Gate paywalled searches on VPN confirmation before booting Chrome

The LLM-as-agent path was running searches that involved IEEE / Scholar /
paywalled publishers without first checking whether the user had VPN
or institutional access. Without VPN: Scholar captchas within a few
requests, IEEE serves abstract-only / 403 for the PDF stage, and the
user spends minutes watching a useless Chrome window.

CLAUDE.md HARD RULE now requires the agent to confirm VPN status
(recall from conversation, or AskUserQuestion) BEFORE running
'python -m autopapertoppt -q ...' or any scripts/llm_*.py invocation.
When the user says no VPN, the source mix is restricted to open
sources (arxiv,openalex,pubmed,crossref,dblp,openaire).

compliance-auditor: the in-practice list now leads with the VPN
confirmation step before the WebRunner-vs-httpx rules.

paper-summary-author: source-level browser-automation rule prefaced
with a VPN gate paragraph naming AskUserQuestion as the canonical
asking mechanism.

Author: JE-Chen

.claude/agents/compliance-auditor.md

@@ -75,11 +75,12 @@ A subset of upstreams reject anonymous `httpx` outright (TLS / JS fingerprint, A
 
 **In practice:**
 
-1. `sources/ieee/fetcher.py:_scrape_search` tries WebRunner first. The httpx `POST /rest/search` branch is a CI / no-Chrome safety net, **not** the production path. On a user machine with VPN, silent fall-through to httpx is a bug — surface it instead of trusting the results.
-2. Never propose `--source` lists that exclude `ieee` "to avoid the slow browser boot." VPN access is precisely why the user wants the browser path.
-3. LLM-as-agent paywalled PDF fetch: drive a one-off Bash + Selenium script in the shape of `scripts/llm_driven_search.py` — `webrunner_browser.make_driver()` for visible Chrome, `driver.get(...)`, `wait_for_captcha_solved(...)`, capture `driver.page_source` or trigger a real download. Never paste a publisher URL into `httpx` / `urllib` / `subprocess curl` and call it equivalent. Never call `mcp__webrunner__webrunner_run_actions` — that tool is not exposed by the MCP server registered here.
-4. The visible Chrome window is a feature (CAPTCHA + SSO). Don't suppress it — no `--headless`, no `options.add_argument("--headless")`.
-5. Debugging: look for the `IEEE (scrape) returned N papers …` INFO log emitted by `sources/ieee/fetcher.py`. If results came back in under ~5 seconds without that log line AND without a Chrome window appearing, WebRunner threw and httpx silently fired — flag it.
+1. **Confirm VPN access BEFORE running any search that involves IEEE / Scholar / paywalled-PDF flows.** When the user requests a paper search ("搜尋 X" / "search X" / "find papers on X"), the LLM's first action is NOT to invoke the search — it is to check VPN status. Either recall from the conversation, or ask via `AskUserQuestion` ("Do you have VPN / institutional access for IEEE / ACM / Springer for this topic? Affects whether I include them as sources."). Without VPN: Scholar gets captcha'd within a few requests, IEEE returns abstract-only / 403 for the PDF stage, and the user wastes minutes staring at a useless Chrome window. Same gate applies before invoking `scripts/llm_driven_search.py` or `scripts/llm_download_pdfs.py`. When the user confirms NO VPN, restrict the source mix to open sources (`arxiv,openalex,pubmed,crossref,dblp,openaire`) and skip `ieee,scholar`.
+2. `sources/ieee/fetcher.py:_scrape_search` tries WebRunner first. The httpx `POST /rest/search` branch is a CI / no-Chrome safety net, **not** the production path. On a user machine with VPN, silent fall-through to httpx is a bug — surface it instead of trusting the results.
+3. Never propose `--source` lists that exclude `ieee` "to avoid the slow browser boot." VPN access is precisely why the user wants the browser path — but only after step 1 confirmed they have it.
+4. LLM-as-agent paywalled PDF fetch: drive a one-off Bash + Selenium script in the shape of `scripts/llm_driven_search.py` — `webrunner_browser.make_driver()` for visible Chrome, `driver.get(...)`, `wait_for_captcha_solved(...)`, capture `driver.page_source` or trigger a real download. Never paste a publisher URL into `httpx` / `urllib` / `subprocess curl` and call it equivalent. Never call `mcp__webrunner__webrunner_run_actions` — that tool is not exposed by the MCP server registered here.
+5. The visible Chrome window is a feature (CAPTCHA + SSO). Don't suppress it — no `--headless`, no `options.add_argument("--headless")`.
+6. Debugging: look for the `IEEE (scrape) returned N papers …` INFO log emitted by `sources/ieee/fetcher.py`. If results came back in under ~5 seconds without that log line AND without a Chrome window appearing, WebRunner threw and httpx silently fired — flag it.
 
 **Audit checks for this category:**
 - Grep changed files for `headless`, `--headless`, `add_argument("--headless")`.

.claude/agents/paper-summary-author.md

@@ -23,6 +23,18 @@ The xlsx has columns `# | Title | Authors | Year | Source | Indexed via | DOI |
 
 ## Source-level browser-automation rule (read before anything else)
 
+**VPN gate (applies to SEARCH, not just PDF download).** Before invoking
+any search that includes IEEE / Scholar / paywalled-publisher domains
+— including the parent agent's `python -m autopapertoppt -q ...` or
+`scripts/llm_driven_search.py` — confirm the user's VPN / institutional
+access status. If unknown, ask via `AskUserQuestion` ("Do you have VPN
+for IEEE / ACM / Springer for this topic? Affects whether I include
+them."). Without VPN: Scholar gets captcha'd quickly and IEEE returns
+abstract-only / 403 PDFs, making the run a waste of the user's time
+watching Chrome boot. When the user confirms NO VPN, restrict the
+search to open sources (`arxiv,openalex,pubmed,crossref,dblp,openaire`)
+and skip `ieee,scholar`.
+
 Even before you touch a PDF: if the user's run included IEEE (default on),
 Scholar (opt-in), or any paywalled publisher CDN, the canonical path is
 **visible Chrome via WebRunner**, never direct httpx. The IEEE plugin's
@@ -31,8 +43,8 @@ branch is only a safety net for machines without Chrome. If you reviewed
 a previous run and IEEE returned a result set in under ~5 seconds without
 a Chrome window appearing, WebRunner silently fell through to httpx —
 flag this to the user, do not treat those results as authoritative for
-summary authoring. (Full rule in `CLAUDE.md` "Browser Automation Is
-Mandatory for Publisher Domains".)
+summary authoring. (Full rule in `CLAUDE.md` "IEEE / Publisher CDN:
+Browser Automation Is Mandatory".)
 
 ## When the CLI couldn't download a paywalled PDF (LLM-driven Bash + Selenium)
 

CLAUDE.md

@@ -69,6 +69,19 @@ later" is not allowed.
 
 ## IEEE / Publisher CDN: Browser Automation Is Mandatory (HARD RULE)
 
+**Before triggering ANY search that involves IEEE / Scholar / paywalled
+publishers, the LLM in this session MUST confirm the user's VPN /
+institutional access status first** — either by recalling a recent
+statement, or by asking via `AskUserQuestion` ("Do you have VPN for
+IEEE / ACM / Springer for this topic?"). Without VPN, Scholar gets
+captcha'd quickly and IEEE returns abstract-only / 403 PDFs, so the
+run wastes the user's time watching a useless Chrome window. When the
+user says no VPN, restrict the search to open sources
+(`arxiv,openalex,pubmed,crossref,dblp,openaire`) and skip
+`ieee,scholar`. This gate applies BEFORE running `python -m
+autopapertoppt -q …`, before `scripts/llm_driven_search.py`, and
+before any `scripts/llm_download_*pdf*.py` invocation.
+
 IEEE search, IEEE document fetch, Google Scholar search, and any paywalled-PDF
 download from publisher CDNs (ieeexplore.ieee.org, dl.acm.org, link.springer.com,
 sciencedirect.com, wiley/oup/nature/science/…) MUST go through **visible Chrome**.