diff --git a/.context/PR-TODOLIST.md b/.context/PR-TODOLIST.md
index a3e52476..ec76faf1 100644
--- a/.context/PR-TODOLIST.md
+++ b/.context/PR-TODOLIST.md
@@ -1,6 +1,6 @@
 # PR Review Todolist
 
-> Last updated: 2026-02-01 | Total open PRs: 79
+> Last updated: 2026-02-02 | Total open PRs: 95
 
 ---
 
@@ -15,29 +15,33 @@
 | ~~#1717~~ | ~~YuriNachos~~ | ~~Fix local sentence-transformers embeddings blocked by OpenAI fallback. (#1658)~~ | **merged** |
 | ~~#1714~~ | ~~YuriNachos~~ | ~~Fix: Replace `tf-playwright-stealth` with `playwright-stealth` dependency. (#1553)~~ | **merged** |
 | ~~#1667~~ | ~~christian-oudard~~ | ~~Fix `crwl --deep-crawl` only outputting first page. Real CLI bug with tests.~~ | **merged** |
-| #1640 | Martichou | Fix memory leak — unused browser contexts never cleaned up under continuous load. (#943) | pending |
-| #1622 | zhaoyun006 | Fix redirect target verification in AsyncUrlSeeder and enhance tests. | pending |
-| #1592 | jzmiller1 | Fix CDP page leaks and race conditions in concurrent crawling. (#1563) | pending |
+| ~~#1640~~ | ~~Martichou~~ | ~~Fix memory leak — unused browser contexts never cleaned up under continuous load. (#943)~~ | **closed** |
+| #1622 | Ahmed-Tawfik94 | Fix redirect target verification in AsyncUrlSeeder and enhance tests. | pending |
+| #1592 | Ahmed-Tawfik94 | Fix CDP page leaks and race conditions in concurrent crawling. (#1563) | pending |
 | #1572 | yuexuan-chen | Fix CDP setting with managed browser. | pending |
 | #1450 | prlz77 | Fix LLM extraction fails when content is in alternative response fields. | pending |
 | ~~#1364~~ | ~~nnxiong~~ | ~~Fix `<script>` tag removal losing adjacent text in `cleaned_html`.~~ | **merged** |
-| #1308 | cjh-GITHUB | Fix css_selector variable type error (assigned to list). | pending |
+| #1308 | dominicx | Fix css_selector variable type error (assigned to list). | pending |
 | ~~#1296~~ | ~~vladmandic~~ | ~~Fix `VersionManager` ignoring `CRAWL4_AI_BASE_DIRECTORY` env var. 1-line fix.~~ | **merged** |
 | ~~#1281~~ | ~~garyluky~~ | ~~Fix proxy auth `ERR_INVALID_AUTH_CREDENTIALS`. Fixes #993, #974, #1109.~~ | **merged** |
-| #1234 | hellokayas | Fix TypeError when `keep_data_attributes=False` by ensuring list concat. | pending |
-| #1211 | zhangbo-tj | Fix: safely create new page if no page exists in persistent context. | pending |
-| #1207 | ninjapanzer | Fix streaming error handling. | pending |
-| #1200 | Gyscos | Bugfix browser manager session handling. | pending |
-| #1179 | Nuo-55 | Fix leak token when input url as raw html. | pending |
+| #1234 | AdarsHH30 | Fix TypeError when `keep_data_attributes=False` by ensuring list concat. | pending |
+| #1211 | Praneeth1-O-1 | Fix: safely create new page if no page exists in persistent context. | pending |
+| #1207 | moncapitaine | Fix streaming error handling. | pending |
+| #1200 | fischerdr | Bugfix browser manager session handling. | pending |
+| #1179 | phamngocquy | Fix leak token when input url as raw html. | pending |
 | ~~#1150~~ | ~~scris~~ | ~~Fix LLM extraction `response` variable not overridden causing `'str' has no attribute 'choices'`.~~ | **closed (already fixed)** |
-| #1133 | Daniel21b | Enforce auth when JWT is enabled. 1-line fix. | pending |
-| #1106 | ruoyuGao | Fix: Adapt to CrawlerMonitor constructor change. | pending |
+| #1133 | chrizzly2309 | Enforce auth when JWT is enabled. 1-line fix. | pending |
+| #1106 | devxpain | Fix: Adapt to CrawlerMonitor constructor change. | pending |
 | #1081 | Joorrit | Fix deep crawl scorer logic was inverted — high-distance paths scored higher. | **needs work (commented)** |
 | ~~#1077~~ | ~~RoyLeviLangware~~ | ~~Fix bs4 deprecation warning (`text` -> `string`). 1 line.~~ | **merged** |
 | #1073 | saipavanmeruga7797 | Fix local HTML file crawling broken when `capture_console_messages=False`. | pending |
-| #1065 | dzhao-gearset | Fix: Update deprecated Groq models to recommended replacements. | pending |
-| #1059 | wangs1024 | Fix wrong proxy config type in proxy demo example. | pending |
+| #1065 | mccullya | Fix: Update deprecated Groq models to recommended replacements. | pending |
+| #1059 | Aaron2516 | Fix wrong proxy config type in proxy demo example. | pending |
 | #1058 | Aaron2516 | Fix dict-type `proxy_config` not handled properly. (#1057) | pending |
+| #983 | umerkhan95 | Fix memory leak and empty responses in streaming mode. (#980) | pending |
+| #973 | danyQe | Fix typo of `temperature` in async_configs.py. 1 line. | pending |
+| #948 | GeorgeVince | Fix `summarize_page.py` example. | pending |
+| #729 | complete-dope | Fix: Logging for Error. 1-line fix. | pending |
 
 ## Good Features
 
@@ -48,44 +52,55 @@
 | #1707 | dillonledoux | Add `Crawl-delay` directive support from robots.txt. Good compliance feature. | pending |
 | #1706 | vikas-gits-good | Fix `arun_many` not working with `DeepCrawlStrategy`. (#1277) | pending |
 | #1702 | YxmMyth | Add CSS background image extraction. (#1691) | pending |
-| #1689 | dillonledoux | Docker: optimize concurrency performance and memory management. | pending |
-| #1683 | unknown | Implement double config for AdaptiveCrawler. | pending |
+| #1689 | mzyfree | Docker: optimize concurrency performance and memory management. | pending |
+| #1683 | Vaccarini-Lorenzo | Implement double config for AdaptiveCrawler. | pending |
 | #1674 | blentz | Add output pagination/control for MCP endpoints. Useful for LLM context windows. | pending |
 | #1668 | microHoffman | Add `--json-ensure-ascii` CLI flag for Unicode handling. Clean, small. | pending |
-| #1650 | sathyanarays | Add support for Vertex AI in LLM Extraction Strategy. | pending |
-| #1580 | GrumpyLion | Add Azure OpenAI configuration support to crwl config. | pending |
+| #1650 | KennyStryker | Add support for Vertex AI in LLM Extraction Strategy. | pending |
+| #1580 | arpagon | Add Azure OpenAI configuration support to crwl config. | pending |
 | #1463 | TristanDonze | Add configurable `device_scale_factor` for screenshot quality. 3 files, clean. | pending |
-| #1450 | prlz77 | Fix LLM extraction fails with alternative response fields. | pending |
 | #1435 | charlaie | Add `redirected_status_code` to CrawlResult. 3 files, clean. | pending |
-| #1425 | Nisarg38 | Add OpenRouter API support. | pending |
+| #1425 | denrusio | Add OpenRouter API support. | pending |
 | #1417 | NickMandylas | Add CDP headers support for remote browser auth (AWS Bedrock etc). | pending |
 | #1290 | 130347665 | Support type-list pipeline in JsonElementExtraction (multi-step extract). | pending |
 | #1255 | itsskofficial | Fix JsonCssSelector to handle adjacent sibling CSS selectors (`+ tr`). | pending |
-| #1238 | IgorLeno | Fix ManagedBrowser constructor and Windows encoding issues. | pending |
-| #1220 | chineidu | Allow `OPENAI_BASE_URL` to be used to control the base_url for the LLM. | pending |
-| #1180 | aravindkarnam | Add CallbackURLFilter for custom URL filtering in deep crawling. | pending |
-| #999 | Morriz | Add filters that filter based on regular expressions in deep crawling. | pending |
+| #1245 | mukul-atomicwork | Feature: GitHub releases integration. | pending |
+| #1238 | yerik515 | Fix ManagedBrowser constructor and Windows encoding issues. | pending |
+| #1220 | dcieslak19973 | Allow `OPENAI_BASE_URL` to be used to control the base_url for the LLM. | pending |
+| #1180 | kunalmanelkar | Add CallbackURLFilter for custom URL filtering in deep crawling. | pending |
+| #999 | loliw | Add filters that filter based on regular expressions in deep crawling. | pending |
+| #901 | gbe3hunna | CrawlResult model: add pydantic fields and descriptions. | pending |
+| #800 | atomlong | `ensure_ascii=False` for json.dumps to support non-ASCII characters. | pending |
+| #799 | atomlong | Allow setting `base_url` for LLM extraction strategy in CLI. | pending |
+| #741 | atomlong | Add config option to control Content-Security-Policy header. | pending |
+| #723 | alexandreolives | Optional close page after screenshot. | pending |
+| #681 | ksallee | JS execution should happen after waiting (reorder in strategy). | pending |
 
 ## Quick Doc/Maintenance Merges
 
 | PR | Author | Description | Status |
 |----|--------|-------------|--------|
 | #1734 | pgoslatara | Update outdated GitHub Actions versions (v4->v6). 2 files. | pending |
+| #1722 | YuriNachos | Add missing docstring to MCP `md` endpoint. | pending |
 | #1716 | YuriNachos | Fix wrong return types in arun/arun_many docs. | pending |
 | #1715 | YuriNachos | Add missing `CacheMode` import in quickstart docs. | pending |
-| #1722 | YuriNachos | Add missing docstring to MCP `md` endpoint. | pending |
-| #1655 | unknown | Replace Chinese comment with English in nullcontext method. 1 line. | pending |
+| #1655 | daviddl9 | Replace Chinese comment with English in nullcontext method. 1 line. | pending |
 | #1494 | AkosLukacs | Fix wrong param name in `arun()` docstring. | pending |
 | #1488 | AkosLukacs | Fix syntax error in README JSON example. | pending |
-| #1483 | unknown | Update README.md with latest docker image. | pending |
-| #1416 | unknown | Fix missing bracket in README code block. | pending |
-| #1272 | unknown | Fix get title bug in amazon example. | pending |
-| #1263 | unknown | Fix: consistent with sdk behavior. | pending |
-| #1225 | unknown | Fix docker deployment guide URL. | pending |
-| #1223 | unknown | Docs: add links to other language versions of README. | pending |
+| #1483 | NiclasLindqvist | Update README.md with latest docker image. | pending |
+| #1416 | adityaagre | Fix missing bracket in README code block. | pending |
+| #1272 | zhenjunMa | Fix get title bug in amazon example. | pending |
+| #1263 | vvanglro | Fix: consistent with sdk behavior. | pending |
+| #1225 | albertkim | Fix docker deployment guide URL. | pending |
+| #1223 | dowithless | Docs: add links to other language versions of README. | pending |
 | #1159 | lbeziaud | Fix cleanup warning when no process on debug port. 1 line. | pending |
-| #1098 | unknown | Docs: fix outdated links to Docker guide and release notes. | pending |
-| #1093 | unknown | Docs: Fixed incorrect elapsed calculation and output format. | pending |
+| #1098 | B-X-Y | Docs: fix outdated links to Docker guide and release notes. | pending |
+| #1093 | Aaron2516 | Docs: Fixed incorrect elapsed calculation and output format. | pending |
+| #948 | GeorgeVince | Fix `summarize_page.py` example. | pending |
+| #931 | stevenaldinger | Remove duplicate variable definition dead code in prompts.py. | pending |
+| #967 | prajjwalnag | Update README.md. | pending |
+| #671 | SteveAlphaVantage | Update README.md. | pending |
+| #605 | mochamadsatria | Fix typo in docker-deployment.md filename. | pending |
 
 ## Duplicates (Close These)
 
@@ -98,6 +113,7 @@
 | ~~#1710~~ | ~~#1719~~ | ~~Same script.js packaging fix~~ **closed** |
 | #1478 | #1715 | Same quickstart CacheMode fix |
 | #1465 | #1715 | Same quickstart example fix |
+| #800 | #1668 | Overlaps with `--json-ensure-ascii` feature |
 
 ## Skip / Close
 
@@ -115,20 +131,22 @@
 | #1547 | mziv | lxml update — touches 100 files (lockfile). Needs careful review. |
 | #1395 | granolacowboy | "Feature/interactive wizard" — no description. |
 | #1408 | PATAKAMURIVENKATAGANESH | "Basic Health Check Endpoint" — no description filled. |
-| #1533 | unknown | Add Claude Code GitHub Workflow — CI workflow, not core. |
-| #1274 | unknown | Devcontainer support — 913 additions, dev tooling. |
-| #1420 | unknown | Opt-in telemetry system — 3,208 additions. Too large/sensitive. |
-| #1497 | unknown | Firecrawl backend support — 191 additions, niche integration. |
-| #1496 | unknown | normalize_url refactor — 869 additions, too large for URL normalization. |
-| #1518 | unknown | Docker PDF strategy — 324 additions, Docker-specific. |
-| #1413 | unknown | Full scan update — 290 additions, unclear scope. |
-| #1373 | unknown | MCP server endpoint fixes — 753 additions, large. |
-| #1212 | unknown | Stateless streamable_http transport for MCP — 154 additions. |
-| #1157 | unknown | Content change detection — 229 additions, feature scope unclear. |
-| #1140 | unknown | Prompt-driven recursive crawler script — 268 additions, not core. |
-| #1124 | unknown | VNC streaming support — 98 additions, niche. |
-| #1068 | unknown | Playground enhancement — 158 additions, separate feature. |
-| #1083 | unknown | Provider base url feature — 40 additions, overlaps with #1220. |
+| #1533 | unclecode | Add Claude Code GitHub Workflow — CI workflow, not core. |
+| #1274 | Fiser12 | Devcontainer support — 913 additions, dev tooling. |
+| #1420 | ntohidi | Opt-in telemetry system — 3,208 additions. Too large/sensitive. |
+| #1497 | Akeemkabiru | Firecrawl backend support — 191 additions, niche integration. |
+| #1496 | Ahmed-Tawfik94 | normalize_url refactor — 869 additions, too large for URL normalization. |
+| #1518 | YorelN | Docker PDF strategy — 324 additions, Docker-specific. |
+| #1413 | GarfieldTheOldCat | Full scan update — 290 additions, unclear scope. |
+| #1373 | ywatanabe1989 | MCP server endpoint fixes — 753 additions, large. |
+| #1212 | ACakshay | Stateless streamable_http transport for MCP — 154 additions. |
+| #1157 | yesidc | Content change detection — 229 additions, feature scope unclear. |
+| #1140 | tmocky1134 | Prompt-driven recursive crawler script — 268 additions, not core. |
+| #1124 | unclecode | VNC streaming support — 98 additions, niche. |
+| #1068 | jeremygiberson | Playground enhancement — 158 additions, separate feature. |
+| #1083 | Sacristaan | Provider base url feature — 40 additions, overlaps with #1220. |
+| #865 | janbuchar | Apify Actor sponsorship — 4,384 additions, external integration. |
+| #680 | lassedrud | 79,791 additions, Jupyter notebook for Legat4me. Not core. |
 
 ---
 
diff --git a/crawl4ai/prompts.py b/crawl4ai/prompts.py
index c306308e..ce4edd85 100644
--- a/crawl4ai/prompts.py
+++ b/crawl4ai/prompts.py
@@ -8,67 +8,6 @@ And here is the cleaned HTML content of that webpage:
 
 Your task is to break down this HTML content into semantically relevant blocks, and for each block, generate a JSON object with the following keys:
 
-- index: an integer representing the index of the block in the content
-- tags: a list of semantic tags that are relevant to the content of the block
-- content: a list of strings containing the text content of the block
-- questions: a list of 3 questions that a user may ask about the content in this block
-
-To generate the JSON objects:
-
-1. Carefully read through the HTML content and identify logical breaks or shifts in the content that would warrant splitting it into separate blocks.
-
-2. For each block:
-   a. Assign it an index based on its order in the content.
-   b. Analyze the content and generate a list of relevant semantic tags that describe what the block is about.
-   c. Extract the text content, clean it up if needed, and store it as a list of strings in the "content" field.
-   d. Come up with 3 questions that a user might ask about this specific block of content, based on the tags and content. The questions should be relevant and answerable by the content in the block.
-
-3. Ensure that the order of the JSON objects matches the order of the blocks as they appear in the original HTML content.
-
-4. Double-check that each JSON object includes all required keys (index, tags, content, questions) and that the values are in the expected format (integer, list of strings, etc.).
-
-5. Make sure the generated JSON is complete and parsable, with no errors or omissions.
-
-6. Make sure to escape any special characters in the HTML content, and also single or double quote to avoid JSON parsing issues.
-
-Please provide your output within <blocks> tags, like this:
-
-<blocks>
-[{
-  "index": 0,
-  "tags": ["introduction", "overview"],
-  "content": ["This is the first paragraph of the article, which provides an introduction and overview of the main topic."],
-  "questions": [
-    "What is the main topic of this article?",
-    "What can I expect to learn from reading this article?",
-    "Is this article suitable for beginners or experts in the field?"
-  ]
-},
-{
-  "index": 1,
-  "tags": ["history", "background"],
-  "content": ["This is the second paragraph, which delves into the history and background of the topic.",
-              "It provides context and sets the stage for the rest of the article."],
-  "questions": [
-    "What historical events led to the development of this topic?",
-    "How has the understanding of this topic evolved over time?",
-    "What are some key milestones in the history of this topic?"
-  ]
-}]
-</blocks>
-
-Remember, the output should be a complete, parsable JSON wrapped in <blocks> tags, with no omissions or errors. The JSON objects should semantically break down the content into relevant blocks, maintaining the original order."""
-
-PROMPT_EXTRACT_BLOCKS = """Here is the URL of the webpage:
-<url>{URL}</url>
-
-And here is the cleaned HTML content of that webpage:
-<html>
-{HTML}
-</html>
-
-Your task is to break down this HTML content into semantically relevant blocks, and for each block, generate a JSON object with the following keys:
-
 - index: an integer representing the index of the block in the content
 - content: a list of strings containing the text content of the block