. Unresolved free-text fields come back as `client_tasks` for the calling agent to write. `src` names the source of every answer that is not "profile". A result too large for one response is paged: it carries `next` and `total`; call again with `cursor=next` to get the next page of the SAME plan (from memory, no re-plan) until `next` is null. Pages keep the shape (answers/src stay dicts) so they merge. The first call of a session may ask the user the top open profile questions (elicitati…

Top open profile gaps (questions the tool could not answer, or answered with a default), ranked by frequency x impact (blocked applications weigh most). Ask the user these, then call answer_profile_question.

Origin, model, prompt hash and ancestor chain for a text id.

The user types the code they received (email/SMS) for a submission in status `awaiting_code`. Ask the USER; never try to read their mail or guess. Only the format is checked; the code is typed into the open page, the page's verify button is clicked once, then the normal confirmation check runs. One attempt per code; the application is never resubmitted; after `verification.code_ttl_s` it becomes a `handoff`.

Match open submissions (submitted/unknown/submitting/handoff) to confirmation emails and mark confident matches `confirmed` (evidence = email subject/date; never bodies). Checks run at ingest.reconcile_delays_min after each submit; force=true checks now. With the default client mail source and no `messages`, returns a `client_task`: fetch recent confirmation-email summaries and pass them here or to ingest_confirmations. An unknown with no match after the last window stays unknown and is listed under `unresolved`. Read-only on mail; never resubmits.

Record provenance for a text artifact (kind: resume_bullet|cover_letter|answer|profile_fact). origin: user_written | llm_generated (llm_generated needs `model`). `context` = job/question the text answers.

Propose (and, if a coder backend is configured, implement as a PR for human review) a change to this tool. kind: platform_adapter | control | config | new_tool | bug (auto-detected if omitted).

Inspect (no outcome) or resolve a submission stuck in submitting/unknown. outcome: submitted|failed| handoff. Requires `evidence` = the evidence folder path reported for the ref. Audit-logged.

Apply from any mix of sources in one run: explicit `links` (or `links_file`, one URL per line), job links the user emailed to themselves (read-only mail; sender, recipient and label come from config only; `mail` may only narrow with {query, since, since_days}), and discovery (`discovery` = search_jobs arguments). Priority: links, then mail, then discovery. `sources` subsets ["links","mail","discovery"]. `max_applications` (whole number >= 1; default intake.max_applications or run_size feedback, capped at intake.max_applications_cap) caps the eligible postings handled, the same in dry and live …

Report of a run (default: the latest): counts plus rows per status (submitted, confirmed, dry_run_ok, needs_human, quota_blocked, skipped, unsupported_site, unknown, failed; see run_applications), each with `why`. `category` shows one only (the old names handed_off and dry_run still work).

Search postings across enabled platforms in parallel. Returns compact rows: ref, co, title, loc, pay, flags. The first call runs the whole search once; pass the returned `next` as `cursor` for more pages (instant).

Progress of a search_jobs session: status, boards done/total, rows, elapsed. Accepts a session id or cursor.

Seed dedupe from confirmation-email history (default ingest.seed_since_days=180) before a run, so no side files are needed. mbox/imap sources are read directly; with the client source and no `messages` this returns a `client_task` to fetch summaries and call it again with them.

Submit using the best available path (platform API, else browser driver). Honors global dry_run; a per-call dry_run can only make it safer. `approval_id` is the server-issued id from plan_application. With approval_mode=human a person must approve (dialog, or `job-apply-mcp approve <id>`).

Pull confirmation emails from the configured read-only source (ingest.source: mbox or imap) for the last `since_days` days and record them as already applied. Never sends, moves, flags or deletes mail.

Train a LoRA on the user's own texts, gate it against the incumbent, promote only if better. trigger: manual | new_data (skips below the configured threshold) | rollback (restore previous adapter). wait=False starts in the background; poll tune_status.

Local style-tuning state: backend, promoted/previous adapter, new user texts vs threshold, last run.

Which ATS hosts have a stored login (host and count only, never a username's password), whether the credentials consent window is open, accounts awaiting email verification, and this run's login flags (lockout, wrong_password, captcha). Read-only: logins are added by a human with `job-apply-mcp vault add`.

User approves LLM text. Without edited_text -> user_verified; with it -> user_edited child plus diff.