Skip to content

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).

fix(watchlist): page watches keep no keyword trigger; ticker watches ground on the ticker

Rufusb162e1da7285
diff --git a/packages/core/openexecutive/architecture/architecture-facts.yaml b/packages/core/openexecutive/architecture/architecture-facts.yaml
index 0e8a9152..509f6ca7 100644
--- a/packages/core/openexecutive/architecture/architecture-facts.yaml
+++ b/packages/core/openexecutive/architecture/architecture-facts.yaml
@@ -1373,8 +1373,8 @@ external_monitoring:
company > competitor > vendor > ticker > initiative > priority > watch.
Partial (token) matching ignores stopwords and tokens < 4 chars.
- score ledger: +2 entity in company data (mandatory), +1 entity already
- watched under another source, +1 target is the entity's own source (the
- entity's ticker or a profile-tracked ticker / a URL whose SITE LABEL —
+ watched under another source, +1 target is the entity's own source (for
+ stock/edgar the grounding entity IS the ticker / a URL whose SITE LABEL —
"acme" in status.acme.com, acme.co.uk; never a subdomain or TLD — is the
entity's / a primary-source host: sec.gov, federalregister.gov,
eur-lex), +1 finding confidence high, +1 verification confirmed, +1
@@ -1396,9 +1396,14 @@ external_monitoring:
budget is filed as a suggestion and charged to that budget).
- quiet defaults on every research row (model cannot loosen): cadence
daily (vendor_status hourly; page_watch/query weekly), severity_floor
- medium, feed keyword trigger = material-event words + priority terms
- (NEVER the entity name: feed summaries carry the feed label, so it would
- match every entry), stock abs_change_pct_gte=5.
+ medium, keyword trigger (rss/query only — a page_watch summary is
+ "page changed" and would never match) = material-event words +
+ priority terms (NEVER the entity name: feed summaries carry the feed
+ label, so it would match every entry), stock abs_change_pct_gte=5.
+ Vocabulary: URL targets contribute their site label only; short
+ whole-term names (IBM, AWS) still match in longer forms; the policy
+ stamp keeps the model's entity string when nothing matched, so a
+ not_relevant decline on an ungrounded suggestion still blacklists it.
- direct → mode=active, origin=research; suggestion → mode=dry_run,
origin=research_proposed; rationale in `notes`; policy stamp (entity,
grounding_kind, specialist, score, reasons, source_url) in
diff --git a/packages/core/openexecutive/architecture/prebuilt/external_monitoring.json b/packages/core/openexecutive/architecture/prebuilt/external_monitoring.json
index 4b767cb9..3c650425 100644
--- a/packages/core/openexecutive/architecture/prebuilt/external_monitoring.json
+++ b/packages/core/openexecutive/architecture/prebuilt/external_monitoring.json
@@ -1,7 +1,7 @@
{
"section_id": "external_monitoring",
"title": "External Monitoring",
- "markdown": "`openexecutive.monitoring` watches the outside world on a heartbeat and turns detected changes into briefing proposals via the same alert pipeline that handles inbound email and Slack.\n\nThe `external_monitor_scan` heartbeat (`__internal__` channel, default every 5 min) walks `list_watchlist(enabled_only=True)`, skipping rows fresher than their per-source cadence floor. For each due row it fires a read-only source adapter resolved from `_REGISTRY` by `signal_type`:\n\n- `vendor_status` — Statuspage Atom/RSS incident feeds (AWS, Stripe, GitHub, …). Reads each incident's current status out of the entry body, parses `<updated>` into `published_at`, and keys its dedup on `(entry id, <updated>)`; a **seeding** source (see below).\n- `rss` — generic Atom/RSS via feedparser (changelogs, layoffs.fyi, filings). Parses each entry's `<pubDate>`/`<updated>` into `published_at`; a **seeding** source (see below).\n- `stock` — Yahoo Finance chart endpoint; fires on `abs_change_pct_gte` moves.\n- `page_watch` — change-detection on a feed-less page. Fetches via the keyless httpx fetcher by default, or via xcrawl's scrape API when the row carries `config.fetch = \"xcrawl\"` — so JS-rendered / bot-blocked pages that publish no RSS (most modern news / marketing sites) are still monitorable.\n- `edgar` and the BILLED `query` web-search adapter.\n\nEach `Signal` is trigger-filtered, severity-clamped to the row's `[floor, ceiling]`, and INSERTed into `external_signals` where `UNIQUE(dedup_key)` drops replays. Survivors pass a suppression cascade (`baseline` → `stale` → `dry_run` → `below_floor` → capture-time relevance enrichment → promote), then `promote_signal_to_alert` builds an `AlertEvent` handed to `alerts.pipeline.schedule_evaluation` and surfaced as a `/today` proposal.\n\nEvery signal carries two timestamps that are never conflated: `captured_at` (when the monitor first saw it) and `published_at` (when the upstream says it happened — RSS `<pubDate>`, EDGAR filing date; null for `stock`, `page_watch`, `query`). Two freshness gates run first in the cascade, before anything that costs an LLM call. **Baseline:** the first poll that returns entries for a row whose adapter declares `seed_on_first_poll` (`rss`, `edgar`) records every entry already in the feed — trigger misses included, so the first entry that ever matches a keyword is news and a later, wider trigger can't resurface old ones — as `suppressed_baseline`, promotes nothing, and stamps `watchlist.baselined_at`, so a new watch reports what changes from now on instead of replaying the feed's back-catalogue (the same idea as `page_watch`'s first-observation baseline). It is keyed on `baselined_at` rather than `last_polled_at`, so a failed first fetch can't forfeit it; the claim and the recording are one transaction (a compare-and-swap on the stamp plus the rows, all-or-nothing), so of two overlapping scans exactly one records the back-catalogue and a failure part-way leaves nothing behind to replay; the other scan promotes only entries dated after that stamp (undated entries count as baseline, since the feed controls the date; entries dated more than a few minutes past its own clock are deferred rather than recorded); and baseline rows don't count against `max_signals_per_scan`, so a large feed can't be half-baselined. `vendor_status` used to sit outside both gates for a structural reason: its dedup key was `sha256(slug, entry id)`, and an incident's id never changes across its updates, so any suppressed insert muted that incident for good. Keying on `(entry id, <updated>)` instead (issue #90) makes a suppression cost one *state* of an incident rather than the incident, so both gates now apply to vendor feeds too — and an incident moving Investigating → Resolved mints a new key and surfaces, while re-polling an unchanged feed still dedups. Because a history feed's archive is mostly incidents resolved months ago, the adapter also carves live news out of its own baseline: it reads each incident's current status from the entry body (Statuspage renders the newest update first as `<strong>Resolved</strong>` / `Investigating` / `Monitoring` / … — the body is parsed by a real HTML parser, off the event loop, and the reading is deliberately asymmetric: any sign that the incident is over closes it, wherever it appears, while only a marked-up label can say it is still open. Working out which update is newest turned out to be something tag soup cannot be trusted to express, and every attempt reported a long-resolved incident as live) and exempts the ones still OPEN via the optional `promote_on_baseline` hook, so a watch added during an outage reports that outage on its first poll while the resolved archive is recorded as `suppressed_baseline`. An unrecognised status counts as closed — a vendor changing feed format must not be able to promote its whole archive at HIGH, and nothing is lost, since the next `<updated>` bump surfaces normally. An exempt entry must still pass the row's trigger filter (one that misses stays in the baseline, so widening a trigger later cannot resurface it) and is still judged by the stale gate below: the exemption buys an entry past the baseline, never past its own timestamp, because \"this is live\" is a reading of vendor-controlled markup and an entry the feed dates outside the age window is not news whatever that reading says. **Stale:** a signal whose `published_at` is older than `EXTERNAL_MONITOR_MAX_SIGNAL_AGE_DAYS` (default 7; `0` disables) at capture time is recorded as `suppressed_stale` and never promoted — a January article a feed resurfaces in September is not September news. An entry dated more than `EXTERNAL_MONITOR_MAX_FUTURE_SKEW_HOURS` ahead (default 24; `0` disables; `config_json.max_future_skew_hours` overrides it per row for calendar or maintenance feeds that legitimately date entries ahead) is deferred instead: skipped for the tick and not recorded (recording would burn its dedup key and let a feed mute an announcement for good by post-dating it), with one aggregated `external_signal_deferred` audit row per poll — carrying each held-back entry's summary and link, and emitted even if the poll later raises — then judged normally once the date passes. Inside the window, the alert body handed to triage carries `Published:` and `Discovered:` lines so the item is judged on when it happened. Adapters prefer a plausible date key over one more than a day in the future (and keep the future value when every key is implausible, so the pipeline defers it rather than waving an undated entry through), and the alert body collapses whitespace in the summary so no source can forge its own labeled body line.\n\nThe `query` adapter is a special case: it emits every web hit flat-LOW (it can't judge materiality per-hit), so for query signals enrichment runs BEFORE the floor gate and `_grade_query_severity` regrades from the relevance read (≥0.8 HIGH, ≥0.5 MEDIUM, else LOW). Without this, any query watch item with a `severity_floor` above LOW would suppress every hit — which is what left the Monitoring section empty even while standing queries were returning material findings.\n\nWhich lane a proposal lands in is decided by `briefing.ranking.categorize`: an unrouted, low/medium signal from a monitoring source (`stock`, `vendor_status`, `rss`, `query`, `edgar`, `page_watch`, or any `external:*` topic tag) is `monitoring` (the collapsible Monitoring section); a routed or high/urgent one is `action` (the \"Needs you\" queue). The triage prompt's External Signals rule covers all six source kinds so it trusts the source and emits the `external:*` tags that drive this split.\n\nThe watchlist is editable from chat (`add_watchlist_entry`, `tune_watchlist_entry`) and HTTP (`/watchlist`); the `executive_research` workflow proposes what to watch through a deterministic policy (next section). Because that workflow is LLM-driven and historically proposed feed URLs it never verified (most were dead — 404 / 403 / not-actually-a-feed), every `rss` target is validated at insert time (`monitoring.target_validation`): a URL that fetches and parses as a feed is kept; a public page that isn't a feed is converted to a scrape-backed `page_watch` when xcrawl can read it, otherwise rejected (HTTP 422 / tool error); SSRF-blocked or unparseable URLs are rejected outright and never handed to xcrawl. Non-`rss` types insert unchanged with no network I/O.\n\n### One watch, one card — and dismissals teach the watch\n\n`promote_signal_to_alert` stamps the `AlertEvent` with `dedup_hint=\"watch:<slug>\"`, which `alerts.pipeline` uses as the *alert* dedup key. A repeat from the same watch coalesces into the open card (`occurrence_count`, `last_seen_at`, severity max) rather than minting another, and re-pings only when severity rose into high/urgent — so a ticker that stays over its threshold or an incident that keeps updating no longer produces a new \"Needs you\" item every day. The signal-level `dedup_key` (stock's UTC-date bucket, vendor_status's `<updated>`) is untouched, so every observation still lands in `external_signals`. Dismissing a watch-sourced alert calls `store.record_dismissal(slug)` (`dismiss_count += 1`, `trust_score = max(0.2, trust × 0.8)`); approving calls `record_confirmation` (+0.05). `trust_score` discounts the briefing ranking and is shown to the Executive's alert review as evidence, alongside the newer signals for that watch (a \"Resolved\" incident state, a reversed move) that let it close the card with evidence.\n\n### What the research pass may put on the watchlist\n\nEvery watchlist row carries an `origin`: `manual` (the principal, via UI/API), `executive` (the chat tool acting on a request), `research` (the research pass added it on its own) or `research_proposed` (a pending suggestion). The `executive_research` workflow's watchlist pass no longer calls `add_watchlist_entry`; its only tool is `propose_watch` (slug, signal_type, target, `grounding_entity`, `rationale`, `certainty`), and `monitoring.research.watch_policy` decides what happens to each proposal from company data, not from the model's confidence in itself:\n\n- **Direct add** — the row lands live, `origin=research`, with quiet defaults the model cannot loosen (daily cadence — hourly for `vendor_status`, weekly for `page_watch`/`query` — `severity_floor=medium`, a keyword trigger of material-event words + the current-year priority terms for feeds — never the entity's own name, which appears in every entry's feed label and would fire on everything — and `abs_change_pct_gte=5` for stocks). Requires the `grounding_entity` to name an external entity in company data — the company itself, a `competitive_landscape.primary_competitors` entry, or one of the profile's `vendors` / `tickers` (an initiative title or a current-year priority also grounds a proposal, but only ever to a suggestion: they are bags of common words a planted finding can echo) — *and* a score ≥ 4 on a fixed ledger: +2 entity in company data (mandatory), +1 entity already watched under another source, +1 target is the entity's own source (the entity's ticker or one the profile tracks; a URL whose site label — `acme` in `status.acme.com` / `acme.co.uk`, never a subdomain or TLD — is the entity's; or a primary-source host such as sec.gov), +1 finding confidence high, +1 verification confirmed, +1 cross-specialist consensus (the three finding points count only when the cited finding concerns this source: a URL target must share its site with one of the finding's cited URLs, a ticker must appear in its text — a strong finding cannot be borrowed for an unrelated page), ±1 from the policy's own approval history for that `(signal_type, grounding kind)` once it has ≥5 samples. A direct add is further reserved for the entity's **own** source (its ticker, its site, its status page): a well-corroborated third-party page about a competitor is the principal's call. The model's `certainty` can only downgrade a direct add to a suggestion; a `query` watch is always a suggestion. At most `WATCHLIST_RESEARCH_MAX_DIRECT_ADDS` (2) per run. When one term appears in several sources the strongest kind wins (company > competitor > vendor > ticker > initiative > priority > watch label).\n- **Suggestion** — anything that validates, has a linked finding and scores at least 1 but misses the bar is inserted in `dry_run` (polls and records signals, never alerts) with `origin=research_proposed` and the rationale in `notes`, at most `WATCHLIST_RESEARCH_MAX_PROPOSALS` (2) per run. `/watchlist` shows them in a \"Suggested by the Executive\" section with Approve (`POST /watchlist/{slug}/approve` → `active`, `origin=research`) and Decline (`POST /watchlist/{slug}/decline` with a reason: `not_relevant` blacklists the entity, `wrong_source` blacklists only this target, `too_noisy` keeps the source live with `severity_floor=high` — the one way a suggestion goes live without an approve — and counts as a decline for calibration). A suggestion nobody reviews within `WATCHLIST_PROPOSAL_TTL_DAYS` (14) is removed. The morning brief mentions the pending count in one line; a `watchlist_suggestions` alert nudges only once ≥3 suggestions have waited ≥7 days — one card for the whole pile (an open card is refreshed in place; a dismissed one is not re-minted until the next ISO week), so acting on a suggestion never spawns another nudge.\n- **Reject** — an invalid target, a second watch on the same site + signal type (disabled rows included), a declined target or entity, nothing vouching for it (no linked finding, score 0), the enabled-watch ceiling `WATCHLIST_MAX_ENABLED` (40; suggestions poll too, so the ceiling stops them as well), or a spent budget. Every decision is audited (`watchlist_research_added` / `_suggested` / `_rejected`) with the score and reasons; the stamp also lives in the row's `config_json._policy` so approve/decline/auto-disable can attribute the outcome.\n\n**Declines are remembered and enforced.** `watchlist_declines` is keyed by the normalized target (upper-cased ticker; URL with `https` forced, `www.` dropped, host and path lower-cased, query, fragment and trailing slash removed; free-text queries case- and whitespace-folded). A `not_relevant` decline also blacklists the *entity*: any later proposal whose `grounding_entity` names it is refused whatever the target. An explicit decline — the Decline button, \"Stop watching…\" on a research-added card, `remove_watchlist_entry` or `DELETE /watchlist/{slug}` on a research-origin row — is permanent; an unreviewed expiry may be re-proposed once after 90 days. The `propose_watch` handler refuses a declined target or entity before anything is fetched, so a new slug cannot route around a decline (URL keys also fold percent-encoding, dot segments and a trailing host dot); the list is also rendered to the model as DECLINED. The routing pass that runs before the watchlist pass has no watchlist write tools at all (`add_watchlist_entry`, `tune_watchlist_entry`, `remove_watchlist_entry` are withheld from synthesis), and `tune_watchlist_entry` accepts only `notes` on a pending suggestion — never `mode` / `enabled` (only the principal's approve or decline moves one out of review) nor cadence / floor / trigger (it goes live with the quiet defaults policy gave it). Every URL-typed target (`rss`, `vendor_status`, `page_watch`) is checked against the SSRF guard at insert time, and a suggestion's `source_url` link is kept only when it is a public http(s) URL.\n\n**The policy learns from outcomes.** Approve, decline, expiry and auto-disable write `watchlist_policy_outcomes` rows keyed by `(signal_type, grounding kind, specialist)`; the pass renders the tallies (\"stock watches grounded in a competitor: 4 approved / 1 declined\"; \"proposals from cso: …\") and the score ledger reads them. The research turn also shows each existing watch's `origin`, `fired_count`, `dismiss_count` and `trust_score`.\n\n**Research watches retire themselves.** The scheduler's 15-minute sweep (`watch_policy.sweep`, alongside the alert expiry sweep) disables a `research`-origin watch — audited as `watchlist_auto_disabled`, re-enable from `/watchlist` — when it fired ≥5 alerts of which ≥2 were dismissed and trust ≤ 0.5, or after 3 consecutive poll failures (silence is deliberately not a rule: an unchanged page or a healthy vendor is a working watch); the retired target is also recorded as a 90-day decline so the next run cannot re-add it under a new slug with fresh counters (a disabled row already counts as \"same source watched\"). Approve, decline and expiry are compare-and-act on \"still pending\", so a concurrent approve always wins over a decline or the sweep. Direct adds and auto-disables appear in the brief's \"handled overnight\" block as `watching` / `stopped_watching`. The research skip-if-unchanged fingerprint hashes only enabled, `active` rows, so approving or declining a suggestion never triggers a fresh 7-specialist run.\n\n### Invariants\n\n- Adapters are read-only — they never write upstream and never auto-execute.\n- Every `Signal` carries a deterministic `dedup_key` and a mandatory `provenance_url`.\n- Fetches are SSRF-guarded and bounded by `external_monitor_max_fetch_bytes`; xcrawl scrape (off by default, gated by `XCRAWL_ENABLED` + `XCRAWL_API_KEY`) is the one path that delegates the fetch to an external API.\n- Suppressed signals are still persisted so audits show the full picture.\n- A repeat from the same watch never becomes a second open card: the alert-level `watch:<slug>` key coalesces it, and only a severity escalation re-dispatches.\n- The research model never writes the watchlist: it proposes, deterministic policy adds (only when grounded in company data) or suggests, and a target the principal declined is refused at the handler.",
+ "markdown": "`openexecutive.monitoring` watches the outside world on a heartbeat and turns detected changes into briefing proposals via the same alert pipeline that handles inbound email and Slack.\n\nThe `external_monitor_scan` heartbeat (`__internal__` channel, default every 5 min) walks `list_watchlist(enabled_only=True)`, skipping rows fresher than their per-source cadence floor. For each due row it fires a read-only source adapter resolved from `_REGISTRY` by `signal_type`:\n\n- `vendor_status` — Statuspage Atom/RSS incident feeds (AWS, Stripe, GitHub, …). Reads each incident's current status out of the entry body, parses `<updated>` into `published_at`, and keys its dedup on `(entry id, <updated>)`; a **seeding** source (see below).\n- `rss` — generic Atom/RSS via feedparser (changelogs, layoffs.fyi, filings). Parses each entry's `<pubDate>`/`<updated>` into `published_at`; a **seeding** source (see below).\n- `stock` — Yahoo Finance chart endpoint; fires on `abs_change_pct_gte` moves.\n- `page_watch` — change-detection on a feed-less page. Fetches via the keyless httpx fetcher by default, or via xcrawl's scrape API when the row carries `config.fetch = \"xcrawl\"` — so JS-rendered / bot-blocked pages that publish no RSS (most modern news / marketing sites) are still monitorable.\n- `edgar` and the BILLED `query` web-search adapter.\n\nEach `Signal` is trigger-filtered, severity-clamped to the row's `[floor, ceiling]`, and INSERTed into `external_signals` where `UNIQUE(dedup_key)` drops replays. Survivors pass a suppression cascade (`baseline` → `stale` → `dry_run` → `below_floor` → capture-time relevance enrichment → promote), then `promote_signal_to_alert` builds an `AlertEvent` handed to `alerts.pipeline.schedule_evaluation` and surfaced as a `/today` proposal.\n\nEvery signal carries two timestamps that are never conflated: `captured_at` (when the monitor first saw it) and `published_at` (when the upstream says it happened — RSS `<pubDate>`, EDGAR filing date; null for `stock`, `page_watch`, `query`). Two freshness gates run first in the cascade, before anything that costs an LLM call. **Baseline:** the first poll that returns entries for a row whose adapter declares `seed_on_first_poll` (`rss`, `edgar`) records every entry already in the feed — trigger misses included, so the first entry that ever matches a keyword is news and a later, wider trigger can't resurface old ones — as `suppressed_baseline`, promotes nothing, and stamps `watchlist.baselined_at`, so a new watch reports what changes from now on instead of replaying the feed's back-catalogue (the same idea as `page_watch`'s first-observation baseline). It is keyed on `baselined_at` rather than `last_polled_at`, so a failed first fetch can't forfeit it; the claim and the recording are one transaction (a compare-and-swap on the stamp plus the rows, all-or-nothing), so of two overlapping scans exactly one records the back-catalogue and a failure part-way leaves nothing behind to replay; the other scan promotes only entries dated after that stamp (undated entries count as baseline, since the feed controls the date; entries dated more than a few minutes past its own clock are deferred rather than recorded); and baseline rows don't count against `max_signals_per_scan`, so a large feed can't be half-baselined. `vendor_status` used to sit outside both gates for a structural reason: its dedup key was `sha256(slug, entry id)`, and an incident's id never changes across its updates, so any suppressed insert muted that incident for good. Keying on `(entry id, <updated>)` instead (issue #90) makes a suppression cost one *state* of an incident rather than the incident, so both gates now apply to vendor feeds too — and an incident moving Investigating → Resolved mints a new key and surfaces, while re-polling an unchanged feed still dedups. Because a history feed's archive is mostly incidents resolved months ago, the adapter also carves live news out of its own baseline: it reads each incident's current status from the entry body (Statuspage renders the newest update first as `<strong>Resolved</strong>` / `Investigating` / `Monitoring` / … — the body is parsed by a real HTML parser, off the event loop, and the reading is deliberately asymmetric: any sign that the incident is over closes it, wherever it appears, while only a marked-up label can say it is still open. Working out which update is newest turned out to be something tag soup cannot be trusted to express, and every attempt reported a long-resolved incident as live) and exempts the ones still OPEN via the optional `promote_on_baseline` hook, so a watch added during an outage reports that outage on its first poll while the resolved archive is recorded as `suppressed_baseline`. An unrecognised status counts as closed — a vendor changing feed format must not be able to promote its whole archive at HIGH, and nothing is lost, since the next `<updated>` bump surfaces normally. An exempt entry must still pass the row's trigger filter (one that misses stays in the baseline, so widening a trigger later cannot resurface it) and is still judged by the stale gate below: the exemption buys an entry past the baseline, never past its own timestamp, because \"this is live\" is a reading of vendor-controlled markup and an entry the feed dates outside the age window is not news whatever that reading says. **Stale:** a signal whose `published_at` is older than `EXTERNAL_MONITOR_MAX_SIGNAL_AGE_DAYS` (default 7; `0` disables) at capture time is recorded as `suppressed_stale` and never promoted — a January article a feed resurfaces in September is not September news. An entry dated more than `EXTERNAL_MONITOR_MAX_FUTURE_SKEW_HOURS` ahead (default 24; `0` disables; `config_json.max_future_skew_hours` overrides it per row for calendar or maintenance feeds that legitimately date entries ahead) is deferred instead: skipped for the tick and not recorded (recording would burn its dedup key and let a feed mute an announcement for good by post-dating it), with one aggregated `external_signal_deferred` audit row per poll — carrying each held-back entry's summary and link, and emitted even if the poll later raises — then judged normally once the date passes. Inside the window, the alert body handed to triage carries `Published:` and `Discovered:` lines so the item is judged on when it happened. Adapters prefer a plausible date key over one more than a day in the future (and keep the future value when every key is implausible, so the pipeline defers it rather than waving an undated entry through), and the alert body collapses whitespace in the summary so no source can forge its own labeled body line.\n\nThe `query` adapter is a special case: it emits every web hit flat-LOW (it can't judge materiality per-hit), so for query signals enrichment runs BEFORE the floor gate and `_grade_query_severity` regrades from the relevance read (≥0.8 HIGH, ≥0.5 MEDIUM, else LOW). Without this, any query watch item with a `severity_floor` above LOW would suppress every hit — which is what left the Monitoring section empty even while standing queries were returning material findings.\n\nWhich lane a proposal lands in is decided by `briefing.ranking.categorize`: an unrouted, low/medium signal from a monitoring source (`stock`, `vendor_status`, `rss`, `query`, `edgar`, `page_watch`, or any `external:*` topic tag) is `monitoring` (the collapsible Monitoring section); a routed or high/urgent one is `action` (the \"Needs you\" queue). The triage prompt's External Signals rule covers all six source kinds so it trusts the source and emits the `external:*` tags that drive this split.\n\nThe watchlist is editable from chat (`add_watchlist_entry`, `tune_watchlist_entry`) and HTTP (`/watchlist`); the `executive_research` workflow proposes what to watch through a deterministic policy (next section). Because that workflow is LLM-driven and historically proposed feed URLs it never verified (most were dead — 404 / 403 / not-actually-a-feed), every `rss` target is validated at insert time (`monitoring.target_validation`): a URL that fetches and parses as a feed is kept; a public page that isn't a feed is converted to a scrape-backed `page_watch` when xcrawl can read it, otherwise rejected (HTTP 422 / tool error); SSRF-blocked or unparseable URLs are rejected outright and never handed to xcrawl. Non-`rss` types insert unchanged with no network I/O.\n\n### One watch, one card — and dismissals teach the watch\n\n`promote_signal_to_alert` stamps the `AlertEvent` with `dedup_hint=\"watch:<slug>\"`, which `alerts.pipeline` uses as the *alert* dedup key. A repeat from the same watch coalesces into the open card (`occurrence_count`, `last_seen_at`, severity max) rather than minting another, and re-pings only when severity rose into high/urgent — so a ticker that stays over its threshold or an incident that keeps updating no longer produces a new \"Needs you\" item every day. The signal-level `dedup_key` (stock's UTC-date bucket, vendor_status's `<updated>`) is untouched, so every observation still lands in `external_signals`. Dismissing a watch-sourced alert calls `store.record_dismissal(slug)` (`dismiss_count += 1`, `trust_score = max(0.2, trust × 0.8)`); approving calls `record_confirmation` (+0.05). `trust_score` discounts the briefing ranking and is shown to the Executive's alert review as evidence, alongside the newer signals for that watch (a \"Resolved\" incident state, a reversed move) that let it close the card with evidence.\n\n### What the research pass may put on the watchlist\n\nEvery watchlist row carries an `origin`: `manual` (the principal, via UI/API), `executive` (the chat tool acting on a request), `research` (the research pass added it on its own) or `research_proposed` (a pending suggestion). The `executive_research` workflow's watchlist pass no longer calls `add_watchlist_entry`; its only tool is `propose_watch` (slug, signal_type, target, `grounding_entity`, `rationale`, `certainty`), and `monitoring.research.watch_policy` decides what happens to each proposal from company data, not from the model's confidence in itself:\n\n- **Direct add** — the row lands live, `origin=research`, with quiet defaults the model cannot loosen (daily cadence — hourly for `vendor_status`, weekly for `page_watch`/`query` — `severity_floor=medium`, a keyword trigger of material-event words + the current-year priority terms for `rss` / `query` only — never for `page_watch`, whose summary is just \"page changed\" and would never match, and never the entity's own name, which appears in every feed entry's label and would fire on everything — and `abs_change_pct_gte=5` for stocks). Requires the `grounding_entity` to name an external entity in company data — the company itself, a `competitive_landscape.primary_competitors` entry, or one of the profile's `vendors` / `tickers` (an initiative title or a current-year priority also grounds a proposal, but only ever to a suggestion: they are bags of common words a planted finding can echo) — *and* a score ≥ 4 on a fixed ledger: +2 entity in company data (mandatory), +1 entity already watched under another source, +1 target is the entity's own source (for stock/edgar the grounding entity must be the ticker itself; a URL whose site label — `acme` in `status.acme.com` / `acme.co.uk`, never a subdomain or TLD — is the entity's; or a primary-source host such as sec.gov), +1 finding confidence high, +1 verification confirmed, +1 cross-specialist consensus (the three finding points count only when the cited finding concerns this source: a URL target must share its site with one of the finding's cited URLs, a ticker must appear in its text — a strong finding cannot be borrowed for an unrelated page), ±1 from the policy's own approval history for that `(signal_type, grounding kind)` once it has ≥5 samples. A direct add is further reserved for the entity's **own** source (its ticker, its site, its status page): a well-corroborated third-party page about a competitor is the principal's call. The model's `certainty` can only downgrade a direct add to a suggestion; a `query` watch is always a suggestion. At most `WATCHLIST_RESEARCH_MAX_DIRECT_ADDS` (2) per run. When one term appears in several sources the strongest kind wins (company > competitor > vendor > ticker > initiative > priority > watch label).\n- **Suggestion** — anything that validates, has a linked finding and scores at least 1 but misses the bar is inserted in `dry_run` (polls and records signals, never alerts) with `origin=research_proposed` and the rationale in `notes`, at most `WATCHLIST_RESEARCH_MAX_PROPOSALS` (2) per run. `/watchlist` shows them in a \"Suggested by the Executive\" section with Approve (`POST /watchlist/{slug}/approve` → `active`, `origin=research`) and Decline (`POST /watchlist/{slug}/decline` with a reason: `not_relevant` blacklists the entity, `wrong_source` blacklists only this target, `too_noisy` keeps the source live with `severity_floor=high` — the one way a suggestion goes live without an approve — and counts as a decline for calibration). A suggestion nobody reviews within `WATCHLIST_PROPOSAL_TTL_DAYS` (14) is removed. The morning brief mentions the pending count in one line; a `watchlist_suggestions` alert nudges only once ≥3 suggestions have waited ≥7 days — one card for the whole pile (an open card is refreshed in place; a dismissed one is not re-minted until the next ISO week), so acting on a suggestion never spawns another nudge.\n- **Reject** — an invalid target, a second watch on the same site + signal type (disabled rows included), a declined target or entity, nothing vouching for it (no linked finding, score 0), the enabled-watch ceiling `WATCHLIST_MAX_ENABLED` (40; suggestions poll too, so the ceiling stops them as well), or a spent budget. Every decision is audited (`watchlist_research_added` / `_suggested` / `_rejected`) with the score and reasons; the stamp also lives in the row's `config_json._policy` so approve/decline/auto-disable can attribute the outcome.\n\n**Declines are remembered and enforced.** `watchlist_declines` is keyed by the normalized target (upper-cased ticker; URL with `https` forced, `www.` dropped, host and path lower-cased, query, fragment and trailing slash removed; free-text queries case- and whitespace-folded). A `not_relevant` decline also blacklists the *entity*: any later proposal whose `grounding_entity` names it is refused whatever the target. An explicit decline — the Decline button, \"Stop watching…\" on a research-added card, `remove_watchlist_entry` or `DELETE /watchlist/{slug}` on a research-origin row — is permanent; an unreviewed expiry may be re-proposed once after 90 days. The `propose_watch` handler refuses a declined target or entity before anything is fetched, so a new slug cannot route around a decline (URL keys also fold percent-encoding, dot segments and a trailing host dot); the list is also rendered to the model as DECLINED. The routing pass that runs before the watchlist pass has no watchlist write tools at all (`add_watchlist_entry`, `tune_watchlist_entry`, `remove_watchlist_entry` are withheld from synthesis), and `tune_watchlist_entry` accepts only `notes` on a pending suggestion — never `mode` / `enabled` (only the principal's approve or decline moves one out of review) nor cadence / floor / trigger (it goes live with the quiet defaults policy gave it). Every URL-typed target (`rss`, `vendor_status`, `page_watch`) is checked against the SSRF guard at insert time, and a suggestion's `source_url` link is kept only when it is a public http(s) URL.\n\n**The policy learns from outcomes.** Approve, decline, expiry and auto-disable write `watchlist_policy_outcomes` rows keyed by `(signal_type, grounding kind, specialist)`; the pass renders the tallies (\"stock watches grounded in a competitor: 4 approved / 1 declined\"; \"proposals from cso: …\") and the score ledger reads them. The research turn also shows each existing watch's `origin`, `fired_count`, `dismiss_count` and `trust_score`.\n\n**Research watches retire themselves.** The scheduler's 15-minute sweep (`watch_policy.sweep`, alongside the alert expiry sweep) disables a `research`-origin watch — audited as `watchlist_auto_disabled`, re-enable from `/watchlist` — when it fired ≥5 alerts of which ≥2 were dismissed and trust ≤ 0.5, or after 3 consecutive poll failures (silence is deliberately not a rule: an unchanged page or a healthy vendor is a working watch); the retired target is also recorded as a 90-day decline so the next run cannot re-add it under a new slug with fresh counters (a disabled row already counts as \"same source watched\"). Approve, decline and expiry are compare-and-act on \"still pending\", so a concurrent approve always wins over a decline or the sweep. Direct adds and auto-disables appear in the brief's \"handled overnight\" block as `watching` / `stopped_watching`. The research skip-if-unchanged fingerprint hashes only enabled, `active` rows, so approving or declining a suggestion never triggers a fresh 7-specialist run.\n\n### Invariants\n\n- Adapters are read-only — they never write upstream and never auto-execute.\n- Every `Signal` carries a deterministic `dedup_key` and a mandatory `provenance_url`.\n- Fetches are SSRF-guarded and bounded by `external_monitor_max_fetch_bytes`; xcrawl scrape (off by default, gated by `XCRAWL_ENABLED` + `XCRAWL_API_KEY`) is the one path that delegates the fetch to an external API.\n- Suppressed signals are still persisted so audits show the full picture.\n- A repeat from the same watch never becomes a second open card: the alert-level `watch:<slug>` key coalesces it, and only a severity escalation re-dispatches.\n- The research model never writes the watchlist: it proposes, deterministic policy adds (only when grounded in company data) or suggests, and a target the principal declined is refused at the handler.",
"mermaid": "flowchart TD\n ADD[\"add (chat tool / POST /watchlist / research)\"]\n VAL[\"target_validation: rss feed? → keep / convert→page_watch(xcrawl) / reject\"]\n WL[(\"watchlist\")]\n HB[\"external_monitor_scan heartbeat (~5 min)\"]\n AD[\"read-only adapters: vendor_status / rss / stock / query / edgar / page_watch (httpx | xcrawl)\"]\n SIG[(\"external_signals UNIQUE(dedup_key)\")]\n ENRICH[\"capture-time enrichment<br/>(relevance score + why_it_matters)\"]\n PROMO[\"promote_signal_to_alert\"]\n PIPE[\"alert pipeline (triage)\"]\n TODAY[\"/today proposals\"]\n ADD --> VAL\n VAL -->|\"insert valid rows\"| WL\n HB -->|\"walk enabled rows\"| WL\n WL -->|\"poll due rows\"| AD\n AD -->|\"emit Signal\"| SIG\n SIG -->|\"baseline / stale / dry_run / floor gates\"| ENRICH\n ENRICH -->|\"≥ relevance floor\"| PROMO\n PROMO --> PIPE\n PIPE --> TODAY\n class HB hot\n class WL storage\n class VAL compute\n class AD external\n class SIG storage\n class ENRICH compute\n class PROMO compute\n class PIPE compute\n class TODAY entry\n class ADD compute",
- "generated_at": "2026-09-12T11:10:47.561830+00:00"
+ "generated_at": "2026-09-12T11:14:44.757524+00:00"
}
diff --git a/packages/core/openexecutive/monitoring/research/watch_policy.py b/packages/core/openexecutive/monitoring/research/watch_policy.py
index b433b6ad..9bdee33a 100644
--- a/packages/core/openexecutive/monitoring/research/watch_policy.py
+++ b/packages/core/openexecutive/monitoring/research/watch_policy.py
@@ -130,6 +130,7 @@ _STOPWORDS: frozenset[str] = frozenset({
"new", "more", "across", "team", "company", "inc", "corp", "ltd", "llc", "co",
"group", "labs", "platform", "product", "market", "customer", "customers",
"revenue", "sales", "enterprise", "global", "digital", "cloud", "data", "api",
+ "http", "https", "www", "com", "net", "org", "feed", "blog", "status", "news",
})
# Shortest token that may match on its own inside a multi-word term. Tickers
# and short names still match exactly (whole-term equality is checked first).
@@ -262,7 +263,10 @@ def grounding_vocabulary(
label = item.config_json.get(label_key) if isinstance(item.config_json, dict) else None
if label:
add(str(label), KIND_WATCH)
- add(item.target, KIND_WATCH)
+ # A URL target contributes its site label only ("acme" for
+ # https://status.acme.com/feed), never its scheme/host/path tokens.
+ host = registrable_domain(item.target)
+ add(_site_label(host) if host else item.target, KIND_WATCH)
add(item.slug.replace("-", " "), KIND_WATCH)
for i in initiatives:
add(str(getattr(i, "title", "") or ""), KIND_INITIATIVE)
@@ -289,6 +293,17 @@ def priority_terms(profile: Any) -> list[str]:
return out[:6]
+def _distinctive_tokens(text: str, vocabulary: dict[str, str] | None = None) -> set[str]:
+ """Tokens that may carry a partial match: not stopwords, and either long
+ enough or a whole vocabulary term in their own right (short names such
+ as IBM, AWS, SAP)."""
+ vocab = vocabulary or {}
+ return {
+ t for t in text.split()
+ if t not in _STOPWORDS and (len(t) >= _MIN_PARTIAL_TOKEN or t in vocab)
+ }
+
+
def match_entity(entity: str, vocabulary: dict[str, str]) -> tuple[str, str] | None:
"""``(term, kind)`` for the vocabulary term the entity names, else None.
@@ -301,16 +316,18 @@ def match_entity(entity: str, vocabulary: dict[str, str]) -> tuple[str, str] | N
if exact is not None and exact != KIND_WATCH:
return n, exact
# Partial matching only on distinctive tokens: no stopwords, nothing
- # shorter than _MIN_PARTIAL_TOKEN, so "Growth Inc" cannot match the
- # priority "drive growth in EMEA" and "corp" matches nothing.
- tokens = {t for t in n.split() if t not in _STOPWORDS and len(t) >= _MIN_PARTIAL_TOKEN}
+ # shorter than _MIN_PARTIAL_TOKEN unless the token is itself a whole
+ # vocabulary term ("IBM Corp" still matches competitor "IBM"), so
+ # "Growth Inc" cannot match the priority "drive growth in EMEA" and
+ # "corp" matches nothing.
+ tokens = _distinctive_tokens(n, vocabulary)
# An exact hit on a watch label is only the fallback: a company-data term
# that contains (or is contained by) the entity still wins.
best: tuple[str, str] | None = (n, exact) if exact is not None else None
if not tokens:
return best
for term, kind in vocabulary.items():
- term_tokens = {t for t in term.split() if t not in _STOPWORDS and len(t) >= _MIN_PARTIAL_TOKEN}
+ term_tokens = _distinctive_tokens(term, vocabulary)
if not term_tokens or not (term_tokens <= tokens or tokens <= term_tokens):
continue
# Prefer a company-data kind over a watch label, then the longer term.
@@ -351,11 +368,10 @@ def _is_own_source(proposal: WatchProposal, entity_term: str, vocabulary: dict[s
"""The target is the entity's own primary source: its ticker for
stock/edgar, its own domain for a URL, or an allowlisted primary host."""
if proposal.signal_type in (SOURCE_KIND_STOCK, SOURCE_KIND_EDGAR):
- # The ticker is the entity itself, or one the profile explicitly
- # tracks (`tickers`). A ticker that merely appears as some other
- # watch's target says nothing about THIS entity.
- target_norm = _norm(proposal.target)
- return target_norm == entity_term or vocabulary.get(target_norm) == KIND_TICKER
+ # Only when the grounding entity IS this ticker. A ticker the profile
+ # tracks for someone else (MSFT) says nothing about "Acme Corp"; the
+ # model grounds a ticker watch with the ticker itself.
+ return _norm(proposal.target) == entity_term
host = registrable_domain(proposal.target)
if not host:
return False
@@ -556,11 +572,13 @@ def quiet_defaults(
if proposal.signal_type == SOURCE_KIND_STOCK:
if not isinstance(trigger.get("abs_change_pct_gte"), (int, float)):
trigger["abs_change_pct_gte"] = _STOCK_DEFAULT_PCT
- elif proposal.signal_type in (SOURCE_KIND_RSS, SOURCE_KIND_PAGE_WATCH, SOURCE_KIND_QUERY):
- # Material-event words + priority terms only. The entity's own name
- # must NOT be a keyword: feed summaries are rendered as
- # "[<feed label>] <title>", so a keyword equal to the label would
- # match every entry and turn the trigger into a no-op.
+ elif proposal.signal_type in (SOURCE_KIND_RSS, SOURCE_KIND_QUERY):
+ # Material-event words + priority terms only, and only for sources
+ # with prose to match (feed titles, search snippets). A page_watch
+ # summary is "[label] page changed — <diff>" — a keyword filter
+ # there would mean the watch could never fire. The entity's own
+ # name must NOT be a keyword either: feed summaries carry the feed
+ # label, so it would match every entry.
existing_kw = trigger.get("keywords")
keywords: list[str] = [str(k) for k in existing_kw] if isinstance(existing_kw, list) else []
for kw in list(_EVENT_KEYWORDS) + priority_words:
@@ -590,7 +608,10 @@ def _safe_source_url(finding: ResearchFinding | None) -> str:
def _policy_stamp(decision: Decision, proposal: WatchProposal, finding: ResearchFinding | None) -> dict[str, Any]:
return {
- "entity": decision.entity,
+ # The matched company-data term, else the model's own entity string,
+ # so a not_relevant decline on an ungrounded suggestion still
+ # blacklists the entity the model named.
+ "entity": decision.entity or _norm(proposal.grounding_entity),
"grounding_kind": decision.grounding_kind,
"specialist": (finding.source_specialist if finding else ""),
"score": decision.score,
diff --git a/packages/core/openexecutive/workflows/executive_research.py b/packages/core/openexecutive/workflows/executive_research.py
index af5811f0..5a690575 100644
--- a/packages/core/openexecutive/workflows/executive_research.py
+++ b/packages/core/openexecutive/workflows/executive_research.py
@@ -252,7 +252,8 @@ def _build_watchlist_system(max_direct: int, max_suggest: int) -> str:
f"one. Policy adds at most {max_direct} on its own and files at most "
f"{max_suggest} suggestions per run — extra proposals are dropped.\n"
" - `grounding_entity` MUST name the competitor / vendor / ticker / "
- "initiative from the company context this source is about.\n"
+ "initiative from the company context this source is about. For a "
+ "stock / edgar watch the entity is the ticker itself (e.g. 'ACME').\n"
" - `target` MUST be concrete and real: a ticker symbol, or a URL "
"taken from a finding's `urls` list — do NOT invent feed URLs. If you "
"cannot give a real target, do not propose.\n"
diff --git a/packages/core/tests/unit/test_executive_research_watchlist.py b/packages/core/tests/unit/test_executive_research_watchlist.py
index 93adafd3..bd89a72e 100644
--- a/packages/core/tests/unit/test_executive_research_watchlist.py
+++ b/packages/core/tests/unit/test_executive_research_watchlist.py
@@ -49,7 +49,7 @@ def db(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Path:
return db_path
-def _finding(title: str = "Tesla cut prices", url: str = "https://example.com/feed.xml") -> ResearchFinding:
+def _finding(title: str = "TSLA: Tesla cut prices", url: str = "https://example.com/feed.xml") -> ResearchFinding:
return ResearchFinding(
title=title,
summary="Detail with a source.",
@@ -71,7 +71,7 @@ def _profile():
})
-def _propose(slug: str, signal_type: str, target: str, entity: str = "Tesla",
+def _propose(slug: str, signal_type: str, target: str, entity: str = "TSLA",
certainty: str = "confident", **extra: Any) -> tuple[str, dict[str, Any]]:
return ("propose_watch", {
"slug": slug, "signal_type": signal_type, "target": target,
diff --git a/packages/core/tests/unit/test_watch_policy.py b/packages/core/tests/unit/test_watch_policy.py
index cb5e7e14..bd76d365 100644
--- a/packages/core/tests/unit/test_watch_policy.py
+++ b/packages/core/tests/unit/test_watch_policy.py
@@ -163,10 +163,19 @@ def test_grounded_own_source_high_confidence_is_direct() -> None:
assert d.grounding_kind == wp.KIND_COMPETITOR
-def test_ticker_in_profile_is_own_source_for_stock() -> None:
- p = _proposal(slug="stock-acme", signal_type="stock", target="ACME", grounding_entity="Acme Corp")
- d = wp.classify(p, _finding(), _ctx())
- assert d.tier == wp.TIER_DIRECT
+def test_ticker_is_own_source_only_when_it_is_the_entity() -> None:
+ p = _proposal(slug="stock-acme", signal_type="stock", target="ACME", grounding_entity="ACME")
+ d = wp.classify(p, _finding(title="ACME slides", summary="ACME fell 8% on 2026-09-01."), _ctx())
+ assert d.tier == wp.TIER_DIRECT and d.grounding_kind == wp.KIND_TICKER
+ # A profile ticker that belongs to someone else lends nothing to "Acme Corp".
+ other = _proposal(slug="stock-msft", signal_type="stock", target="MSFT", grounding_entity="Acme Corp")
+ profile = CompanyProfile.model_validate({
+ "name": "Sente Labs", "competitive_landscape": {"primary_competitors": ["Acme Corp"]},
+ "tickers": ["MSFT"],
+ })
+ ctx = wp.PolicyContext(vocabulary=wp.grounding_vocabulary(profile, [], []), priority_terms=[], existing=[])
+ d2 = wp.classify(other, _finding(), ctx)
+ assert d2.tier == wp.TIER_SUGGEST and "own source" not in " ".join(d2.reasons)
def _stripe_finding(**kw: Any) -> ResearchFinding:
@@ -316,10 +325,10 @@ def test_apply_adds_direct_and_files_suggestion(db: Path) -> None:
def test_apply_honours_budgets_and_duplicate_targets(db: Path) -> None:
- findings = [_finding(), _stripe_finding(), _initech_finding(confidence="high")]
+ findings = [_finding(title="ACME cuts prices"), _stripe_finding(), _initech_finding(confidence="high")]
proposals = [
- _proposal(slug="stock-acme", signal_type="stock", target="ACME"),
- _proposal(slug="stock-acme-2", signal_type="stock", target="acme"), # same target
+ _proposal(slug="stock-acme", signal_type="stock", target="ACME", grounding_entity="ACME"),
+ _proposal(slug="stock-acme-2", signal_type="stock", target="acme", grounding_entity="ACME"), # same target
_proposal(slug="vendor-stripe", signal_type="vendor_status",
target="https://status.stripe.com/feed.atom", grounding_entity="Stripe", finding_index=1),
_proposal(slug="rss-acme-blog"), # third direct → budget → suggestion
@@ -528,9 +537,9 @@ def test_finding_points_need_a_finding_about_this_source() -> None:
d = wp.classify(p, _finding(verification="confirmed", source_specialist="cso,cfo"), _ctx())
assert d.score == 2 and d.tier == wp.TIER_SUGGEST
assert "does not mention this source" in " ".join(d.reasons)
- # A finding that names the entity does support a ticker watch on it.
- p2 = _proposal(slug="stock-acme", signal_type="stock", target="ACME", grounding_entity="Acme Corp")
- assert wp.classify(p2, _finding(), _ctx()).tier == wp.TIER_DIRECT
+ # A finding that names the ticker does support a ticker watch on it.
+ p2 = _proposal(slug="stock-acme", signal_type="stock", target="ACME", grounding_entity="ACME")
+ assert wp.classify(p2, _finding(title="ACME slides 8%"), _ctx()).tier == wp.TIER_DIRECT
def test_direct_add_requires_the_entitys_own_source() -> None:
@@ -557,6 +566,37 @@ def test_generic_tokens_do_not_ground() -> None:
# "enterprise" appears in a priority but is a stopword; "Corp" is too.
assert wp.match_entity("Enterprise Corp", _ctx().vocabulary) is None
assert wp.match_entity("Growth", {"drive growth in emea": wp.KIND_PRIORITY}) is None
+ # Short names that are whole vocabulary terms still match in longer forms.
+ assert wp.match_entity("IBM Corp", {"ibm": wp.KIND_COMPETITOR}) == ("ibm", wp.KIND_COMPETITOR)
+ assert wp.match_entity("AWS Lambda", {"aws": wp.KIND_VENDOR}) == ("aws", wp.KIND_VENDOR)
+
+
+def test_vocabulary_from_url_targets_uses_the_site_label(db: Path) -> None:
+ ms.insert_watchlist_item(slug="vendor-stripe", signal_type="vendor_status",
+ target="https://status.stripe.com/history.atom", db_path=db)
+ vocab = wp.grounding_vocabulary(CompanyProfile(name="X"), [], ms.list_watchlist(db_path=db))
+ assert vocab.get("stripe") == wp.KIND_WATCH
+ assert not any(t.startswith("https") for t in vocab)
+ assert wp.match_entity("Status Labs", vocab) is None
+
+
+def test_quiet_defaults_never_put_keywords_on_a_page_watch() -> None:
+ _, _, trigger = wp.quiet_defaults(
+ _proposal(signal_type="page_watch", target="https://acme.com/pricing"), ["accounts"],
+ )
+ assert "keywords" not in trigger
+
+
+def test_not_relevant_decline_remembers_the_models_entity_when_ungrounded(db: Path) -> None:
+ findings = [_initech_finding(confidence="high")]
+ out = wp.apply_proposals(
+ [_proposal(slug="rss-initech", target="https://initech.com/feed.xml",
+ grounding_entity="Initech Industries", certainty="unsure")],
+ findings, _ctx(), db_path=db,
+ )
+ assert out[0]["outcome"] == "suggested"
+ row = ms.get_watchlist_item_by_slug("rss-initech", db_path=db)
+ assert row is not None and row.config_json["_policy"]["entity"] == "initech industries"
def test_own_source_ignores_generic_host_tokens() -> None: