Skip to content

Add AGENTS.md with initial cloud agent instructions#1

Closed
FluffyAIcode wants to merge 1 commit intomainfrom
cursor/env-setup-b5e9
Closed

Add AGENTS.md with initial cloud agent instructions#1
FluffyAIcode wants to merge 1 commit intomainfrom
cursor/env-setup-b5e9

Conversation

@FluffyAIcode
Copy link
Copy Markdown
Owner

Adds AGENTS.md documenting the current state of the repository for future Cursor Cloud agents.

The repository is brand new (only contains a LICENSE file), so this file notes that there are no dependencies, services, or build commands yet, and instructs future agents to re-evaluate once application code is added.

Open in Web Open in Cursor 

Co-authored-by: FluffyAIcode <FluffyAIcode@users.noreply.github.com>
cursor Bot pushed a commit that referenced this pull request Apr 21, 2026
Targets directly hit:
  4.13 save_load_consistency  : FAIL -> PASS (outputs bit-identical)
  4.25 prefix_length_scaling  : FAIL -> PASS (mass_B/mass_A = 1.543 >= 1.10)

Targets held (no regression from v3.44-rewrite):
  4.24 context_descriptor_cluster_probe: PASS (0.9375 / 1.0)
  4.16 retrieval_generation_alignment_audit: PASS

Targets still FAIL (same as v3.44-rewrite, unaddressed by #1/#3):
  4.23 keyword_specific_tail_slot_probe: median_rank=1402, hit=0
  4.8 / 4.21 / 4.7  : decoder repetition triple (will be addressed by #2)
  4.11 / 4.19       : prefix-token-class mismatch (will be addressed by #5)

Surprising finding on 4.23:
  The diagnostic dump (diag_4_23_slot_direction.py) reveals that
  bridge._last_tail_slots read by 4.23 does NOT come from prefix_cond -
  it comes from the SECOND inject call inside _build_contrastive_uncond_prefix,
  which is called with rare_keyword_wte_residual=None.  This overwrites
  _last_tail_slots and _last_residual with the uncond contrastive prefix's
  values.  The probe has been reading the uncond tail since at least v3.42.
  This is a pre-existing diagnostic-buffer aliasing bug, not a change-#1
  regression.  It explains why v3.48 (median_rank=1089) and v3.45
  (median_rank=1402) both point at whitespace/punct - both are reading
  tail slots that were rebuilt without rare-keyword residual.
  Fix belongs in a separate PR (write residual to a second buffer in
  cond path, or snapshot bridge._last_tail_slots before uncond inject).

axis_coverage under v3.49 runner reporting:
  A compression   : ratio 8.97 (< 10)     FAIL
  B injection     : 164224 floats, O(1)   PASS
  C fidelity      : 7/11 (threshold 9)    FAIL
  D stability     : 2/3 (4.21 FAIL)       FAIL

elapsed: 1508 s on CPU, AMS_DETERMINISTIC=1, fresh init.

This audit validates:
  - #1 revert did not regress anything and recovered 4.25 (predicted by
    the plan's 'LN-bounded extra slot mass' magnitude calculus).
  - #3 refresh timing alignment recovered 4.13 (predicted by the plan's
    'rare_keyword_ids fresh-vs-load asymmetry' mechanism).

This audit does not validate:
  - any claim about 4.23 reachability; 4.23 has a pre-existing aliasing
    bug that the current plan's change #2 ([B] replacement) cannot fix
    because the replacement would still be overwritten by the uncond
    inject call.

Co-authored-by: FluffyAIcode <FluffyAIcode@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants