Clarify session type labels, docstrings, and variable naming#2202
Merged
Trecek merged 2 commits intoMay 7, 2026
Merged
Conversation
- Rename headless→tier_gate in tools_execution.py (3 call sites) for consistency with other gate variable naming conventions - Add orchestration-level docstring section to build_interactive_cmd - Fix orchestration-levels.md: distinguish SessionType enum (headless) from CLI display labels (interactive); clarify L1 run_skill restriction is headless-mode only; expand mapping table with CLI label column - Add bypass rationale comment to resume_ownership_guard.py Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…E501 ignore for vis-lens test build_interactive_cmd docstring uses L1/L2 as orchestration-level vocabulary (not import-layer annotations); add to _LOAD_BEARING_SKIP_PATHS like the other three legitimate orchestration-vocabulary files already in that set. test_vis_lens_methodology_norms.py contains long test-data strings (pre-existing on develop, committed before this branch was cut); add E501 per-file-ignore matching the established pattern for other long-data test files in the codebase.
Trecek
commented
May 7, 2026
Collaborator
Author
Trecek
left a comment
Trecek
left a comment
There was a problem hiding this comment.
AutoSkillit review passed. No blocking issues found. (Self-authored PR — submitted as comment instead of approval)
Trecek
deleted the
clarity-gaps-session-type-labels-docstrings-and-variable-nam/2197
branch
Trecek
added a commit
that referenced
this pull request
May 8, 2026
## Summary Four targeted fixes to eliminate terminology confusion identified by empirical LLM probe testing: 1. **`build_interactive_cmd` docstring** (`execution/commands.py:69`) — add orchestration level annotation mirroring `build_food_truck_cmd`'s pattern. 2. **`headless` variable rename** (`server/tools/tools_execution.py:68,154,263`) — rename the `_require_orchestrator_or_higher` result variable from `headless` to `tier_gate` at all three call sites, matching the naming convention used by every other gate variable. 3. **`docs/orchestration-levels.md` corrections** (lines 32, 34–35, 55, 91–96) — fix four inaccuracies where the doc conflates headless `SessionType` enum values with interactive CLI display labels, and omits the headless-only qualifier on the L1 `run_skill` restriction. 4. **`resume_ownership_guard.py` bypass comment** (`hooks/guards/resume_ownership_guard.py:63`) — add missing rationale comment on the interactive session short-circuit. These changes are documentation and naming-only; they do not alter runtime behaviour. Closes #2197 ## Implementation Plan Plan file: `/home/talon/projects/autoskillit-runs/impl-20260507-152024-443820/.autoskillit/temp/make-plan/clarity_gaps_session_type_labels_plan_2026-05-07_152941.md` 🤖 Generated with [Claude Code](https://claude.com/claude-code) via AutoSkillit <!-- autoskillit:pipeline-signature steps=prepare_pr,run_arch_lenses,compose_pr,annotate_pr_diff,review_pr --> ## Token Usage Summary | Step | Model | count | uncached | output | cache_read | peak_ctx | turns | cache_write | time | |------|-------|-------|----------|--------|------------|----------|-------|-------------|------| | plan | claude-sonnet-4-6 | 1 | 115 | 8.1k | 398.5k | 43.4k | 42 | 34.8k | 5m 11s | | verify | claude-sonnet-4-6 | 1 | 84 | 10.9k | 390.6k | 58.6k | 38 | 46.3k | 2m 56s | | implement* | MiniMax-M2.7-highspeed | 1 | 377.4k | 5.0k | 651.9k | 29.8k | 60 | 16.3k | 2m 5s | | fix | claude-sonnet-4-6 | 1 | 246 | 14.1k | 1.4M | 66.1k | 73 | 73.2k | 9m 58s | | prepare_pr* | MiniMax-M2.7-highspeed | 1 | 104.1k | 5.9k | 255.5k | 28.7k | 24 | 15.3k | 1m 43s | | compose_pr* | MiniMax-M2.7-highspeed | 1 | 42.5k | 1.7k | 169.4k | 28.7k | 15 | 15.1k | 43s | | **Total** | | | 524.5k | 45.7k | 3.3M | 66.1k | | 201.0k | 22m 38s | \* *Step used a non-Anthropic provider; caching behavior may differ.* ## Token Efficiency | Step | LoC Changed | cache_read/LoC | cache_write/LoC | output/LoC | |------|-------------|----------------|-----------------|------------| | plan | 0 | — | — | — | | verify | 0 | — | — | — | | implement | 49 | 13305.0 | 331.7 | 102.9 | | fix | 2 | 698937.0 | 36595.5 | 7052.0 | | prepare_pr | 0 | — | — | — | | compose_pr | 0 | — | — | — | | **Total** | **51** | 63993.5 | 3941.6 | 896.5 | ## Model Usage Breakdown | Model | steps | uncached | output | cache_read | cache_write | time | |-------|-------|----------|--------|------------|-------------|------| | claude-sonnet-4-6 | 3 | 445 | 33.0k | 2.2M | 154.3k | 18m 6s | | MiniMax-M2.7-highspeed | 3 | 524.0k | 12.7k | 1.1M | 46.7k | 4m 31s | --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
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
1 participant
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.
Summary
Four targeted fixes to eliminate terminology confusion identified by empirical LLM probe testing:
build_interactive_cmddocstring (execution/commands.py:69) — add orchestration level annotation mirroringbuild_food_truck_cmd's pattern.headlessvariable rename (server/tools/tools_execution.py:68,154,263) — rename the_require_orchestrator_or_higherresult variable fromheadlesstotier_gateat all three call sites, matching the naming convention used by every other gate variable.docs/orchestration-levels.mdcorrections (lines 32, 34–35, 55, 91–96) — fix four inaccuracies where the doc conflates headlessSessionTypeenum values with interactive CLI display labels, and omits the headless-only qualifier on the L1run_skillrestriction.resume_ownership_guard.pybypass comment (hooks/guards/resume_ownership_guard.py:63) — add missing rationale comment on the interactive session short-circuit.These changes are documentation and naming-only; they do not alter runtime behaviour.
Closes #2197
Implementation Plan
Plan file:
/home/talon/projects/autoskillit-runs/impl-20260507-152024-443820/.autoskillit/temp/make-plan/clarity_gaps_session_type_labels_plan_2026-05-07_152941.md🤖 Generated with Claude Code via AutoSkillit
Token Usage Summary
* Step used a non-Anthropic provider; caching behavior may differ.
Token Efficiency
Model Usage Breakdown