| workspace_autoresearch prompts: DSL-neutralize PLAN / DIAGNOSE / REPLAN
The shared planning prompts and diversity check were authored with
triton vocabulary baked in (matmul epilogues, num_warps, num_stages,
block_size_*). Same prompt flow runs for every DSL, so the framing
should match: otherwise an ascendc / cuda_c / tilelang task gets
copy-as-shown plan items oriented around triton primitives, and
parameter-tuning detection has dead clauses on one DSL while letting
the others' tuning vocabulary slip through.
guidance.py:
- _PLAN_XML_EXAMPLE rewritten to three structural items (tree-style
accumulation / inner-axis re-layout / vector-width padding) using
DSL-neutral language; design-note comment updated to match
- DIAGNOSE subagent prompt's hardcoded "Do NOT Write kernel.py"
replaced with the editable-file list rendered from task.yaml,
so multi-file editable sets (compile-pipeline DSLs) read right;
threads the existing editable kwarg through _diagnose_subagent_
prompt's signature
create_plan.py:
- _PARAM_WORDS expanded with cross-backend tuning vocabulary
(chunk / shard / lanes / threads / cores / queue / depth / count /
dim / value / search)
- _PARAM_PHRASES grew sections for ascendc (block_dim / tile_num /
core_num / queue_depth / tiling_key) and cuda_c (threads_per_block
/ blocks_per_grid / shared_mem); kept as one shared set rather
than DSL-bucketed since diversity-check semantics are identical
across DSLs
.claude/agents/ar-diagnosis.md:
- first-time check-in (previously gitignored); content already in
DSL-neutral form: kernel.py literals replaced with "editable
file(s) listed in the parent's prompt", since the parent
guidance.py already passes the resolved list
Single _dsl_specific_hint branch in guidance.py was considered and
rejected: DSL-specific knowledge (e.g. ascendc's three-source-string
contract) belongs in the skills tree, not the prompt scaffolding.
guidance stays one shared shape for every DSL.
| 5 天前 |
| gitignore: stop ignoring workspace_autoresearch's .claude/ subtree
The generic .claude/ rule (two entries in this .gitignore) was meant
for editor-local Claude Code config, the kind that lives under user
home and shouldn't be in the repo. workspace_autoresearch ships
project-level Claude Code definitions under its own .claude/:
- settings.json points AKG_AGENTS_AR_SKILLS_ROOT at the in-repo
skills tree and carries the AR-script permissions allowlist
- commands/autoresearch.md is the /autoresearch slash command spec
- agents/ar-diagnosis.md (added in follow-up commit) is the DIAGNOSE
subagent prompt
These are shared definitions, not personal config, so they belong in
git. Negation rule sits after both generic .claude/ entries because
gitignore is last-match-wins; the companion /** pattern is needed
because a parent-dir negation alone does not always re-include its
children.
| 5 天前 |
| gitignore: stop ignoring workspace_autoresearch's .claude/ subtree
The generic .claude/ rule (two entries in this .gitignore) was meant
for editor-local Claude Code config, the kind that lives under user
home and shouldn't be in the repo. workspace_autoresearch ships
project-level Claude Code definitions under its own .claude/:
- settings.json points AKG_AGENTS_AR_SKILLS_ROOT at the in-repo
skills tree and carries the AR-script permissions allowlist
- commands/autoresearch.md is the /autoresearch slash command spec
- agents/ar-diagnosis.md (added in follow-up commit) is the DIAGNOSE
subagent prompt
These are shared definitions, not personal config, so they belong in
git. Negation rule sits after both generic .claude/ entries because
gitignore is last-match-wins; the companion /** pattern is needed
because a parent-dir negation alone does not always re-include its
children.
| 5 天前 |
