Repository navigation
Design: FireRed AutoStory pilot to Brock, reusable pieces in their final homes - #42
Merged
Merged
Conversation
…tory Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
dayfine
added a commit
that referenced
this pull request
Oct 25, 2026
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…from a new game Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Reorder the plan so the first PRs touch only FRLG files and end in a runnable pilot (new game -> Boulder Badge in about 10 PRs, first runnable at PR 5), with an F3 go/no-go gate on checkpoints and Switch hours. The SV/BDSP shared run flow moves to a later phase. Add a one-page upstream-facing proposal, standalone review comment drafts for PokemonAutomation#1717 (not posted), and the FRLG authors on main. Drop the agent process section. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
dayfine
changed the title
The plan wrote FRLG's run flow and tile path inside the FRLG module and moved them out in phase D (R0, T4): move-only PRs of our own code. Adding new files to a shared module changes no one else's code, so they now start in Pokemon/AutoStory and Pokemon/Navigation. New section 0.1 lists the game-neutral pieces from SV, BDSP PokemonAutomation#1717, SwSh PokemonAutomation#1207, BBQ and the BDSP lab work (screen machine, step trace, failure policy, list selection, system keyboard, Lab Console, run flow, tile path, decision tests) with their homes; D4 builds the FRLG intro on the screen machine. The proposal says the same. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
dayfine
changed the title
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…aced it Lessons: a table of his recorded route against what console B showed (timed legs, slot-3 Ember, no healing, pixel-matched Potion, the Poke Mart lady and Barry missed by a tile), our own mistakes in this round (an optional step kept for hours, claims not checked on screen, map errors, untiled movement, a fixed OCR cut), and stepping through new ground before automating it. Design: the executor, move choice, training and Potion healing as built, and the Lab Console stepping. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…t's talk Each row of the Butters comparison and each of our own mistakes now links the fork commit that fixed it, on bdsp/new-game-intro-v2. Adds what stepping through Phase 23 showed: A re-opens the president's talk, B advances it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…om the ground; towns need grids too Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…nt 00 leftovers scheduled Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…oma; Butters' segment 01 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…MVP branches Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…hire Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…esources) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…und them Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
) and Part 2 for us Sections are renumbered; cross-references updated. Butters' segment 01 table and the two PokemonAutomation#1717 failures from r108 get their own sections in Part 1. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
…nAutomation#1717 drafts stale; pose status Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E
dayfine
marked this pull request as ready for review
October 30, 2026 05:24
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Base:
main. No parent PRs; the diff is only the design docs.FRLG on
mainhas most of the pieces an AutoStory needs but nothing that plays the story, and SV, the BDSP draft (PokemonAutomation#1717) and the SwSh draft (PokemonAutomation#1207) each rebuild the same run flow and screen handling. The plan builds a FireRed AutoStory to Brock first, in about 10 PRs that change no existing program: game-neutral pieces (run flow, tile path, a closed-loop screen driver, step trace) go into shared folders from their first PR, with FRLG as their only user, so nothing of ours is moved later. Users can run it from PR 5, and a public go/no-go gate (every pilot checkpoint passes 3 times from its save, at 3 Switch hours or less per checkpoint) decides whether to continue; migrating SV and offering the shared code to BDSP come only after the pilot is in use.AutoStory-Proposal.mdis the one-page upstream summary,AutoStory.mdthe full plan (§0.1 lists the reusable pieces and their homes), andAutoStory-1717-review-drafts.mdholds unposted review comments for the BDSP PR. Not tested on a Switch; the screen driver is being proven on the BDSP intro in the lab.🤖 Generated with Claude Code
https://claude.ai/code/session_01AKYzhrMnPK61XHWEch4a6E