Extract is bounded to the ranking: pull → embed → score → extract → score → summarise
The free stages run first and their score bounds the two model stages. Extract reads only the best extract.per_agent roles of each agent at extract.min_score or more, then score runs again so the gates read what it filled; summarise gets a min_score of its own. The cascade steps by position, since score is in it twice. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
c4f2bcc0c9
commit
7db77e83a3
15 files changed
+215
-89
No files matched your search
+4
-2
@@ -84,7 +84,9 @@ What was decided for roledesk and the one reason for each. The longer reasoning
|
||||
|
||||
**`embed` and `score` run in the server process.** newsdesk isolates `embed` in a child process with a timeout. roledesk's run is one bounded pass over open roles, and in-process keeps the embedder replaceable in tests. The cost is torch's memory staying in the server after the first run; isolate it if that becomes the problem.
|
||||
|
||||
**The pull cascade is `pull → extract → embed → score`.** Every stage is always in the chain and a stage that is off finds nothing, as in newsdesk. Extract precedes score so the gates read what it filled, and reads `on_ingest` only as a stage of a pull, so with `auto` and no model reachable a pull passes it quietly.
|
||||
**The pull cascade is `pull → embed → score → extract → score → summarise`.** Every stage is always in the chain and a stage that is off finds nothing, as in newsdesk. The free stages run first: embed and score cost no tokens, and their score is what bounds the two model stages. Extract reads only what ranks, then score runs again so the gates read what it filled. A stage is addressed by its position in the tuple, since `score` is in it twice. Extract reads `on_ingest` only as a stage of a pull, so with `auto` and no model reachable a pull passes it quietly.
|
||||
|
||||
**Extract is bounded like summarise: the top `per_agent` roles of each agent at `min_score` or more.** Extract has short answers but would otherwise touch every open role, and the seed boards alone produced 29,000; at Haiku's rates that is tens of dollars for a first pass over roles nobody will look at. Bounded to the ranking, a pull reads a few hundred. `per_agent` is the backstop (default 500) and `min_score` the real stop (default 0.3, loose): a fixed count stays flat whatever the boards produce, where a percentage would not. A batch dealt named uids finishes them whatever their rank, so a running batch is not cut short by a rescore.
|
||||
|
||||
## The pages
|
||||
|
||||
@@ -128,7 +130,7 @@ What was decided for roledesk and the one reason for each. The longer reasoning
|
||||
|
||||
**A search role's posting text is fetched on demand, not in the pull.** `POST /api/roles/{uid}/text` scrapes `original_url` only when the read page asks for it, because following Jobindex's redirect for every role during a pull would count as a click in Jobindex's own statistics; one click for a posting somebody actually opened is fair.
|
||||
|
||||
**Summarising is bounded to the top `per_agent` roles of each agent, and off by default.** The pull's `summarise` stage only considers roles with no summary yet that are in the top `summarise.per_agent` (default 30) of an enabled agent's scores, so the cost stays flat whatever the backlog of open roles is. `summarise.enabled: false` matches `extract`'s own default; the read page's Summarise button asks for one role's summary either way.
|
||||
**Summarising is bounded to the top `per_agent` roles of each agent at `min_score` or more, and off by default.** The pull's `summarise` stage only considers roles with no summary yet that are in the top `summarise.per_agent` (default 30) of an enabled agent's scores and at `summarise.min_score` (default 0.5, stricter than extract's since a summary is the long answer), so the cost stays flat whatever the backlog of open roles is. `summarise.enabled: false` matches `extract`'s own default; the read page's Summarise button asks for one role's summary either way.
|
||||
|
||||
**The schedules element's narrow layout is fixed upstream, in `../boilerplate`.** `<desk-schedules>` is a shadow root the app cannot lay out from outside, and `pipeline/` is a downstream copy refreshed with `git archive`, so a fix landing only in roledesk would be reverted by the next refresh.
|
||||
|
||||
|
||||
Reference in new issue
Block a user