mirror of
https://github.com/wahyd4/by-agent-for-agent.git
synced 2026-08-08 21:06:00 +10:00
15 lines
33 KiB
JSON
15 lines
33 KiB
JSON
{"type":"session","version":3,"id":"ea2a5346-888e-40b4-a53d-4df99c7dbed1","timestamp":"2026-02-02T09:43:58.346Z","cwd":"/home/node/.openclaw/workspace-kimi-k2-5"}
|
||
{"type":"model_change","id":"19db8cbf","parentId":null,"timestamp":"2026-02-02T09:43:58.349Z","provider":"openrouter","modelId":"google/gemini-3-flash-preview"}
|
||
{"type":"thinking_level_change","id":"6c6cc06e","parentId":"19db8cbf","timestamp":"2026-02-02T09:43:58.349Z","thinkingLevel":"low"}
|
||
{"type":"custom","customType":"model-snapshot","data":{"timestamp":1770025438349,"provider":"openrouter","modelApi":"openai-completions","modelId":"google/gemini-3-flash-preview"},"id":"0ec47dd9","parentId":"6c6cc06e","timestamp":"2026-02-02T09:43:58.350Z"}
|
||
{"type":"message","id":"90269ea1","parentId":"0ec47dd9","timestamp":"2026-02-02T09:43:58.374Z","message":{"role":"user","content":[{"type":"text","text":"大哥已经给我开启了派生你的权限！现在请 Kimi 老师出手。\n我们需要一个在 Docker 容器环境里 100% 能下 Twitter/X 原图的脚本。\n\n现状：\n1. 之前的 Playwright 因为缺系统库（libgbm 等）在容器里跑不动。\n2. Nitter 镜像站目前也不太稳定。\n\n请你发挥代码专家的能力：\n1. 编写 `scripts/twitter_pro_dl.py`。\n2. 使用 `uv` 内联依赖声明。\n3. 如果 Playwright 不行，看看能不能用 `httpx` 模拟更高级的浏览器特征（携带 Guest Token 等）直接下载，或者寻找更隐蔽的 API 接口。\n4. 确保在 Linux 容器环境下能跑通。\n\n写完代码并测试（你可以尝试 `uv run` 它），然后把最终能用的脚本保存好。完成后通知我。"}],"timestamp":1770025438367}}
|
||
{"type":"message","id":"7fe4d008","parentId":"90269ea1","timestamp":"2026-02-02T09:44:00.303Z","message":{"role":"assistant","content":[{"type":"toolCall","id":"tool_web_search_0kmKmMRcpEW9F2zlKbma","name":"web_search","arguments":{"query":"twitter guest token api httpx python"},"thoughtSignature":"{\"index\":0,\"id\":\"tool_web_search_0kmKmMRcpEW9F2zlKbma\",\"type\":\"reasoning.encrypted\",\"data\":\"EjQKMgFyyNp8/amw3vEfEypKy7A9cH/gqDjPdhzkYhBvPXJvXByJlX0QuTEi+D9La9deFDTg\",\"format\":\"google-gemini-v1\"}"}],"api":"openai-completions","provider":"openrouter","model":"google/gemini-3-flash-preview","usage":{"input":3924,"output":22,"cacheRead":4053,"cacheWrite":0,"totalTokens":7999,"cost":{"input":0.0019619999999999998,"output":0.000066,"cacheRead":0.00020265,"cacheWrite":0,"total":0.00223065}},"stopReason":"toolUse","timestamp":1770025438373}}
|
||
{"type":"message","id":"8b14d99b","parentId":"7fe4d008","timestamp":"2026-02-02T09:44:01.559Z","message":{"role":"toolResult","toolCallId":"tool_web_search_0kmKmMRcpEW9F2zlKbma","toolName":"web_search","content":[{"type":"text","text":"{\n \"query\": \"twitter guest token api httpx python\",\n \"provider\": \"brave\",\n \"count\": 5,\n \"tookMs\": 1255,\n \"results\": [\n {\n \"title\": \"Getting Started — python-twitter 3.4.2 documentation\",\n \"url\": \"https://python-twitter.readthedocs.io/en/latest/getting_started.html\",\n \"description\": \"import twitter api = twitter.Api(consumer_key=<consumer key>, consumer_secret=<consumer secret>, access_token_key=<access token>, access_token_secret=<access token secret>)\",\n \"siteName\": \"python-twitter.readthedocs.io\"\n },\n {\n \"title\": \"Interacting with the Twitter API using Python – Ben Alex Keen\",\n \"url\": \"https://benalexkeen.com/interacting-with-the-twitter-api-using-python/\",\n \"description\": \"The next step is to make a post request to the authentication endpoint to obtain a Bearer Token to be included in subsequent API requests. ... import requests base_url = 'https://api.twitter.com/' auth_url = '{}oauth2/token'.format(base_url) auth_headers = { 'Authorization': 'Basic {}'.format(b64_encoded_key), 'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8' } auth_data = { 'grant_type': 'client_credentials' } auth_resp = requests.post(auth_url, headers=auth_headers, data=auth_data)\",\n \"siteName\": \"benalexkeen.com\"\n },\n {\n \"title\": \"ajax - Twitter scraping using Python - Stack Overflow\",\n \"url\": \"https://stackoverflow.com/questions/67137294/twitter-scraping-using-python\",\n \"description\": \"To get the x-guest-token you'll need something dynamic because it has expiration, what I would suggest is <strong>send a curl request to twitter, parse the token from there and put it in your header before sending the request</strong>.\",\n \"siteName\": \"stackoverflow.com\"\n },\n {\n \"title\": \"twitter-api-client/twitter/login.py at main · trevorhobenshield/twitter-api-client\",\n \"url\": \"https://github.com/trevorhobenshield/twitter-api-client/blob/main/twitter/login.py\",\n \"description\": \"from httpx import Client · · from .constants import YELLOW, RED, BOLD, RESET, USER_AGENTS · from .util import find_key · · def update_token(client: Client, key: str, url: str, **kwargs) -> Client: caller_name = sys._getframe(1).f_code.co_name · try: headers = { 'x-guest-token': client.cookies.get('guest_token', ''), 'x-csrf-token': client.cookies.get('ct0', ''), 'x-twitter-auth-type': 'OAuth2Client' if client.cookies.get('auth_token') else '', } client.headers.update(headers) r = client.post(url, **kwargs) info = r.json() ·\",\n \"siteName\": \"github.com\"\n },\n {\n \"title\": \"twitter-api-client · PyPI\",\n \"url\": \"https://pypi.org/project/twitter-api-client/\",\n \"description\": \"from twitter.scraper import Scraper ## sign-in with credentials email, username, password = ..., ..., ... scraper = Scraper(email, username, password) ## or, resume session using cookies # scraper = Scraper(cookies={"ct0": ..., "auth_token": ...}) ## or, resume session using cookies (JSON file) # scraper = Scraper(cookies='twitter.cookies') ## or, initialize guest session (limited endpoints) # from twitter.util import init_session # scraper = Scraper(session=init_session()) # user data users = scraper.users(['foo', 'bar', 'hello', 'world']) users = scraper.users_by_ids([123, 234, 345]) # prefe\",\n \"siteName\": \"pypi.org\"\n }\n ]\n}"}],"details":{"query":"twitter guest token api httpx python","provider":"brave","count":5,"tookMs":1255,"results":[{"title":"Getting Started — python-twitter 3.4.2 documentation","url":"https://python-twitter.readthedocs.io/en/latest/getting_started.html","description":"import twitter api = twitter.Api(consumer_key=<consumer key>, consumer_secret=<consumer secret>, access_token_key=<access token>, access_token_secret=<access token secret>)","siteName":"python-twitter.readthedocs.io"},{"title":"Interacting with the Twitter API using Python – Ben Alex Keen","url":"https://benalexkeen.com/interacting-with-the-twitter-api-using-python/","description":"The next step is to make a post request to the authentication endpoint to obtain a Bearer Token to be included in subsequent API requests. ... import requests base_url = 'https://api.twitter.com/' auth_url = '{}oauth2/token'.format(base_url) auth_headers = { 'Authorization': 'Basic {}'.format(b64_encoded_key), 'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8' } auth_data = { 'grant_type': 'client_credentials' } auth_resp = requests.post(auth_url, headers=auth_headers, data=auth_data)","siteName":"benalexkeen.com"},{"title":"ajax - Twitter scraping using Python - Stack Overflow","url":"https://stackoverflow.com/questions/67137294/twitter-scraping-using-python","description":"To get the x-guest-token you'll need something dynamic because it has expiration, what I would suggest is <strong>send a curl request to twitter, parse the token from there and put it in your header before sending the request</strong>.","siteName":"stackoverflow.com"},{"title":"twitter-api-client/twitter/login.py at main · trevorhobenshield/twitter-api-client","url":"https://github.com/trevorhobenshield/twitter-api-client/blob/main/twitter/login.py","description":"from httpx import Client · · from .constants import YELLOW, RED, BOLD, RESET, USER_AGENTS · from .util import find_key · · def update_token(client: Client, key: str, url: str, **kwargs) -> Client: caller_name = sys._getframe(1).f_code.co_name · try: headers = { 'x-guest-token': client.cookies.get('guest_token', ''), 'x-csrf-token': client.cookies.get('ct0', ''), 'x-twitter-auth-type': 'OAuth2Client' if client.cookies.get('auth_token') else '', } client.headers.update(headers) r = client.post(url, **kwargs) info = r.json() ·","siteName":"github.com"},{"title":"twitter-api-client · PyPI","url":"https://pypi.org/project/twitter-api-client/","description":"from twitter.scraper import Scraper ## sign-in with credentials email, username, password = ..., ..., ... scraper = Scraper(email, username, password) ## or, resume session using cookies # scraper = Scraper(cookies={"ct0": ..., "auth_token": ...}) ## or, resume session using cookies (JSON file) # scraper = Scraper(cookies='twitter.cookies') ## or, initialize guest session (limited endpoints) # from twitter.util import init_session # scraper = Scraper(session=init_session()) # user data users = scraper.users(['foo', 'bar', 'hello', 'world']) users = scraper.users_by_ids([123, 234, 345]) # prefe","siteName":"pypi.org"}]},"isError":false,"timestamp":1770025441556}}
|
||
{"type":"message","id":"5a86e7a9","parentId":"8b14d99b","timestamp":"2026-02-02T09:44:03.392Z","message":{"role":"assistant","content":[{"type":"toolCall","id":"tool_web_search_WbY35tmU2TQVuIBgn0lz","name":"web_search","arguments":{"query":"twitter graphql tweet detail api parameters guest token"},"thoughtSignature":"{\"index\":0,\"id\":\"tool_web_search_WbY35tmU2TQVuIBgn0lz\",\"type\":\"reasoning.encrypted\",\"data\":\"EjQKMgFyyNp88uZDBBkGL2s3LyLe4+bCF2wqMyoSj457Ynmep2tJkJy7q7ts/cNfKZ6AAhFU\",\"format\":\"google-gemini-v1\"}"}],"api":"openai-completions","provider":"openrouter","model":"google/gemini-3-flash-preview","usage":{"input":9163,"output":23,"cacheRead":0,"cacheWrite":0,"totalTokens":9186,"cost":{"input":0.0045815,"output":0.000069,"cacheRead":0,"cacheWrite":0,"total":0.004650499999999999}},"stopReason":"toolUse","timestamp":1770025441560}}
|
||
{"type":"message","id":"bf60deed","parentId":"5a86e7a9","timestamp":"2026-02-02T09:44:04.077Z","message":{"role":"toolResult","toolCallId":"tool_web_search_WbY35tmU2TQVuIBgn0lz","toolName":"web_search","content":[{"type":"text","text":"{\n \"query\": \"twitter graphql tweet detail api parameters guest token\",\n \"provider\": \"brave\",\n \"count\": 5,\n \"tookMs\": 658,\n \"results\": [\n {\n \"title\": \"GitHub - trevorhobenshield/twitter-api-client: Implementation of X/Twitter v1, v2, and GraphQL APIs\",\n \"url\": \"https://github.com/trevorhobenshield/twitter-api-client\",\n \"description\": \"}, "reply_count": 44, "retweet_count": 177, "retweeted": false, "user_id_str": "33836629", "id_str": "1648726807301218305" }, "quick_promote_eligibility": { "eligibility": "IneligibleNotProfessional" } } }, "tweetDisplayType": "Tweet" }, "clientEventInfo": { "component": "suggest_ranked_organic_tweet", "details": { "timelinesDetails": { "injectionType": "RankedOrganicTweet", "controllerData": "DAACDAABDAABCgABAAAAABAAAAEKAAIAAAAAAQFACAMACAsKAAlOl1Y+3/MuOg8ADAMAAAAUAQAAEAAAAAAIQAEBAAAAAAAAACAOAA0KAAAAAAIADwAKABBTz7prvJdidwAAAAA=" } } } } }, { "entryId": "homeConversation-1648811419998228480-1-t\",\n \"siteName\": \"github.com\"\n },\n {\n \"title\": \"Graphql value in Twitter API - Stack Overflow\",\n \"url\": \"https://stackoverflow.com/questions/65502651/graphql-value-in-twitter-api\",\n \"description\": \"There is no public GraphQL API for Twitter and you should not be calling this endpoint. The value of the key you’re trying to use is not documented for external use. ... The token 6SBWVfRVIH0h71ssRzNVUg is queryId of the Graphql.\",\n \"siteName\": \"stackoverflow.com\"\n },\n {\n \"title\": \"GitHub - GoodbyePlanet/graphql-twitter-api: :star::point_right: Use GraphQL to get Twitter User and his details by providing Twitter screen_name\",\n \"url\": \"https://github.com/GoodbyePlanet/graphql-twitter-api\",\n \"description\": \"PORT=<port> CONSUMER_KEY=<consumer_key> CONSUMER_SECRET=<consumer_secret> ACCESS_TOKEN=<access_token> ACCESS_TOKEN_SECRET=<access_token_secret> Run npm start. { twitter_user(screen_name: "Nemanjas_Vasic") { name screen_name description followers_count friends_count friends { screen_name } followers { screen_name } tweets { created_at text retweets_count likes } } }\",\n \"siteName\": \"github.com\"\n },\n {\n \"title\": \"Twitter GraphQL sample · GitHub\",\n \"url\": \"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add\",\n \"description\": \"A great way to explore the Twitter API and returned data, without worrying about authorization or local setup. Just add a query in the explorer and hit run. The GraphQL Hub website has an interactive GraphiQL service which allows access to Gitub, Twitter, Giphy and other APIs in the browser without authorization.\",\n \"siteName\": \"gist.github.com\"\n },\n {\n \"title\": \"Nevkontakte: \\\"All #twitter API calls require some sort of...\\\"\",\n \"url\": \"https://m.nevkontakte.com/o/5df582f647a745c6bc02897e2020b152\",\n \"description\": \"The actual authentication happens elsewhere. For guest sessions, you need a `<strong>x-guest-token: 1649859312251027458</strong>` header, where there token is obtained by a separate call. Only a subset of calls are available in this mode.\",\n \"siteName\": \"m.nevkontakte.com\"\n }\n ]\n}"}],"details":{"query":"twitter graphql tweet detail api parameters guest token","provider":"brave","count":5,"tookMs":658,"results":[{"title":"GitHub - trevorhobenshield/twitter-api-client: Implementation of X/Twitter v1, v2, and GraphQL APIs","url":"https://github.com/trevorhobenshield/twitter-api-client","description":"}, "reply_count": 44, "retweet_count": 177, "retweeted": false, "user_id_str": "33836629", "id_str": "1648726807301218305" }, "quick_promote_eligibility": { "eligibility": "IneligibleNotProfessional" } } }, "tweetDisplayType": "Tweet" }, "clientEventInfo": { "component": "suggest_ranked_organic_tweet", "details": { "timelinesDetails": { "injectionType": "RankedOrganicTweet", "controllerData": "DAACDAABDAABCgABAAAAABAAAAEKAAIAAAAAAQFACAMACAsKAAlOl1Y+3/MuOg8ADAMAAAAUAQAAEAAAAAAIQAEBAAAAAAAAACAOAA0KAAAAAAIADwAKABBTz7prvJdidwAAAAA=" } } } } }, { "entryId": "homeConversation-1648811419998228480-1-t","siteName":"github.com"},{"title":"Graphql value in Twitter API - Stack Overflow","url":"https://stackoverflow.com/questions/65502651/graphql-value-in-twitter-api","description":"There is no public GraphQL API for Twitter and you should not be calling this endpoint. The value of the key you’re trying to use is not documented for external use. ... The token 6SBWVfRVIH0h71ssRzNVUg is queryId of the Graphql.","siteName":"stackoverflow.com"},{"title":"GitHub - GoodbyePlanet/graphql-twitter-api: :star::point_right: Use GraphQL to get Twitter User and his details by providing Twitter screen_name","url":"https://github.com/GoodbyePlanet/graphql-twitter-api","description":"PORT=<port> CONSUMER_KEY=<consumer_key> CONSUMER_SECRET=<consumer_secret> ACCESS_TOKEN=<access_token> ACCESS_TOKEN_SECRET=<access_token_secret> Run npm start. { twitter_user(screen_name: "Nemanjas_Vasic") { name screen_name description followers_count friends_count friends { screen_name } followers { screen_name } tweets { created_at text retweets_count likes } } }","siteName":"github.com"},{"title":"Twitter GraphQL sample · GitHub","url":"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add","description":"A great way to explore the Twitter API and returned data, without worrying about authorization or local setup. Just add a query in the explorer and hit run. The GraphQL Hub website has an interactive GraphiQL service which allows access to Gitub, Twitter, Giphy and other APIs in the browser without authorization.","siteName":"gist.github.com"},{"title":"Nevkontakte: \"All #twitter API calls require some sort of...\"","url":"https://m.nevkontakte.com/o/5df582f647a745c6bc02897e2020b152","description":"The actual authentication happens elsewhere. For guest sessions, you need a `<strong>x-guest-token: 1649859312251027458</strong>` header, where there token is obtained by a separate call. Only a subset of calls are available in this mode.","siteName":"m.nevkontakte.com"}]},"isError":false,"timestamp":1770025444049}}
|
||
{"type":"message","id":"e658b270","parentId":"bf60deed","timestamp":"2026-02-02T09:44:06.218Z","message":{"role":"assistant","content":[{"type":"toolCall","id":"tool_web_search_8a7Nn0SNqNihDsqePQQG","name":"web_search","arguments":{"query":"twitter graphql TweetDetail variables features queryId 2024 2025"},"thoughtSignature":"{\"index\":0,\"id\":\"tool_web_search_8a7Nn0SNqNihDsqePQQG\",\"type\":\"reasoning.encrypted\",\"data\":\"EjQKMgFyyNp84T7oruO0mf0QR8tyUFTKMGdj+vLGaOT/rtzDG64+uf28VsZiDMKhvQn6HydI\",\"format\":\"google-gemini-v1\"}"}],"api":"openai-completions","provider":"openrouter","model":"google/gemini-3-flash-preview","usage":{"input":10258,"output":33,"cacheRead":0,"cacheWrite":0,"totalTokens":10291,"cost":{"input":0.005129,"output":0.00009900000000000001,"cacheRead":0,"cacheWrite":0,"total":0.005228}},"stopReason":"toolUse","timestamp":1770025444077}}
|
||
{"type":"message","id":"0a8c62f4","parentId":"e658b270","timestamp":"2026-02-02T09:44:06.897Z","message":{"role":"toolResult","toolCallId":"tool_web_search_8a7Nn0SNqNihDsqePQQG","toolName":"web_search","content":[{"type":"text","text":"{\n \"query\": \"twitter graphql TweetDetail variables features queryId 2024 2025\",\n \"provider\": \"brave\",\n \"count\": 5,\n \"tookMs\": 652,\n \"results\": [\n {\n \"title\": \"Graphql value in Twitter API - Stack Overflow\",\n \"url\": \"https://stackoverflow.com/questions/65502651/graphql-value-in-twitter-api\",\n \"description\": \"You can get list queryId of each Graphql query on the link like main.9dc7dbfa.js\",\n \"siteName\": \"stackoverflow.com\"\n },\n {\n \"title\": \"Unable to fetch tweets using TwitterTweetScraper · Issue #855 · JustAnotherArchivist/snscrape\",\n \"url\": \"https://github.com/JustAnotherArchivist/snscrape/issues/855\",\n \"description\": \"variables = { "focalTweetId": str(self._tweetId), "with_rux_injections": False, "includePromotedContent": True, "withCommunity":True, "withQuickPromoteEligibilityTweetFields": True, "withBirdwatchNotes": False, "withVoice": True, "withV2Timeline": True } features = { "blue_business_profile_image_shape_enabled": True, "responsive_web_graphql_exclude_directive_enabled": True, "verified_phone_label_enabled": True, "responsive_web_graphql_timeline_navigation_enabled": True, "responsive_web_graphql_skip_user_profile_image_extensions_enabled": False, "tweetypie_unmention_optimization_enabled": True,\",\n \"published\": \"April 24, 2023\",\n \"siteName\": \"github.com\"\n },\n {\n \"title\": \"Twitter GraphQL sample · GitHub\",\n \"url\": \"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add\",\n \"description\": \"Twitter GraphQL sample. GitHub Gist: instantly share code, notes, and snippets.\",\n \"siteName\": \"gist.github.com\"\n },\n {\n \"title\": \"How X (Twitter) Designed Its Home Timeline API: Lessons to Learn | by Oleksii Trekhleb | TDS Archive | Medium\",\n \"url\": \"https://medium.com/data-science/api-design-of-x-twitter-home-timeline-da426f19edfe\",\n \"description\": \"*/ // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineRequest = { queryId: string; // 's6ERr1UxkxxBx4YundNsXw' variables: { count: number; // 20 cursor?: string; // 'DAAACgGBGedb3Vx__9sKAAIZ5g4QENc99AcAAwAAIAIAAA' seenTweetIds: string[]; // ['1867041249938530657', '1867041249938530658'] }; features: Features; }; // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineResponse = { data: { home: { home_timeline_urt: { instructions: (TimelineAddEntries | TimelineTerminateTimeline)[]; responseObjects: { feedbackActions: TimelineAction[]; }; }; }\",\n \"published\": \"December 15, 2024\",\n \"siteName\": \"medium.com\"\n },\n {\n \"title\": \"API Design of X (Twitter) Home Timeline | Trekhleb\",\n \"url\": \"https://trekhleb.dev/blog/2024/api-design-x-home-timeline/\",\n \"description\": \"Then, the client (i.e. the browser or the mobile app) will send the queryId along with some additional "dynamic" data (like pagination cursor) to the backend, which, in turn, would fetch the query by its queryId, augment the prepared query with a dynamic data and then would finally execute the actual GraphQL query.\",\n \"siteName\": \"trekhleb.dev\"\n }\n ]\n}"}],"details":{"query":"twitter graphql TweetDetail variables features queryId 2024 2025","provider":"brave","count":5,"tookMs":652,"results":[{"title":"Graphql value in Twitter API - Stack Overflow","url":"https://stackoverflow.com/questions/65502651/graphql-value-in-twitter-api","description":"You can get list queryId of each Graphql query on the link like main.9dc7dbfa.js","siteName":"stackoverflow.com"},{"title":"Unable to fetch tweets using TwitterTweetScraper · Issue #855 · JustAnotherArchivist/snscrape","url":"https://github.com/JustAnotherArchivist/snscrape/issues/855","description":"variables = { "focalTweetId": str(self._tweetId), "with_rux_injections": False, "includePromotedContent": True, "withCommunity":True, "withQuickPromoteEligibilityTweetFields": True, "withBirdwatchNotes": False, "withVoice": True, "withV2Timeline": True } features = { "blue_business_profile_image_shape_enabled": True, "responsive_web_graphql_exclude_directive_enabled": True, "verified_phone_label_enabled": True, "responsive_web_graphql_timeline_navigation_enabled": True, "responsive_web_graphql_skip_user_profile_image_extensions_enabled": False, "tweetypie_unmention_optimization_enabled": True,","published":"April 24, 2023","siteName":"github.com"},{"title":"Twitter GraphQL sample · GitHub","url":"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add","description":"Twitter GraphQL sample. GitHub Gist: instantly share code, notes, and snippets.","siteName":"gist.github.com"},{"title":"How X (Twitter) Designed Its Home Timeline API: Lessons to Learn | by Oleksii Trekhleb | TDS Archive | Medium","url":"https://medium.com/data-science/api-design-of-x-twitter-home-timeline-da426f19edfe","description":"*/ // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineRequest = { queryId: string; // 's6ERr1UxkxxBx4YundNsXw' variables: { count: number; // 20 cursor?: string; // 'DAAACgGBGedb3Vx__9sKAAIZ5g4QENc99AcAAwAAIAIAAA' seenTweetIds: string[]; // ['1867041249938530657', '1867041249938530658'] }; features: Features; }; // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineResponse = { data: { home: { home_timeline_urt: { instructions: (TimelineAddEntries | TimelineTerminateTimeline)[]; responseObjects: { feedbackActions: TimelineAction[]; }; }; }","published":"December 15, 2024","siteName":"medium.com"},{"title":"API Design of X (Twitter) Home Timeline | Trekhleb","url":"https://trekhleb.dev/blog/2024/api-design-x-home-timeline/","description":"Then, the client (i.e. the browser or the mobile app) will send the queryId along with some additional "dynamic" data (like pagination cursor) to the backend, which, in turn, would fetch the query by its queryId, augment the prepared query with a dynamic data and then would finally execute the actual GraphQL query.","siteName":"trekhleb.dev"}]},"isError":false,"timestamp":1770025446869}}
|
||
{"type":"message","id":"642ca968","parentId":"0a8c62f4","timestamp":"2026-02-02T09:44:09.203Z","message":{"role":"assistant","content":[{"type":"toolCall","id":"tool_web_search_TidVoDT1kYu9G2LFCzJv","name":"web_search","arguments":{"query":"twitter graphql TweetDetail queryId latest 2025"},"thoughtSignature":"{\"index\":0,\"id\":\"tool_web_search_TidVoDT1kYu9G2LFCzJv\",\"type\":\"reasoning.encrypted\",\"data\":\"EjQKMgFyyNp8/FIX+IvQA/RlVBt+aF+j6Iu4InQmZrzO0lzrwfsMWJDIm1rToNpDpIVBmvEF\",\"format\":\"google-gemini-v1\"}"}],"api":"openai-completions","provider":"openrouter","model":"google/gemini-3-flash-preview","usage":{"input":11326,"output":27,"cacheRead":0,"cacheWrite":0,"totalTokens":11353,"cost":{"input":0.005663,"output":0.000081,"cacheRead":0,"cacheWrite":0,"total":0.005744}},"stopReason":"toolUse","timestamp":1770025446897}}
|
||
{"type":"message","id":"863e4cbf","parentId":"642ca968","timestamp":"2026-02-02T09:44:10.127Z","message":{"role":"toolResult","toolCallId":"tool_web_search_TidVoDT1kYu9G2LFCzJv","toolName":"web_search","content":[{"type":"text","text":"{\n \"query\": \"twitter graphql TweetDetail queryId latest 2025\",\n \"provider\": \"brave\",\n \"count\": 5,\n \"tookMs\": 898,\n \"results\": [\n {\n \"title\": \"Twitter GraphQL sample · GitHub\",\n \"url\": \"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add\",\n \"description\": \"The GraphQL Hub website has an interactive GraphiQL service which allows access to Gitub, Twitter, Giphy and other APIs in the browser without authorization.\",\n \"siteName\": \"gist.github.com\"\n },\n {\n \"title\": \"How X (Twitter) Designed Its Home Timeline API: Lessons to Learn | by Oleksii Trekhleb | TDS Archive | Medium\",\n \"url\": \"https://medium.com/data-science/api-design-of-x-twitter-home-timeline-da426f19edfe\",\n \"description\": \"*/ // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineRequest = { queryId: string; // 's6ERr1UxkxxBx4YundNsXw' variables: { count: number; // 20 cursor?: string; // 'DAAACgGBGedb3Vx__9sKAAIZ5g4QENc99AcAAwAAIAIAAA' seenTweetIds: string[]; // ['1867041249938530657', '1867041249938530658'] }; features: Features; }; // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineResponse = { data: { home: { home_timeline_urt: { instructions: (TimelineAddEntries | TimelineTerminateTimeline)[]; responseObjects: { feedbackActions: TimelineAction[]; }; }; }\",\n \"published\": \"December 15, 2024\",\n \"siteName\": \"medium.com\"\n },\n {\n \"title\": \"Search tweets of Twitter with its API v2 with a GraphQL based query - Pipedream\",\n \"url\": \"https://pipedream.com/community/t/search-tweets-of-twitter-with-its-api-v2-with-a-graphql-based-query/2890\",\n \"description\": \"I’d like to improve my resource usage efficiency of Twitter tweet search, so I consider to use Twitter API v2, so how can I reach and query it most easily from PipeDream? Their solution is based on GraphQL ( Twitter bl…\",\n \"published\": \"July 27, 2022\",\n \"siteName\": \"pipedream.com\"\n },\n {\n \"title\": \"Twitter GraphQL API opens up new facets| Data365 Social Media API does as well\",\n \"url\": \"https://data365.co/blog/twitter-graphql-api\",\n \"description\": \"The advantage of combining data queries through a single interface is that the public Twitter API can easily provide new Twitter features by querying GraphQL data that is already directly used by user applications. GraphQL is now, without exaggeration, the latest in IT fashion.\",\n \"siteName\": \"data365.co\"\n },\n {\n \"title\": \"Unable to fetch tweets using TwitterTweetScraper · Issue #855 · JustAnotherArchivist/snscrape\",\n \"url\": \"https://github.com/JustAnotherArchivist/snscrape/issues/855\",\n \"description\": \"Describe the bug Trying to fetch the tweet using TwitterTweetScraper but returns no output Apparently the cause of this bug is due to not updated GQL endpoints outdated - https://twitter.com/i/api/graphql/NNiD2K-nEYUfXlMwGCocMQ/TweetDeta...\",\n \"published\": \"April 24, 2023\",\n \"siteName\": \"github.com\"\n }\n ]\n}"}],"details":{"query":"twitter graphql TweetDetail queryId latest 2025","provider":"brave","count":5,"tookMs":898,"results":[{"title":"Twitter GraphQL sample · GitHub","url":"https://gist.github.com/MichaelCurrin/ae75545c451629b909a7dd7580a08add","description":"The GraphQL Hub website has an interactive GraphiQL service which allows access to Gitub, Twitter, Giphy and other APIs in the browser without authorization.","siteName":"gist.github.com"},{"title":"How X (Twitter) Designed Its Home Timeline API: Lessons to Learn | by Oleksii Trekhleb | TDS Archive | Medium","url":"https://medium.com/data-science/api-design-of-x-twitter-home-timeline-da426f19edfe","description":"*/ // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineRequest = { queryId: string; // 's6ERr1UxkxxBx4YundNsXw' variables: { count: number; // 20 cursor?: string; // 'DAAACgGBGedb3Vx__9sKAAIZ5g4QENc99AcAAwAAIAIAAA' seenTweetIds: string[]; // ['1867041249938530657', '1867041249938530658'] }; features: Features; }; // POST https://x.com/i/api/graphql/{query-id}/HomeTimeline export type TimelineResponse = { data: { home: { home_timeline_urt: { instructions: (TimelineAddEntries | TimelineTerminateTimeline)[]; responseObjects: { feedbackActions: TimelineAction[]; }; }; }","published":"December 15, 2024","siteName":"medium.com"},{"title":"Search tweets of Twitter with its API v2 with a GraphQL based query - Pipedream","url":"https://pipedream.com/community/t/search-tweets-of-twitter-with-its-api-v2-with-a-graphql-based-query/2890","description":"I’d like to improve my resource usage efficiency of Twitter tweet search, so I consider to use Twitter API v2, so how can I reach and query it most easily from PipeDream? Their solution is based on GraphQL ( Twitter bl…","published":"July 27, 2022","siteName":"pipedream.com"},{"title":"Twitter GraphQL API opens up new facets| Data365 Social Media API does as well","url":"https://data365.co/blog/twitter-graphql-api","description":"The advantage of combining data queries through a single interface is that the public Twitter API can easily provide new Twitter features by querying GraphQL data that is already directly used by user applications. GraphQL is now, without exaggeration, the latest in IT fashion.","siteName":"data365.co"},{"title":"Unable to fetch tweets using TwitterTweetScraper · Issue #855 · JustAnotherArchivist/snscrape","url":"https://github.com/JustAnotherArchivist/snscrape/issues/855","description":"Describe the bug Trying to fetch the tweet using TwitterTweetScraper but returns no output Apparently the cause of this bug is due to not updated GQL endpoints outdated - https://twitter.com/i/api/graphql/NNiD2K-nEYUfXlMwGCocMQ/TweetDeta...","published":"April 24, 2023","siteName":"github.com"}]},"isError":false,"timestamp":1770025450100}}
|
||
{"type":"message","id":"5306ef2b","parentId":"863e4cbf","timestamp":"2026-02-02T09:44:11.541Z","message":{"role":"assistant","content":[],"api":"openai-completions","provider":"openrouter","model":"google/gemini-3-flash-preview","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"error","timestamp":1770025450127,"errorMessage":"400 Provider returned error\n{\n \"error\": {\n \"code\": 400,\n \"message\": \"Unable to submit request because Thought signature is not valid.. Learn more: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini\",\n \"status\": \"INVALID_ARGUMENT\"\n }\n}\n"}}
|