idle-draft: per-work-type allowed_tools; research must web-search for stories

Research and topic_ideas runs get --allowedTools WebSearch,WebFetch;
research template mandates >=1 web search for related stories with
full-URL + access-date citations under the dossier's status labels.

Claude-Session: https://claude.ai/code/session_01YQDoWNM7XPPii28khFWoMc

data/idle-draft/prompts/research.md

@@ -30,6 +30,33 @@ anything new and relevant you find under the evidence directories above:
    for a reader (a scene, a named organisation's experience, a practitioner's account)
    — still sourced, but framed as narrative rather than a bare statistic.
 
+## Required: web search for current stories (before writing Subjective stories)
+
+You have `WebSearch` and `WebFetch` available. Before writing the **Subjective
+stories** section, run **at least one `WebSearch`** for recent stories, case
+studies, or practitioner accounts directly related to this topic — derive your
+query terms from the topic brief (`$overview_path`) and commissioning brief
+(`$agent_path`), not from the dossier title alone. This is not optional and not
+decorative: a research file with zero web search calls and zero web-sourced
+entries is incomplete.
+
+- Web-sourced entries go in Subjective stories (or Objective evidence, if the
+  find is a concrete measurable rather than a narrative) alongside the local
+  evidence-dir findings — web search **complements** the local evidence dirs,
+  it never replaces them. Local evidence-dir citation rules above are
+  unchanged.
+- Cite the **full URL** and the **access date** (today's date) for every
+  web-sourced entry, e.g. `https://example.com/post (accessed 2026-08-02)`.
+- Apply the dossier's status-label family correctly to web sources: a company
+  engineering-blog post is "Named organisation, self-reported"; vendor
+  marketing or a vendor's own benchmark is "Vendor data, treat with caution";
+  an industry survey is "Research-survey finding"; use "GOES synthesis / bet"
+  only for your own synthesis, never for a source you found.
+- **Only cite a URL actually returned by `WebSearch` or fetched via
+  `WebFetch`.** Never construct, guess, or paraphrase a plausible-looking URL.
+  A fabricated URL is grounds for outright rejection at human sampling —
+  treat it as equivalent to citing a dead file path.
+
 ## Citation rules (non-negotiable — read `$agents_root_path` for the full statement)
 
 - **Cite the file, not the concept.** Any code or spec reference must name the file

data/idle-draft/prompts/topic-ideas.md

@@ -22,6 +22,17 @@ Do **not** propose anything that duplicates or trivially rephrases one of these:
 
 $existing_titles
 
+## Check current discussion first
+
+You have `WebSearch` available. Before proposing, run at least one `WebSearch`
+to check what is currently being discussed in this dossier's topic area — this
+keeps proposals grounded in what practitioners are actually talking about
+right now, not just what the local evidence dirs already contain. This is a
+lighter-touch check than the research work type's requirement: you do not need
+to cite web sources in the proposal itself (evidence pointers below still come
+from the evidence directories), just use the search to sanity-check relevance
+and avoid pitching something already stale or already covered elsewhere.
+
 ## What to produce
 
 Propose **up to $max_new** new candidate topics for this dossier, each grounded in