Update detailed README for DiffusionGemma Infinite-Context

README.md

@@ -5,30 +5,46 @@ library_name: transformers
 pipeline_tag: image-text-to-text
 tags:
 - diffusiongemma
+- gemma-4
 - infinite-context
-- nzfc-gram
 - external-memory
 - evidence-retrieval
+- long-context
 - large-documents
+- legal-documents
+- ai-memory
+- nzfc-gram
+- runtime-overlay
+- not-native-infinite-context
 ---
 
 # DiffusionGemma-26B-A4B-it-Infinite-Context
 
-NZFC-GRAM runtime overlay for external evidence context around `google/diffusiongemma-26B-A4B-it`.
+**NZFC-GRAM runtime overlay for external evidence context around `google/diffusiongemma-26B-A4B-it`.**
+
+> **Marketing title:** Infinite-Context  
+> **Technical boundary:** external evidence context, not native unlimited model context.
 
-Technical boundary: external evidence context, not native unlimited model context.
+This repository is a runtime and evidence-governance overlay. It does **not** include or redistribute Google model weights.
 
-## v1.2.5a runtime asset final fix
+The goal is to combine DiffusionGemma's large native working context with NZFC-GRAM's external memory, large-document indexing, scoped retrieval, tombstone filtering, malicious-memory redaction, exact-slot recall, and bounded evidence packs.
 
-This update includes the NZFC root assets required for local runtime initialization:
+---
+
+## TL;DR
 
-- `runtime/`
-- `meta/`
-- `memory_tensors/` when available
-- `archive/` when available
-- `configs/` when available
+```text
+DiffusionGemma native context
++ NZFC-GRAM external evidence memory
++ large-document indexing
++ scoped retrieval
++ tombstone guard
++ bounded evidence packs
+=
+Infinite-Context as an external evidence runtime, not native unlimited context
+```
 
-Runtime-only smoke result:
+Runtime-only validation is already passing from a fresh Hugging Face download.
 
 ```json
 {
@@ -40,32 +56,441 @@ Runtime-only smoke result:
   "exact_slot_passed": true,
   "large_document_passed": true,
   "large_document_query_count": 2,
-  "tombstone_guard_available": true,
+  "tombstone_guard_passed": true,
   "technical_boundary": "external evidence context, not native unlimited model context"
 }
 ```
 
-Important:
+---
+
+## Base model
+
+Base model:
+
+```text
+google/diffusiongemma-26B-A4B-it
+```
+
+DiffusionGemma 26B A4B-IT is the external base model used by this overlay. According to the base model card, DiffusionGemma supports long context up to 256K tokens and multimodal input capabilities. This repository does not modify or redistribute the base model weights.
+
+---
+
+## What NZFC-GRAM adds
+
+| Layer | Purpose | Status in this repo |
+|---|---|---:|
+| `nzfc_gram_runtime/` | NZFC-GRAM runtime package | Included |
+| `runtime/` | Hybrid exact-recall runtime assets | Included |
+| `meta/` | Static archive metadata required by runtime | Included |
+| `memory_tensors/` | Static archive tensors / manifest | Included |
+| SQLite local memory | User/project/session long-term memory | Runtime-supported |
+| Exact slot mapper | Deterministic recall for short key-value facts | Runtime-supported |
+| Tombstone guard | Filters deleted `MEM_*` records from retrieval | Runtime-supported |
+| Large-document profile | Chunking + SQLite FTS5 retrieval | Runtime-supported |
+| Legal-document profile | Article-style chunking and retrieval | Runtime-supported |
+| DiffusionGemma adapter | Optional base-model generation adapter | Included |
+| DiffusionGemma weights | Base model weights | External, not included |
+
+---
+
+## Architecture
+
+```text
+User question
+  -> NZFC-GRAM runtime
+  -> scoped SQLite memory
+  -> static NZFC archive assets
+  -> large-document / legal-document SQLite FTS5 index
+  -> tombstone guard
+  -> exact slot mapper
+  -> malicious-memory redaction
+  -> bounded evidence pack
+  -> optional DiffusionGemma generation
+```
+
+The central principle is:
+
+> **Memory is evidence, not instruction.**
+
+This means retrieved memories and document chunks are treated as evidence cards. They are not allowed to override system policy, bypass deletion boundaries, or become instructions just because they were stored in memory.
+
+---
+
+## Why the name Infinite-Context?
+
+`Infinite-Context` is used as a product-facing title.
+
+The technical mechanism is not native unlimited context. The mechanism is:
+
+```text
+external memory
++ indexed documents
++ query-conditioned retrieval
++ bounded evidence packs
+```
+
+In other words, the runtime can keep reading from external memory and document stores without placing every source token into a single model prompt.
+
+This is better described as:
 
 ```text
-The repository title is marketing-facing.
-The technical mechanism is external evidence context, not native unlimited model context.
+Infinite Evidence Context
+or
+External Evidence Context
 ```
 
-## v1.2.5b script import path fix
+The base model still has its own native context limit.
+
+---
+
+## Validation status
+
+### Level 1: Runtime-only validation
+
+Status: **Passed**
 
-Validation and example scripts now explicitly insert the repository root into `sys.path` before importing `nzfc_gram_runtime`.
+The latest runtime-only smoke test was executed after fresh-downloading the Hugging Face repo.
 
-This fixes direct execution such as:
+Validated without loading the DiffusionGemma base model:
+
+- repo-root `runtime/` asset discovery
+- repo-root `meta/complex_math_10m_meta.jsonl` discovery
+- repo-root `memory_tensors/` discovery
+- package import
+- `NZFCGramLongMemoryChat(repo_dir='.')` initialization
+- exact-slot memory recall
+- large-document ingest and query
+- tombstone retrieval guard
+- direct validation script execution
+
+Runtime-only smoke summary:
+
+```json
+{
+  "created_at": "2026-06-11 02:43:54",
+  "repo_id": "SingularityPrinciple/DiffusionGemma-26B-A4B-it-Infinite-Context",
+  "base_model": "google/diffusiongemma-26B-A4B-it",
+  "runtime_only": true,
+  "model_loaded": false,
+  "repo_root_runtime_exists": true,
+  "repo_root_meta_exists": true,
+  "repo_root_memory_tensors_exists": true,
+  "exact_slot_answer": "PROJECT_CODE_DIFFUSIONGEMMA_SMOKE",
+  "exact_slot_passed": true,
+  "exact_slot_profile": {
+    "version": "v1.2.4b",
+    "description": "Strict deterministic exact slot mapper for short explicit scoped key-value recall questions.",
+    "auto_short_circuit": true,
+    "strict_trigger_gate": true
+  },
+  "large_document_chunk_count": 3,
+  "large_document_query_count": 2,
+  "large_document_method": "fts5_bm25",
+  "large_document_passed": true,
+  "tombstone_guard_profile": {
+    "version": "v1.2.4c",
+    "description": "Filters inactive or tombstoned MEM_* records from memory_store.retrieve results.",
+    "db_path": "/kaggle/working/diffusiongemma_infinite_context_evidence_pack_update/runtime_only_smoke_final/memory.sqlite3",
+    "guarded_method": "memory_store.retrieve"
+  },
+  "tombstone_test": {
+    "available": true,
+    "before_found": true,
+    "after_found": false,
+    "passed": true,
+    "tombstoned": 1
+  },
+  "technical_boundary": "external evidence context, not native unlimited model context",
+  "status": "passed"
+}
+```
+
+### Level 2: Optional DiffusionGemma model-load validation
+
+Status: **Hardware-dependent / not run in the runtime-only validation.**
+
+Run this only on suitable hardware:
+
+```bash
+LOAD_MODEL=1 python examples/optional_diffusiongemma_model_load_check.py
+```
+
+This optional check should validate:
+
+- `AutoProcessor` load
+- DiffusionGemma model load
+- minimal generation call
+- NZFC-GRAM evidence pack generation path
+
+### Level 3: Full serving validation
+
+Recommended future validation:
+
+- high-frequency multi-context memory test
+- large-document / legal-document evidence test
+- multimodal document input test
+- 256K native context stress test
+- latency and VRAM measurements on target hardware
+
+---
+
+## Quick start
+
+Clone and install:
+
+```bash
+git lfs install
+git clone https://huggingface.co/SingularityPrinciple/DiffusionGemma-26B-A4B-it-Infinite-Context
+cd DiffusionGemma-26B-A4B-it-Infinite-Context
+pip install -r requirements.txt
+```
+
+Run runtime-only validation:
 
 ```bash
 python validation/run_runtime_only_smoke.py
+```
+
+Expected result:
+
+```text
+[PASS] runtime-only smoke passed
+```
+
+---
+
+## Examples
+
+### Exact-slot memory recall without loading the base model
+
+```bash
 python examples/high_frequency_multi_context_runtime_only.py
+```
+
+This validates deterministic retrieval of scoped key-value memory facts.
+
+Example stored memory:
+
+```text
+The project high-frequency test code is PROJECT_CODE_RUNTIME_ONLY.
+```
+
+Example question:
+
+```text
+What was the project high-frequency test code? Answer only with the code.
+```
+
+Expected answer:
+
+```text
+PROJECT_CODE_RUNTIME_ONLY
+```
+
+### Large-document retrieval without loading the base model
+
+```bash
 python examples/large_document_runtime_only.py
 ```
 
-Technical boundary:
+This validates chunking, SQLite FTS5 indexing, and query-time document evidence retrieval.
+
+### Optional DiffusionGemma model load
+
+```bash
+LOAD_MODEL=1 python examples/optional_diffusiongemma_model_load_check.py
+```
+
+This requires hardware capable of loading `google/diffusiongemma-26B-A4B-it`.
+
+---
+
+## Python usage
+
+### Runtime-only memory and document evidence
+
+```python
+from nzfc_gram_runtime import NZFCGramLongMemoryChat
+from nzfc_gram_runtime.quality import attach_answer_quality_governor
+from nzfc_gram_runtime.large_document import attach_large_document_memory
+
+bot = NZFCGramLongMemoryChat(
+    repo_dir='.',
+    model_id='google/diffusiongemma-26B-A4B-it',
+    memory_db_path='./memory.sqlite3',
+    load_model=False,
+    require_model=False,
+    preload_static_memory=False,
+)
+
+attach_large_document_memory(bot)
+attach_answer_quality_governor(bot)
+
+bot.remember(
+    'The project high-frequency test code is PROJECT_CODE_DEMO.',
+    user_id='demo_user',
+    project_id='demo_project',
+    session_id='demo_session',
+    scope='project',
+    tags=['project_code'],
+    trust_level=0.95,
+)
+
+res = bot.quality_chat(
+    'What was the project high-frequency test code? Answer only with the code.',
+    user_id='demo_user',
+    project_id='demo_project',
+    session_id='new_session',
+)
+
+print(res['answer'])
+```
+
+### Optional DiffusionGemma adapter
+
+```python
+from nzfc_gram_runtime.diffusiongemma_adapter import attach_diffusiongemma_block_diffusion
+
+attach_diffusiongemma_block_diffusion(
+    bot,
+    model_id='google/diffusiongemma-26B-A4B-it',
+    device_map='auto',
+    dtype='auto',
+)
+```
+
+---
+
+## Safety and governance features
+
+### Scope isolation
+
+Memory records can be scoped by:
+
+- user
+- project
+- session
+
+The goal is to prevent cross-user, cross-project, or cross-session memory leakage.
+
+### Tombstone filtering
+
+Deleted memories should not be active evidence.
+
+The runtime includes tombstone filtering so deleted `MEM_*` records are filtered at the retrieval layer when the guard is available.
+
+### Malicious-memory redaction
+
+Stored memory is treated as untrusted data. Prompt-injection-like memory should be redacted before generation.
+
+### Exact slot mapper
+
+Short exact-recall questions can be answered deterministically from scoped evidence.
+
+Example:
+
+```text
+What was the project high-frequency test code? Answer only with the code.
+```
+
+The exact-slot mapper is intentionally strict. Broad explanatory prompts should continue through the normal evidence and generation pipeline.
+
+### Large-document evidence
+
+Large documents should not be inserted directly into the prompt.
+
+Recommended path:
+
+```text
+ingest -> chunk -> SQLite FTS5 index -> retrieve evidence -> bounded answer
+```
+
+---
+
+## Repository structure
+
+```text
+nzfc_gram_runtime/       Python runtime package
+runtime/                 Hybrid exact-recall runtime assets
+meta/                    Static archive metadata
+memory_tensors/          Static archive tensor manifests and assets
+archive/                 Optional static archive assets when available
+configs/                 Optional runtime configs when available
+docs/                    Architecture and technical boundary notes
+examples/                Runtime-only and optional model-load examples
+validation/              Validation scripts
+validation_evidence/     Saved validation evidence
+release_notes/           Release notes
+```
+
+---
+
+## Troubleshooting
+
+### `ModuleNotFoundError: No module named 'nzfc_gram_runtime'`
+
+Use the latest scripts in this repo. Validation and example scripts insert the repository root into `sys.path` before importing `nzfc_gram_runtime`.
+
+Run from the repository root:
+
+```bash
+python validation/run_runtime_only_smoke.py
+```
+
+### `Cannot find runtime/`
+
+This repo now includes the repo-root `runtime/` assets required by `NZFCGramLongMemoryChat`.
+
+Confirm:
+
+```bash
+ls runtime
+ls meta
+ls memory_tensors
+```
+
+### Base model load fails
+
+`google/diffusiongemma-26B-A4B-it` is hardware-dependent. Runtime-only validation does not load the base model.
+
+---
+
+## What this is not
+
+- Not native infinite context.
+- Not internal infinite model memory.
+- Not a claim that DiffusionGemma itself has unlimited context.
+- Not a zero-hallucination guarantee.
+- Not legal advice.
+- Not a production security certification.
+- Not affiliated with Google.
+- Not a redistribution of Google model weights.
+
+---
+
+## Roadmap
+
+Recommended next steps:
+
+1. Run optional DiffusionGemma 26B model-load validation on suitable hardware.
+2. Add multimodal document input examples.
+3. Add long-context stress tests using the native model context.
+4. Add latency and VRAM tables for target hardware.
+5. Add Docker or one-click notebook setup.
+6. Add REST API / CLI serving layer.
+
+---
+
+## License and terms
+
+NZFC-GRAM runtime surface: CC BY-NC 4.0 unless otherwise specified.
+
+Base model: see the official `google/diffusiongemma-26B-A4B-it` model card and its license/terms.
+
+---
+
+## Short public description
 
 ```text
-external evidence context, not native unlimited model context
+DiffusionGemma-26B-A4B-it-Infinite-Context is an NZFC-GRAM runtime overlay for external evidence context around Google's DiffusionGemma 26B A4B-IT. It includes runtime assets, scoped memory, exact-slot recall, tombstone filtering, large-document retrieval, validation scripts, and runtime-only validation evidence. The title is marketing-facing; the technical mechanism is external evidence context, not native unlimited model context.
 ```

docs/README_DETAILED_v1_2_5b.md

@@ -0,0 +1,496 @@
+---
+license: cc-by-nc-4.0
+base_model: google/diffusiongemma-26B-A4B-it
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- diffusiongemma
+- gemma-4
+- infinite-context
+- external-memory
+- evidence-retrieval
+- long-context
+- large-documents
+- legal-documents
+- ai-memory
+- nzfc-gram
+- runtime-overlay
+- not-native-infinite-context
+---
+
+# DiffusionGemma-26B-A4B-it-Infinite-Context
+
+**NZFC-GRAM runtime overlay for external evidence context around `google/diffusiongemma-26B-A4B-it`.**
+
+> **Marketing title:** Infinite-Context  
+> **Technical boundary:** external evidence context, not native unlimited model context.
+
+This repository is a runtime and evidence-governance overlay. It does **not** include or redistribute Google model weights.
+
+The goal is to combine DiffusionGemma's large native working context with NZFC-GRAM's external memory, large-document indexing, scoped retrieval, tombstone filtering, malicious-memory redaction, exact-slot recall, and bounded evidence packs.
+
+---
+
+## TL;DR
+
+```text
+DiffusionGemma native context
++ NZFC-GRAM external evidence memory
++ large-document indexing
++ scoped retrieval
++ tombstone guard
++ bounded evidence packs
+=
+Infinite-Context as an external evidence runtime, not native unlimited context
+```
+
+Runtime-only validation is already passing from a fresh Hugging Face download.
+
+```json
+{
+  "runtime_only": true,
+  "model_loaded": false,
+  "repo_root_runtime_exists": true,
+  "repo_root_meta_exists": true,
+  "repo_root_memory_tensors_exists": true,
+  "exact_slot_passed": true,
+  "large_document_passed": true,
+  "large_document_query_count": 2,
+  "tombstone_guard_passed": true,
+  "technical_boundary": "external evidence context, not native unlimited model context"
+}
+```
+
+---
+
+## Base model
+
+Base model:
+
+```text
+google/diffusiongemma-26B-A4B-it
+```
+
+DiffusionGemma 26B A4B-IT is the external base model used by this overlay. According to the base model card, DiffusionGemma supports long context up to 256K tokens and multimodal input capabilities. This repository does not modify or redistribute the base model weights.
+
+---
+
+## What NZFC-GRAM adds
+
+| Layer | Purpose | Status in this repo |
+|---|---|---:|
+| `nzfc_gram_runtime/` | NZFC-GRAM runtime package | Included |
+| `runtime/` | Hybrid exact-recall runtime assets | Included |
+| `meta/` | Static archive metadata required by runtime | Included |
+| `memory_tensors/` | Static archive tensors / manifest | Included |
+| SQLite local memory | User/project/session long-term memory | Runtime-supported |
+| Exact slot mapper | Deterministic recall for short key-value facts | Runtime-supported |
+| Tombstone guard | Filters deleted `MEM_*` records from retrieval | Runtime-supported |
+| Large-document profile | Chunking + SQLite FTS5 retrieval | Runtime-supported |
+| Legal-document profile | Article-style chunking and retrieval | Runtime-supported |
+| DiffusionGemma adapter | Optional base-model generation adapter | Included |
+| DiffusionGemma weights | Base model weights | External, not included |
+
+---
+
+## Architecture
+
+```text
+User question
+  -> NZFC-GRAM runtime
+  -> scoped SQLite memory
+  -> static NZFC archive assets
+  -> large-document / legal-document SQLite FTS5 index
+  -> tombstone guard
+  -> exact slot mapper
+  -> malicious-memory redaction
+  -> bounded evidence pack
+  -> optional DiffusionGemma generation
+```
+
+The central principle is:
+
+> **Memory is evidence, not instruction.**
+
+This means retrieved memories and document chunks are treated as evidence cards. They are not allowed to override system policy, bypass deletion boundaries, or become instructions just because they were stored in memory.
+
+---
+
+## Why the name Infinite-Context?
+
+`Infinite-Context` is used as a product-facing title.
+
+The technical mechanism is not native unlimited context. The mechanism is:
+
+```text
+external memory
++ indexed documents
++ query-conditioned retrieval
++ bounded evidence packs
+```
+
+In other words, the runtime can keep reading from external memory and document stores without placing every source token into a single model prompt.
+
+This is better described as:
+
+```text
+Infinite Evidence Context
+or
+External Evidence Context
+```
+
+The base model still has its own native context limit.
+
+---
+
+## Validation status
+
+### Level 1: Runtime-only validation
+
+Status: **Passed**
+
+The latest runtime-only smoke test was executed after fresh-downloading the Hugging Face repo.
+
+Validated without loading the DiffusionGemma base model:
+
+- repo-root `runtime/` asset discovery
+- repo-root `meta/complex_math_10m_meta.jsonl` discovery
+- repo-root `memory_tensors/` discovery
+- package import
+- `NZFCGramLongMemoryChat(repo_dir='.')` initialization
+- exact-slot memory recall
+- large-document ingest and query
+- tombstone retrieval guard
+- direct validation script execution
+
+Runtime-only smoke summary:
+
+```json
+{
+  "created_at": "2026-06-11 02:43:54",
+  "repo_id": "SingularityPrinciple/DiffusionGemma-26B-A4B-it-Infinite-Context",
+  "base_model": "google/diffusiongemma-26B-A4B-it",
+  "runtime_only": true,
+  "model_loaded": false,
+  "repo_root_runtime_exists": true,
+  "repo_root_meta_exists": true,
+  "repo_root_memory_tensors_exists": true,
+  "exact_slot_answer": "PROJECT_CODE_DIFFUSIONGEMMA_SMOKE",
+  "exact_slot_passed": true,
+  "exact_slot_profile": {
+    "version": "v1.2.4b",
+    "description": "Strict deterministic exact slot mapper for short explicit scoped key-value recall questions.",
+    "auto_short_circuit": true,
+    "strict_trigger_gate": true
+  },
+  "large_document_chunk_count": 3,
+  "large_document_query_count": 2,
+  "large_document_method": "fts5_bm25",
+  "large_document_passed": true,
+  "tombstone_guard_profile": {
+    "version": "v1.2.4c",
+    "description": "Filters inactive or tombstoned MEM_* records from memory_store.retrieve results.",
+    "db_path": "/kaggle/working/diffusiongemma_infinite_context_evidence_pack_update/runtime_only_smoke_final/memory.sqlite3",
+    "guarded_method": "memory_store.retrieve"
+  },
+  "tombstone_test": {
+    "available": true,
+    "before_found": true,
+    "after_found": false,
+    "passed": true,
+    "tombstoned": 1
+  },
+  "technical_boundary": "external evidence context, not native unlimited model context",
+  "status": "passed"
+}
+```
+
+### Level 2: Optional DiffusionGemma model-load validation
+
+Status: **Hardware-dependent / not run in the runtime-only validation.**
+
+Run this only on suitable hardware:
+
+```bash
+LOAD_MODEL=1 python examples/optional_diffusiongemma_model_load_check.py
+```
+
+This optional check should validate:
+
+- `AutoProcessor` load
+- DiffusionGemma model load
+- minimal generation call
+- NZFC-GRAM evidence pack generation path
+
+### Level 3: Full serving validation
+
+Recommended future validation:
+
+- high-frequency multi-context memory test
+- large-document / legal-document evidence test
+- multimodal document input test
+- 256K native context stress test
+- latency and VRAM measurements on target hardware
+
+---
+
+## Quick start
+
+Clone and install:
+
+```bash
+git lfs install
+git clone https://huggingface.co/SingularityPrinciple/DiffusionGemma-26B-A4B-it-Infinite-Context
+cd DiffusionGemma-26B-A4B-it-Infinite-Context
+pip install -r requirements.txt
+```
+
+Run runtime-only validation:
+
+```bash
+python validation/run_runtime_only_smoke.py
+```
+
+Expected result:
+
+```text
+[PASS] runtime-only smoke passed
+```
+
+---
+
+## Examples
+
+### Exact-slot memory recall without loading the base model
+
+```bash
+python examples/high_frequency_multi_context_runtime_only.py
+```
+
+This validates deterministic retrieval of scoped key-value memory facts.
+
+Example stored memory:
+
+```text
+The project high-frequency test code is PROJECT_CODE_RUNTIME_ONLY.
+```
+
+Example question:
+
+```text
+What was the project high-frequency test code? Answer only with the code.
+```
+
+Expected answer:
+
+```text
+PROJECT_CODE_RUNTIME_ONLY
+```
+
+### Large-document retrieval without loading the base model
+
+```bash
+python examples/large_document_runtime_only.py
+```
+
+This validates chunking, SQLite FTS5 indexing, and query-time document evidence retrieval.
+
+### Optional DiffusionGemma model load
+
+```bash
+LOAD_MODEL=1 python examples/optional_diffusiongemma_model_load_check.py
+```
+
+This requires hardware capable of loading `google/diffusiongemma-26B-A4B-it`.
+
+---
+
+## Python usage
+
+### Runtime-only memory and document evidence
+
+```python
+from nzfc_gram_runtime import NZFCGramLongMemoryChat
+from nzfc_gram_runtime.quality import attach_answer_quality_governor
+from nzfc_gram_runtime.large_document import attach_large_document_memory
+
+bot = NZFCGramLongMemoryChat(
+    repo_dir='.',
+    model_id='google/diffusiongemma-26B-A4B-it',
+    memory_db_path='./memory.sqlite3',
+    load_model=False,
+    require_model=False,
+    preload_static_memory=False,
+)
+
+attach_large_document_memory(bot)
+attach_answer_quality_governor(bot)
+
+bot.remember(
+    'The project high-frequency test code is PROJECT_CODE_DEMO.',
+    user_id='demo_user',
+    project_id='demo_project',
+    session_id='demo_session',
+    scope='project',
+    tags=['project_code'],
+    trust_level=0.95,
+)
+
+res = bot.quality_chat(
+    'What was the project high-frequency test code? Answer only with the code.',
+    user_id='demo_user',
+    project_id='demo_project',
+    session_id='new_session',
+)
+
+print(res['answer'])
+```
+
+### Optional DiffusionGemma adapter
+
+```python
+from nzfc_gram_runtime.diffusiongemma_adapter import attach_diffusiongemma_block_diffusion
+
+attach_diffusiongemma_block_diffusion(
+    bot,
+    model_id='google/diffusiongemma-26B-A4B-it',
+    device_map='auto',
+    dtype='auto',
+)
+```
+
+---
+
+## Safety and governance features
+
+### Scope isolation
+
+Memory records can be scoped by:
+
+- user
+- project
+- session
+
+The goal is to prevent cross-user, cross-project, or cross-session memory leakage.
+
+### Tombstone filtering
+
+Deleted memories should not be active evidence.
+
+The runtime includes tombstone filtering so deleted `MEM_*` records are filtered at the retrieval layer when the guard is available.
+
+### Malicious-memory redaction
+
+Stored memory is treated as untrusted data. Prompt-injection-like memory should be redacted before generation.
+
+### Exact slot mapper
+
+Short exact-recall questions can be answered deterministically from scoped evidence.
+
+Example:
+
+```text
+What was the project high-frequency test code? Answer only with the code.
+```
+
+The exact-slot mapper is intentionally strict. Broad explanatory prompts should continue through the normal evidence and generation pipeline.
+
+### Large-document evidence
+
+Large documents should not be inserted directly into the prompt.
+
+Recommended path:
+
+```text
+ingest -> chunk -> SQLite FTS5 index -> retrieve evidence -> bounded answer
+```
+
+---
+
+## Repository structure
+
+```text
+nzfc_gram_runtime/       Python runtime package
+runtime/                 Hybrid exact-recall runtime assets
+meta/                    Static archive metadata
+memory_tensors/          Static archive tensor manifests and assets
+archive/                 Optional static archive assets when available
+configs/                 Optional runtime configs when available
+docs/                    Architecture and technical boundary notes
+examples/                Runtime-only and optional model-load examples
+validation/              Validation scripts
+validation_evidence/     Saved validation evidence
+release_notes/           Release notes
+```
+
+---
+
+## Troubleshooting
+
+### `ModuleNotFoundError: No module named 'nzfc_gram_runtime'`
+
+Use the latest scripts in this repo. Validation and example scripts insert the repository root into `sys.path` before importing `nzfc_gram_runtime`.
+
+Run from the repository root:
+
+```bash
+python validation/run_runtime_only_smoke.py
+```
+
+### `Cannot find runtime/`
+
+This repo now includes the repo-root `runtime/` assets required by `NZFCGramLongMemoryChat`.
+
+Confirm:
+
+```bash
+ls runtime
+ls meta
+ls memory_tensors
+```
+
+### Base model load fails
+
+`google/diffusiongemma-26B-A4B-it` is hardware-dependent. Runtime-only validation does not load the base model.
+
+---
+
+## What this is not
+
+- Not native infinite context.
+- Not internal infinite model memory.
+- Not a claim that DiffusionGemma itself has unlimited context.
+- Not a zero-hallucination guarantee.
+- Not legal advice.
+- Not a production security certification.
+- Not affiliated with Google.
+- Not a redistribution of Google model weights.
+
+---
+
+## Roadmap
+
+Recommended next steps:
+
+1. Run optional DiffusionGemma 26B model-load validation on suitable hardware.
+2. Add multimodal document input examples.
+3. Add long-context stress tests using the native model context.
+4. Add latency and VRAM tables for target hardware.
+5. Add Docker or one-click notebook setup.
+6. Add REST API / CLI serving layer.
+
+---
+
+## License and terms
+
+NZFC-GRAM runtime surface: CC BY-NC 4.0 unless otherwise specified.
+
+Base model: see the official `google/diffusiongemma-26B-A4B-it` model card and its license/terms.
+
+---
+
+## Short public description
+
+```text
+DiffusionGemma-26B-A4B-it-Infinite-Context is an NZFC-GRAM runtime overlay for external evidence context around Google's DiffusionGemma 26B A4B-IT. It includes runtime assets, scoped memory, exact-slot recall, tombstone filtering, large-document retrieval, validation scripts, and runtime-only validation evidence. The title is marketing-facing; the technical mechanism is external evidence context, not native unlimited model context.
+```

validation_evidence/diffusiongemma_infinite_context_preview/detailed_readme_update_summary.json

@@ -0,0 +1,38 @@
+{
+  "version": "v1.2.5b-readme-detailed",
+  "repo_id": "SingularityPrinciple/DiffusionGemma-26B-A4B-it-Infinite-Context",
+  "base_model": "google/diffusiongemma-26B-A4B-it",
+  "update_type": "detailed_readme_update",
+  "purpose": "Make the model card more detailed, credible, and technically bounded.",
+  "technical_boundary": "external evidence context, not native unlimited model context",
+  "runtime_only_validation_summary_used": {
+    "runtime_only": true,
+    "model_loaded": false,
+    "repo_root_runtime_exists": true,
+    "repo_root_meta_exists": true,
+    "repo_root_memory_tensors_exists": true,
+    "exact_slot_passed": true,
+    "large_document_passed": true,
+    "large_document_query_count": 2,
+    "tombstone_guard_passed": true,
+    "technical_boundary": "external evidence context, not native unlimited model context"
+  },
+  "readme_sections": [
+    "TL;DR",
+    "Base model",
+    "What NZFC-GRAM adds",
+    "Architecture",
+    "Why Infinite-Context",
+    "Validation status",
+    "Quick start",
+    "Examples",
+    "Python usage",
+    "Safety and governance features",
+    "Repository structure",
+    "Troubleshooting",
+    "What this is not",
+    "Roadmap",
+    "License and terms"
+  ],
+  "created_at": "2026-06-11 04:16:45"
+}