Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 27 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
<h1 align="center">CompText V7</h1>

<p align="center">
<strong>Deterministic replay-survivability validation for compressed operational state in long-horizon AI agents.</strong>
<strong>Deterministic replay-integrity validation for compressed MCP-style operational traces.</strong>
</p>

<p align="center">
Expand All @@ -27,7 +27,7 @@
· <a href="docs/failure_taxonomy.md">Failure Taxonomy</a>
</p>

CompText V7 does not ask whether a compressed summary sounds good. It asks whether the compressed state can still replay the operational facts required to continue the work.
CompText V7 validates whether compressed operational commitments survive deterministic replay reconstruction in MCP-style agent workflows.

---

Expand Down Expand Up @@ -78,9 +78,26 @@ flowchart LR

---

## Operational commitments

CompText V7 validates whether deterministic replay reconstruction preserves:

- evidence
- constraints
- blockers
- dependencies
- recovery paths
- tool order
- capability boundaries
- governance/policy gates

The `mcp_trace_replay` fixture family validates deterministic replay safety for tool order, validation-before-action, dependency chains, recovery paths, and capability boundaries. Registered contracts: `tool_call_order_preserved`, `validation_before_unsafe_action`, `dependency_chain_preserved`, `recovery_path_available`, `capability_boundary_respected`.

---

## Current fixture-bound signal

- Three manifest-registered operational fixture families.
- Four manifest-registered operational fixture families.
- Standard levels: `baseline`, `mild`, `moderate`, `severe`.
- Deterministic evaluation mode.
- Exact rational scoring.
Expand Down Expand Up @@ -157,6 +174,8 @@ flowchart LR
| `artifacts/layered_admissibility_results.json` | Layered admissibility outputs. |
| `artifacts/multi_family_admissibility_results.json` | Multi-family deterministic aggregates. |
| `artifacts/multi_family_admissibility_curves.svg` | Deterministic degradation curve rendering. |
| `artifacts/mcp_trace_replay_results.json` | Deterministic MCP trace replay contract outcomes. |
| `artifacts/replay_semantic_integrity_results.json` | Deterministic replay semantic integrity outcomes. |
| `docs/benchmarks/multi_family_admissibility_benchmark.md` | Benchmark method and interpretation boundaries. |
| `docs/failure_taxonomy.md` | Failure label documentation. |

Expand All @@ -181,6 +200,7 @@ pytest tests/test_paper_replay_bench.py tests/test_agent_trace_replay.py -q
- `coding_workflow_pr_review`
- `incident_response_page_triage`
- `cross_domain_operational_dependency_workflow`
- `mcp_trace_replay`

```mermaid
flowchart LR
Expand All @@ -196,6 +216,10 @@ flowchart LR
C --> L2
C --> L3
C --> L4
D["mcp_trace_replay"] --> L1
D --> L2
D --> L3
D --> L4
L1 --> M["manifest registration"]
L2 --> M
L3 --> M
Expand Down
Loading