feat(search): P3.1 filters and multi-query merge

Native include/exclude domains, time_range, topic, exact_match, min_score,
and up to 4 queries fused with RRF. Honesty notes stay off the Warn/fail
path. Tavily keeps include_answer false and sets auto_parameters false.
Cache key is canonical JSON. CLI flags and skill recipe included.

skill/SKILL.md

@@ -21,7 +21,9 @@ markdown, JSON → JSON), optionally **digested** for your question by a local m
 **what the fleet already knows** attached from Honcho — so you read 1k tokens, not 20k.
 
 `sift search` is the first step for web search. Use `web_search` only if sift is
-unreachable. Then `sift fetch` the URLs you need. Restricted callers use the same path.
+unreachable. Hermes `web_search` hits `/v2/search` and does **not** get native
+filters. Then `sift fetch` / `sift batch` the URLs you need — do not fetch every
+hit. Restricted callers use the same path.
 
 ## Rule: sift is the explicit first step
 
@@ -38,8 +40,9 @@ Whenever you need the content of a URL:
 ## Commands
 
 ```bash
-# Web search (native). Then sift fetch the URLs you need.
-sift search "HBM wafer share 2026" --k 8
+# Web search (native). Then score/filter, then batch-fetch — not every hit.
+sift search "HBM wafer share 2026" --k 8 --json
+sift search "OpenAI" --include-domain openai.com --topic news --time-range month --json
 
 # Page or document → cleaned content. Add --question to get a focused digest.
 sift fetch "https://example.com/article" --question "what does it say about HBM wafer share?"
@@ -55,6 +58,31 @@ Useful flags: `--mode digest|clean|raw` (default `digest` when `--question` is g
 else `clean`), `--no-context` (skip Honcho lookup), `--recover` (server-side archive ladder
 for blocked pages), `--json` (full envelope: content, source, context, sizes, warnings).
 
+## Search
+
+```bash
+sift search "<query>" [--k n] [--json]
+            [--include-domain host]... [--exclude-domain host]...
+            [--domains-mode restrict|prefer]
+            [--time-range day|week|month|year]
+            [--start-date YYYY-MM-DD] [--end-date YYYY-MM-DD]
+            [--topic general|news|finance]
+            [--exact-match]
+            [--min-score 0.5]
+            [--queries-file path]
+```
+
+Product News Tracker shape (official domain + news + last month):
+
+```bash
+sift search "product launch" --include-domain openai.com --topic news --time-range month --json
+```
+
+**Recipe:** after `sift search --json`, do not `sift fetch` every URL. Drop hits below a
+Tavily score you care about (`--min-score`, Tavily's 0–1 scale) or take top N, then
+`sift batch submit`. `web_search` is only the fallback when sift is unreachable, and it
+still hits `/v2/search` with no filters.
+
 ## Batch
 
 When you will read the content of several URLs later (a shortlist to compare), submit them once