haelyra
2f8a5a271d
test: cover inferred-window hook output
2026-08-29 14:55:13 -04:00
Tanel and haelyra
ecdd517765
fix(suggest-compact): don't quote a percentage against an assumed window
...
The context signal always rendered "N% of <window> window", including when
the window size was the assumed 200k default rather than a detected value.
On a 1M session whose transcript carries no [1m] marker, that produced
lines like:
[StrategicCompact] Context ~194k tokens (97% of 200k window)
while actual usage was ~19%. The user compacts on a false alarm, loses
context, and the resulting quality drop reads as a model regression.
The gap is structural: the context threshold defaults to 80% of the
window (160k on 200k), so the signal fires precisely in the 160k-200k
band where the size cannot be determined — above 200k the observed-tokens
fallback correctly infers 1M, and below 160k nothing fires.
Model id alone cannot close this. A tier may ship both a 200k and a 1M
variant under one id, so neither the known-family table nor a new entry
can distinguish them, and the transcript records no window field.
So stop asserting what isn't known: resolveContextWindow() now reports
whether the size was detected (env override, [1m] marker, known family,
or observed tokens > 200k) or assumed, and the hook omits the percentage
and window label when it was assumed. The token count, threshold, and
firing behaviour are unchanged.
resolveContextWindowTokens() keeps its existing signature and semantics.
Note: 3 pre-existing failures in tests/hooks/suggest-compact.test.js
reproduce identically on unmodified main and are untouched here.
2026-08-29 14:55:13 -04:00
haelyra
e82e477034
test(pack): tolerate slow Windows extraction
2026-08-29 14:53:54 -04:00
haelyra
4c7e965209
fix(gan): distinguish scores from verdict thresholds
2026-08-29 14:24:16 -04:00
van3hardy and haelyra
b2a8091440
test(opencode): guard plugin.tool existence before shape assertion
2026-08-29 13:40:57 -04:00
van3hardy and haelyra
e72f1e6824
test(opencode): assert init does not call shell and root plugin tools
2026-08-29 13:40:56 -04:00
van3hardy and haelyra
f932e63b0a
test(opencode): assert built entry is a working plugin, not just an export shape
2026-08-29 13:40:56 -04:00
van3hardy and haelyra
f0684fda32
test(opencode): assert built entry exports only the plugin function
2026-08-29 13:40:56 -04:00
曹博淳 and haelyra
fcef85cb87
test: skip GAN shell checks on Windows
2026-08-29 13:40:56 -04:00
haelyra
cce8f60206
test(gan): use portable Bash lookup on Windows
2026-08-29 13:40:56 -04:00
CaoBochun and haelyra
91e846dfe2
test: execute final GAN score selection
2026-08-29 13:40:56 -04:00
CaoBochun and haelyra
8a396ef542
test: strengthen GAN harness assertions
2026-08-29 13:40:56 -04:00
CaoBochun and haelyra
37e9683161
test: address GAN harness review feedback
2026-08-29 13:40:56 -04:00
CaoBochun and haelyra
70eb0f68ae
fix: make GAN harness score parsing portable
2026-08-29 13:40:56 -04:00
haelyra
73c29bbd08
fix(install): register AdaL capability metadata
2026-08-29 13:40:56 -04:00
1e7493595c
fix(adal): correct README install paths and add adapter regression tests
...
Address CodeRabbit review feedback on PR #2607 :
- Fix .adal/README.md to document actual install paths (rules/, skills/)
instead of the incorrect namespaced rules/ecc/, skills/ecc/ paths.
- Add regression tests for the adal-project install target adapter:
root/install-state path resolution, dual id/target registry lookup,
native .adal root sync-root-children behavior, and foreign platform
path filtering.
Co-Authored-By: AdaL <adal@sylph.ai >
2026-08-29 13:40:56 -04:00
benno0o and haelyra
7c2bc54be2
test: verify Corepack uses the pinned pnpm version
2026-08-29 13:40:56 -04:00
benno0o and haelyra
b48f22f08c
fix: address pre-push pnpm review findings
2026-08-29 13:40:53 -04:00
benno0o and haelyra
03b441792e
fix: resolve pnpm in Git Bash pre-push hook
2026-08-29 13:40:53 -04:00
haelyra and GitHub
656d4b5746
Merge pull request #2869 from actus7/consolidate/mcp-health-v3
...
fix(hooks): consolidate MCP health-check fixes (3 PRs)
2026-08-29 00:22:27 -04:00
haelyra
303f50c57e
test(hooks): construct mismatch prefix immutably
2026-08-28 22:43:28 -04:00
haelyra
b2ab65d0fb
fix(hooks): classify platform-dependent raw prefixes
2026-08-28 22:35:23 -04:00
haelyra and GitHub
d5ebac49b1
Merge pull request #2380 from chs0813/fix/plugin-hook-bootstrap-no-echo
...
fix(hooks): do not echo raw input from plugin-hook-bootstrap.js
2026-08-28 22:24:24 -04:00
haelyra and GitHub
9ff6949798
Merge pull request #2351 from vladyslavTezyk/main
...
Add ukranian translation of the main Readme.
2026-08-28 21:59:45 -04:00
haelyra
13c476965f
fix(hooks): keep MCP reachability probes bounded
...
Remove the redundant JSON-RPC initialize fallback from the consolidated MCP health-check batch. A routed 404 already proves the endpoint is reachable, and the real authenticated MCP call remains authoritative. Avoiding the fallback also prevents a stalled GET plus stalled POST from consuming twice the configured hook timeout.
2026-08-28 21:09:35 -04:00
haelyra
3702a617db
Merge remote-tracking branch 'origin/main' into maint/pr-2866-current
2026-08-28 18:29:35 -04:00
haelyra and GitHub
2aebdd3408
Merge pull request #2870 from actus7/consolidate/hooks-observer-v3
...
fix(hooks): consolidate hooks and observer fixes (5 PRs)
2026-08-28 18:29:03 -04:00
haelyra
1d19789c75
fix(hooks): preserve metadata-marked human prompts
2026-08-28 16:28:12 -04:00
haelyra
77c358dd3f
fix(costs): retain dated Opus 4 legacy pricing
2026-08-28 16:26:13 -04:00
haelyra
70f42102fc
test(evolve): support Windows line endings
2026-08-28 16:25:30 -04:00
Santhi Prakash and haelyra
64f0acf60e
test: split Sonnet model pricing cases
2026-08-28 16:23:25 -04:00
Santhi Prakash and haelyra
ab8cbf6505
test: cover Sonnet 5 cache rate splits
2026-08-28 16:23:25 -04:00
Santhi Prakash and haelyra
616716f370
test: isolate cost tracker cache fixtures
2026-08-28 16:23:25 -04:00
5ee14cb2af
test(hooks): use unique session IDs in Sonnet 5 pricing tests
...
Prevent stale /tmp/harness-cost cache files from affecting Sonnet 5, dated,
near-miss, and cache-rate pricing tests by using Date.now() in each session ID.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-08-28 16:23:25 -04:00
f5d0b295cb
test(hooks): expand Sonnet 5 cost-tracker coverage for cache and model matching
...
- Add cache write/read token pricing test for Sonnet 5.
- Add dated Sonnet 5 ID and claude-sonnet-50 near-miss regression tests.
- Keep Sonnet 4.6 standard rate distinction intact.
Co-Authored-By: Paperclip <noreply@paperclip.ing >
2026-08-28 16:23:25 -04:00
haelyra
950caaaae1
fix(hooks): preserve short sessions and quote evolved metadata
2026-08-28 16:08:19 -04:00
haelyra
b7d6c61b1e
Merge remote-tracking branch 'origin/main' into maint/pr-2870-current
2026-08-28 16:03:10 -04:00
haelyra
1953a749a2
Merge remote-tracking branch 'origin/main' into maint/pr-2873-current
2026-08-28 15:59:31 -04:00
Aditya Datta and haelyra
cb9dfabcf0
test: pin Ollama whitespace normalization
2026-08-28 15:59:31 -04:00
haelyra
51982fdab1
test(opencode): verify recovery through descriptors
2026-08-25 17:27:26 -04:00
haelyra
aaaff77ef9
test(opencode): avoid path race in recovery fixture
2026-08-25 17:23:24 -04:00
haelyra
204cc2d2a3
fix(release): stage ECC 2.2 launch safely
2026-08-25 17:19:45 -04:00
haelyra
d6d0c4e696
test(nasiko): isolate malformed lock fixture
2026-08-25 13:52:19 -04:00
haelyra
e10c4bb5bf
fix(nasiko): use descriptor lock identity
2026-08-25 13:49:26 -04:00
haelyra
307bbd53a6
fix(nasiko): harden lifecycle recovery
2026-08-25 13:34:58 -04:00
haelyra
d66eaf116f
test(opencode): canonicalize Windows path expectations
2026-08-25 12:55:02 -04:00
haelyra
5aa660219e
test(opencode): isolate environment regression processes
2026-08-25 12:37:39 -04:00
haelyra
856733263c
test(opencode): cover legacy upgrade edge cases
2026-08-25 12:28:23 -04:00
haelyra
2331afbfd3
test(opencode): reproduce ambient config leakage
2026-08-25 12:14:58 -04:00
Aditya Datta and Alex Schmitt
9d233aaa63
Trim provider names in prompt builder
2026-08-24 22:27:42 -03:00
haelyra