Record the judge scale, summarise on both orders and hidden companies in decisions.md
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
d80f26a930
commit
1127d06f03
1 file changed
+2
@@ -178,6 +178,8 @@ What was decided for roledesk and the one reason for each. The longer reasoning
|
||||
|
||||
**Saved filters are per agent, stored on the server (`saved_filters`, migration 32).** A saved filter is the feed's query string under a name: applied with one click, deleted, never edited, since a change is a new one. They are per agent because an agent's filters change with what it hunts, and on the server so they follow the owner across devices.
|
||||
|
||||
**Judge scores 0 to 10, summarise reads the top of both orders, a hidden company is never shown (2026-10-04).** A model's 0 to 100 is an estimate with false precision, so skills, experience and career are 0 to 10 and a broken must-have caps career at 4; the CV match stays 0 to 100 (the weighted mean times 10). Migration 33 cleared every judgement so no old number shows on the new scale, and the first judge run reads the whole cut again. Summarise reads the top `summarise_top` (30) of the want order and of the match order, at most 60 per agent, plus liked and saved roles, since both orders are what the owner reads. The feed's Show hidden companies filter is gone: hidden means hidden.
|
||||
|
||||
**An agent is the group: it holds several prompts, and `fit` is the best prompt's.** A hunt spans several kinds of role (AI and data leadership, customer-facing technical leadership, AI research), and one blended paragraph ranks a role by its distance to the blend. Each prompt is a named text in `agent_prompts` (migration 14, which moved every non-empty `agents.intent` into a prompt named after the agent and dropped the intent columns), embedded on its own and cached under sha1 of model and text, so an edit re-embeds one prompt. A role's fit is the maximum over the prompts of the calibrated cosine, the first prompt winning a tie, and `scores.prompt` names the winner. Votes, liked companies, gates, weights, limits and `taste` stay per agent, so a vote counts for every prompt; a market watch is a second agent with its own. No third level above the agent was added. `POST /api/agents` still takes `intent` when `prompts` is absent. On the live data of 2026-09-29 the embedder separates the three kinds of role but not seniority: an individual contributor's posting on the same subject ranks beside a head's, so seniority has to come from `extract` and a prefer gate, or from votes.
|
||||
|
||||
**`fit` is the cosine between a role and a prompt of the agent, mapped to a level by constants calibrated per embedding model: `clip((cos - lo) / (hi - lo), 0, 1)`.** `(cos + 1) / 2` spanned only about 0.87 to 0.95 on multilingual-e5-small, so a prefer gate at 0.2 outweighed all of fit. Min-max across the roles an agent scored in the run fixed the spread but made fit a rank: the best role of a poor set got 1, a role's fit and the 0.9 favourite floor's meaning drifted from run to run, and the `limits` bars that bound the paid stages compared an absolute number with a relative one. The constants are `CALIBRATION` in `app/config.py`, keyed by model name, and an entry under `embed.calibration` replaces a model's built-in one; keyed by model, a change of `embed.model` cannot carry another geometry's constants along. A model with none falls back to min-max per run, with gated roles left out of the range, and the log warns once per run. `taste` is mapped the same way with its own pair. The starter agents' prefer weights are 0.05.
|
||||
|
||||
Reference in new issue
Block a user