Commit Graph

11 Commits

Author SHA1 Message Date
Ysopwnable 2653b194b6
feat(skills)!: improve Codex onboarding and task recovery (#1613)
Guide task-centered recovery from observed client, registration, PATH and
provider blockers. Install the recovery reference, document exact JavaScript
module selectors, and require clarification before searching for an unnamed
app. Validate public setup in isolated Codex accounts and preserve failed
or unrecognized tool outcomes in the existing evaluator.

Refs: #1587

BREAKING CHANGE: Optional verify:agent reports now use schemaVersion 4.
Consumers must accept expectedFirstTool: null and targetClarificationPassed
for missing-target scenarios. Production CLI/MCP contracts are unchanged.
2026-10-11 03:13:56 +08:00
YouWish 27a9ceade7
fix!: restore caching, preserve failures, and verify fixture claims (#1211)
Restore profile-bound Ghidra snapshot reuse, preserve direct-analysis results through cleanup failures, and grade configured agent fixture claims against returned evidence.

Register the compiled agent-evaluation fixture entry for static analysis.

Co-authored-by: YouWish <29498139+Y0UW1SH@users.noreply.github.com>
Co-authored-by: N0zoM1z0 <161784452+N0zoM1z0@users.noreply.github.com>
2026-10-09 14:49:09 +08:00
morluto e07b81649e
refactor!: simplify runtime tools and remove replay engines (#572)
* fix(hopper): report unavailable procedure body coverage

* refactor!: simplify runtime tools and remove replay engines

Keep direct inspection, capture, and comparison tools. Bind handlers to named contracts and let agents compose experiments with commands and local fixture servers.

BREAKING CHANGE: Remove controlled replay, Node characterization, finite replay-machine, managed runtime planning, and redundant string-tracing tools. Retire process replay, shims, reactive scenarios, custom checkpoints, and active browser replay and origin-scope inputs.
2026-10-05 21:15:04 +08:00
morluto b5e98915c6
fix(tools)!: simplify direct invocation and harden boundary contracts (#555)
Remove REA permission grants, scope ceilings, approval confirmations, and inert settings. Preserve selected local evidence, accept caller-chosen commands and paths, and report actual runtime failures.

Harden provider results, schema serialization, snapshot evidence binding, archive paths, source maps, native screenshots, managed EH parsing, and cancellation cleanup. Regenerate tool metadata and document direct invocation.

BREAKING CHANGE: Removed permission configuration and policy commands, approval fields, filesystem scope inputs, and fixed confirmation options. Process capture inherits the host environment and accepts command names; callers must refresh tool schemas and migrate removed fields.
2026-10-05 20:16:44 +08:00
morluto 5457f4a2bc refactor(schema): remove data-only version markers 2026-09-29 08:45:36 +08:00
morluto 0d96275b68 refactor: return complete tool results inline 2026-09-29 07:08:46 +08:00
morluto ba098f24e5 test(eval): cover navigation and address tool routing 2026-07-29 17:36:51 +00:00
morluto fecddc0549 perf(mcp): reduce cold-start work 2026-07-26 15:02:58 +00:00
morluto 513fa294a4 feat(process): record provider and verifier run lineage 2026-07-22 14:01:47 +00:00
N0zoM1z0 d25e98c3f9 feat: complete REA remediation program 2026-07-22 22:09:12 +09:00
N0zoM1z0 3e3d45856e feat: streamline agent integration and MCP routing 2026-07-20 17:11:06 +08:00