Commit Graph

4 Commits

Author SHA1 Message Date
kshitijk4poor
70203f7752 test(agent): trim #121548 tests to the two invariants
Keep only guard parity (a minted marker matches _COMPRESSION_MARKER_RE)
and the source-level no-imitable-idiom invariant; the per-helper and
per-renderer unit tests restate the helpers and are covered by the
existing renderer tests updated in the cherry-pick.
2026-09-26 23:49:25 +05:30
ahisblessed
77b9ea0831 fix(agent): route every model-visible elision through the non-imitable compression marker (#121548)
The #83714 fix hardened only the tool-call args renderer; five other
renderers (plus three same-idiom siblings) still composed the bare
truncation marker, which the model imitated from replayed context into
new durable writes (#83435).

This routes all model-visible elision in agent/ through shared helpers
in agent/compression_marker.py:

- elide(text, limit): head + marker cap with accurate omitted/total counts
- elide_middle(text, head, tail): kept head/tail with the middle elided

The elision marker's first sentence is byte-identical to the args marker's,
so the existing _COMPRESSION_MARKER_RE (and the dispatch-boundary guard in
tool_dispatch_helpers) rejects a copied marker regardless of which renderer
leaked it; only the tool-call-specific second sentence is dropped so the
marker still fits small caps (the clarify summary cap is 199 chars).

Routed sites:
- context_compressor.py: static-fallback turn renderer, _sum_clarify(),
  summarizer prompt builder (middle elision), active-task snapshot,
  lean user-message quotes (2 sites)
- skill_preprocessing.py: inline-shell output embedded into skill bodies
- lsp/reporter.py: truncate() for <diagnostics> tool output
- verification_stop.py: verify-on-stop nudge output summary

Regression test asserts the imitable idiom appears nowhere in agent/
strings (comments excluded), so a new open-coded renderer cannot land
silently.

Fixes #121548

(cherry picked from commit 69c63d50b4ababedf4fb4ff88c08f5d1e144a79f)
2026-09-26 23:49:25 +05:30
teknium1
b2ecd3518f test: purge low-value tests, lane py04 (294 removed)
Change-detectors, tautologies, source-reading tests, redundant duplicates,
mock-echo tests and dead/unrunnable tests. Per-test rationale in the lane
ledger (category + reason for every removal).
2026-09-23 03:15:26 -07:00
teknium1
85564321be fix(windows): route every bare-bash spawn through _find_bash and surface silent interpreter failures
CreateProcess resolves a bare "bash" to System32 WSL launcher before PATH,
and shutil.which("bash") inherits PATH order (#115124), so node bootstrap,
the TUI node probe and webhook filter scripts ran the wrong interpreter on
Windows. All four sites now use tools.environments.local._find_bash (Git Bash
first, probed). rc!=0 with no output at all is now a WARNING in webhook
filters and an explicit [inline-shell exit N with no output] marker in skills.

Co-authored-by: funky-xamarin <30426178+Wenfengcheng@users.noreply.github.com>
2026-09-20 15:50:26 -07:00