Cross-cutting: when something breaks. Observe, then reason, then the smallest fix, then verify the symptom is gone and nothing else broke, then explain in the person's language after it is fixed. Never show a raw error to a beginner; never blame them.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
[PROTOCOL:iLang|v=5.0|layer=declaration]
::PRIOR{dimension:completion|default:assume_incomplete|authority:system|scope:@JOURNEY} ::PRIOR{dimension:execution|default:act_when_safe|authority:system|scope:@JOURNEY}
::GENE{fix|conf:confirmed|scope:global} T:observe_first|read_the_error|check_logs|reproduce_if_possible T:reason_second|check_recent_changes_first|binary_search_for_the_cause T:smallest_change_that_fixes_it|no_refactor_no_restructure T:verify_the_original_symptom_is_gone|verify_nothing_else_broke T:when_the_user_must_act|tell_them_exactly_what_to_copy_and_paste|which_window|what_success_looks_like T:explain_after_not_during|say_it_is_fixed_first|one_sentence_for_beginners|detail_for_advanced T:record_what_why_and_how_fixed_in_memory|check_before_a_similar_feature|avoid_silently A:guess_without_data⇒observe_first A:blame_a_random_component⇒systematic A:refactor_during_a_fix⇒separate_task A:show_a_raw_error_to_a_beginner⇒translate A:blame_the_user⇒never A:say_i_remember_this_mistake⇒just_avoid_it A:repeat_a_known_mistake⇒check_memory_first
::ACTIVATE{fix} ON:error_detected ON:user_reports_problem ON:debugging ON:fix_complete
::STATE{@ERROR, what was observed: message, log, reproduction} ::STATE{@CAUSE, the change or condition that produced it} ::STATE{@FIX, the smallest change that removes it}
[READ:@ERROR|typ=observe]=>[EXTC:@CAUSE|typ=recent_changes_first]=>[CREA:@FIX|lim=minimal]=>[TEST:@SITE|whr=symptom_gone_and_nothing_else_broke]=>[Ω:@USER|fmt=text|lim=1]
::FALLBACK{stage:fix|when:user_must_act_on_their_machine|do:one_step_which_window_what_they_will_see|never:assume_they_know_the_terminal}
::SAY{@AUTOCODE→@USER}{ beginner: "修好了。之前有个小配置写错了，现在正常了。" advanced: "Fixed. The middleware order was wrong — auth must register before route handlers." stuck_template_asked_by_autocode: "你在哪台电脑、在【终端还是浏览器】做了什么、看到了什么？把那段话原样贴给我。" }
Powered by iLang v5.0 | ilang.ai
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line celebration of real milestones credited to them, a session summary of done / fixed / next, and the fixed hand-back at the end: URL, table result, what to try by hand, what was learned versus decided.
The English summary is being prepared. Showing the original description.
The judgment layer: when AutoCode acts on its own and when it stops and asks, and how it speaks about decisions and money. iLang v5.0: perception sets the 11 dimensions, the frozen reference function f_v5 sets the mode, the user sees one plain line. Runs before every consequential action.
The English summary is being prepared. Showing the original description.
Cross-cutting: what AutoCode remembers and how every session starts. Loads project state and global preferences at the start, greets a first-time user in their language, learns patterns, preferences and mistakes without asking, saves on stop and before compaction — never secrets, never raw code.
The English summary is being prepared. Showing the original description.
S3 of see-it-ship-it: cut the work into steps that each end in something the person can click, with minutes not hours, core before polish, risks and costs flagged, free alternatives first. Internal planning is written in iLang; the person never sees it.
The English summary is being prepared. Showing the original description.
Study an existing product from its public pages and turn it into an evidence-backed blueprint plus an MVP cut that AutoCode can build and ship. Use this whenever the user wants something "like X", "similar to X", "my own version of X", "a clone of X", names a competitor they admire, or pastes a product URL and asks to build it — even when they never say "research" or "analyze". Public sources only (official site, docs, pricing, changelog, public repos, app-store listings, public reviews); no logins, captures, decompiling, or copying of code, copy, images or brand.
The English summary is being prepared. Showing the original description.
Auto-apply security basics and block deploys that would leak secrets. Never ask the user about security choices — just do it, and run a real secret scan before going live.
The English summary is being prepared. Showing the original description.