mirror of
https://github.com/koala73/worldmonitor.git
synced 2026-04-25 17:14:57 +02:00
* fix(intelligence): include framework/systemAppend hash in cache keys (todos 041, 045, 051) * fix(intelligence): gate framework/systemAppend on server-side PRO check (todo 042) * fix(skills): exact hostname allowlist + redirect:manual to prevent SSRF (todos 043, 054) * fix(intelligence): sanitize systemAppend against prompt injection before LLM (todo 044) * fix(intelligence): use framework field in DeductionPanel, fix InsightsPanel double increment (todos 046, 047) * fix(intelligence): settings export, hot-path cache, country-brief debounce (todos 048, 049, 050) * fix(intelligence): i18n, FrameworkSelector note, stripThinkingTags dedup, UUID IDs (todos 052, 055, 056, 057) - i18n Analysis Frameworks settings section (en + fr locales, replace all hardcoded English strings with t() calls) - FrameworkSelector: replace panelId==='insights' hardcode with note? option; both InsightsPanel and DailyMarketBriefPanel pass note - stripThinkingTags: remove inline duplicate in summarize-article.ts, import from _shared/llm; add Strip unterminated comment so tests can locate the section - Replace Date.now() IDs for imported frameworks with crypto.randomUUID() - Drop 'not supported in phase 1' phrasing to 'not supported' - test: fix summarize-reasoning Fix 2 suite to read from llm.ts - test: add premium-check-stub and wire into redis-caching country intel brief importPatchedTsModule so test can resolve the new import * fix(security): address P1 review findings from PR #2386 - premium-check: require `required: true` from validateApiKey so trusted browser origins (worldmonitor.app, Vercel previews, localhost) are not treated as PRO callers; fixes free-user bypass of framework/systemAppend gate - llm: replace weak sanitizeSystemAppend with sanitizeForPrompt from llm-sanitize.js; all callLlm callers now get model-delimiter and control-char stripping, not just phrase blocklist - get-country-intel-brief: apply sanitizeForPrompt to contextSnapshot before injecting into user prompt; fixes unsanitized query-param injection Closes todos 060, 061, 062 (P1 — blocked merge of #2386). * chore(todos): mark P1 todos 060-062 complete * fix(agentskills): address Greptile P2 review comments - hoist ALLOWED_AGENTSKILLS_HOSTS Set to module scope (was reallocated per-request) - add res.type === 'opaqueredirect' check alongside the 3xx guard; Edge Runtime returns status=0 for opaque redirects so the status range check alone is dead code
1.5 KiB
1.5 KiB
status, priority, issue_id, tags, dependencies
| status | priority | issue_id | tags | dependencies | |||
|---|---|---|---|---|---|---|---|
| pending | p2 | 066 |
|
framework param missing from widget-agent PRO system prompt for get-country-intel-brief
Problem Statement
The PRO widget-agent system prompt documents get-country-intel-brief with only params: country_code. The new framework field (added in PR #2380, gated server-side in PR #2386) is not listed. PRO users asking the widget-agent to apply an analytical framework to a country brief silently receive a frameworkless response — the agent has no way to know the field exists.
Since the relay passes query params through as-is, the fix is purely a system prompt documentation update — no backend changes required.
Proposed Solution
Add framework to the param documentation for get-country-intel-brief in WIDGET_PRO_SYSTEM_PROMPT in scripts/ais-relay.cjs. The basic WIDGET_SYSTEM_PROMPT should omit it (server gate rejects non-PRO framework values anyway).
Technical Details
- File:
scripts/ais-relay.cjs(search forWIDGET_PRO_SYSTEM_PROMPTandget-country-intel-brief) - Effort: Small | Risk: Low
Acceptance Criteria
- PRO widget-agent system prompt includes
frameworkparam forget-country-intel-brief - PRO agent can send
?framework=<text>and receive framework-influenced response - Basic agent does not receive the
frameworkdoc entry
Work Log
- 2026-03-28: Identified by agent-native-reviewer during PR #2386 review