archeious/luminos
1
0
Fork 0
Code Issues 42 Pull requests Projects 1 Releases Packages Wiki Activity Actions

test(ai): cover _TokenTracker, _synthesize_from_cache, _discover_directories (#70) #71

Merged
claude-code merged 1 commit from test/issue-70-tracker-synth-discover into main 2026-04-11 10:41:50 -06:00
Conversation 0 Commits 1 Files changed 2 +334 -32
claude-code commented 2026-04-11 10:41:44 -06:00
Collaborator
Copy link

Closes #70.

Second wave of pre-Phase-3 test coverage. The #55 round picked off the easy decision-logic helpers; this round covers the three highest-impact helpers that escaped the first sweep.

Three new test classes

Class Tests What it pins
TestTokenTracker 11 The load-bearing #44 fix: budget_exceeded() uses last_input (most recent call's context size), NOT cumulative input. Cumulative would double-count because each turn's input_tokens already includes the full message history. Tests assert: cumulative-input far above budget does NOT trip the gate when last_input stays small; reset_loop() preserves grand totals; the boundary is strict > not >=.
TestSynthesizeFromCache 5 The synthesis fallback fires only when _run_synthesis exhausts its max_turns, which almost never happens in normal runs — exactly the kind of code that silently rots. Tests assert: empty cache returns the incomplete-message brief; single dir entry produces a markdown line; multi-entry detailed contains all entries; empty-summary entries are skipped; file entries alone do not satisfy (the function reads dir entries only).
TestDiscoverDirectories 9 The leaves-first walk drives the entire dir-loop iteration order and is the foundation of the cache reuse story. Tests assert: empty target returns target only; nested trees come back leaves-first; .git / __pycache__ / node_modules / *.egg-info excluded; custom --exclude honored; hidden dirs excluded by default; show_hidden=True includes them but does not override the skip list.

PLAN.md updates

  • New Phase 2.7 entry for #56 (tool registration cleanup ✅ shipped Session 9).
  • New Phase 2.8 entry for #55 (✅ shipped) and #70 (this PR) — frames pre-Phase-3 test coverage as a two-wave milestone.
  • Removed the now-stale Phase 3.4 (#56) and "Background chore" (#55) sections that were displaced by the pre-Phase-3 cleanup pattern.

Verification

  • 234 tests pass (209 prior + 25 new).
  • All new tests run in well under a second; no real filesystem outside tempfile.mkdtemp().

Notable behavior the tests pin down

  • _TokenTracker.reset_loop() zeroes last_input, not just the loop counters. The original issue draft assumed last_input was preserved across resets — reading the actual code revealed it isn't. The tests now pin the real behavior.
  • The budget gate is strict greater-than. last_input == CONTEXT_BUDGET does NOT trip budget_exceeded(). If anyone changes that to >= later, the test screams.
  • _synthesize_from_cache reads dir entries only. File entries are ignored entirely. The test makes this contract explicit.
  • show_hidden=True does not override the skip list. .git/ stays excluded even with hidden dirs visible — the skip filter and hidden filter are independent gates. Now pinned.
Closes #70. Second wave of pre-Phase-3 test coverage. The #55 round picked off the easy decision-logic helpers; this round covers the three highest-impact helpers that escaped the first sweep. ## Three new test classes | Class | Tests | What it pins | |---|---|---| | `TestTokenTracker` | 11 | The load-bearing #44 fix: `budget_exceeded()` uses `last_input` (most recent call's context size), NOT cumulative input. Cumulative would double-count because each turn's `input_tokens` already includes the full message history. Tests assert: cumulative-input far above budget does NOT trip the gate when `last_input` stays small; `reset_loop()` preserves grand totals; the boundary is strict `>` not `>=`. | | `TestSynthesizeFromCache` | 5 | The synthesis fallback fires only when `_run_synthesis` exhausts its `max_turns`, which almost never happens in normal runs — exactly the kind of code that silently rots. Tests assert: empty cache returns the incomplete-message brief; single dir entry produces a markdown line; multi-entry detailed contains all entries; empty-summary entries are skipped; file entries alone do not satisfy (the function reads dir entries only). | | `TestDiscoverDirectories` | 9 | The leaves-first walk drives the entire dir-loop iteration order and is the foundation of the cache reuse story. Tests assert: empty target returns target only; nested trees come back leaves-first; `.git` / `__pycache__` / `node_modules` / `*.egg-info` excluded; custom `--exclude` honored; hidden dirs excluded by default; `show_hidden=True` includes them but does not override the skip list. | ## PLAN.md updates - New **Phase 2.7** entry for #56 (tool registration cleanup ✅ shipped Session 9). - New **Phase 2.8** entry for #55 (✅ shipped) and #70 (this PR) — frames pre-Phase-3 test coverage as a two-wave milestone. - Removed the now-stale Phase 3.4 (#56) and "Background chore" (#55) sections that were displaced by the pre-Phase-3 cleanup pattern. ## Verification - 234 tests pass (209 prior + 25 new). - All new tests run in well under a second; no real filesystem outside `tempfile.mkdtemp()`. ## Notable behavior the tests pin down - **`_TokenTracker.reset_loop()` zeroes `last_input`**, not just the loop counters. The original issue draft assumed `last_input` was preserved across resets — reading the actual code revealed it isn't. The tests now pin the real behavior. - **The budget gate is strict greater-than.** `last_input == CONTEXT_BUDGET` does NOT trip `budget_exceeded()`. If anyone changes that to `>=` later, the test screams. - **`_synthesize_from_cache` reads dir entries only.** File entries are ignored entirely. The test makes this contract explicit. - **`show_hidden=True` does not override the skip list.** `.git/` stays excluded even with hidden dirs visible — the skip filter and hidden filter are independent gates. Now pinned.
claude-code added 1 commit 2026-04-11 10:41:44 -06:00 
Second wave of pre-Phase-3 test coverage. The #55 round picked off the
easy decision-logic helpers; this round covers the three highest-impact
helpers that escaped the first sweep.

Three new test classes appended to tests/test_ai_pure.py:

- TestTokenTracker (11 tests)
  Pins the load-bearing #44 fix: budget_exceeded() must use last_input
  (the most recent call's context size) NOT cumulative input, because
  each turn's input_tokens already includes the full message history.
  Tests assert: cumulative-input far above budget does NOT trip the
  gate when last_input stays small; reset_loop() preserves grand
  totals; the boundary is strict > not >=.

- TestSynthesizeFromCache (5 tests)
  The synthesis fallback fires only when _run_synthesis exhausts its
  max_turns, which almost never happens in normal runs — exactly the
  kind of code that silently rots. Tests assert: empty cache returns
  the incomplete-message brief and empty detailed; single dir entry
  produces a markdown line; multi-entry detailed contains all entries;
  empty-summary entries are skipped; file entries alone do not satisfy
  (the function reads dir entries only).

- TestDiscoverDirectories (9 tests)
  The leaves-first walk drives the entire dir-loop iteration order
  and is the foundation of the cache reuse story. Tests assert:
  empty target returns target only; nested trees come back leaves-
  first; .git / __pycache__ / node_modules / *.egg-info excluded;
  custom --exclude honored; hidden dirs excluded by default; show_
  hidden=True includes them but does not override the skip list.

PLAN.md: added Phase 2.7 (#56 ✅) and Phase 2.8 (#55 ✅, #70) entries
to the implementation order, and removed the now-stale Phase 3.4 (#56)
and Background chore (#55) sections that were displaced by the
pre-Phase-3 cleanup pattern.

Verification: 234 tests pass (209 prior + 25 new).
claude-code merged commit ef34a83f70 into main 2026-04-11 10:41:50 -06:00
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: archeious/luminos#71
No description provided.
Delete branch "test/issue-70-tracker-synth-discover"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?