Publish Indexed88 v6.4 135K R2

.gitattributes

@@ -2,3 +2,4 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 *.gguf filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+indexed88-v6.4-135k-r2/selected_88064_135k_v64_40_R2.i32le filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,290 +1,150 @@
 ---
+license: other
+license_name: polyform-small-business-1.0.0
+license_link: LICENSE
 base_model: bottlecapai/ThinkingCap-Qwen3.8-27B
 base_model_relation: quantized
 library_name: ninfer
 pipeline_tag: text-generation
-license: other
-license_name: polyform-small-business-1.0.0
-license_link: LICENSE
 tags:
-- qwen3_8
-- ninfer
-- nvfp4
-- blackwell
-- mtp
-- speculative-decoding
-- text-generation
-- vocabulary-prune
+  - ninfer
+  - thinkingcap
+  - qwen3_8
+  - blackwell
+  - sm120a
+  - quantized
+  - speculative-decoding
+  - mtp
+  - indexed88
+  - text-generation
 ---
 
-# ThinkingCap-Qwen3.8-27B — NInfer Blackwell V2
-
-Production-oriented NInfer export of
-`bottlecapai/ThinkingCap-Qwen3.8-27B`, tuned and validated for NVIDIA Blackwell.
-
-**V1 status:** frozen and production validated.
-
-The final artifact combines:
-
-- compact **147,590-token public vocabulary**
-- **147,712 physical vocabulary rows**
-- 131,072-row indexed proposal head
-- native one-layer ThinkingCap MTP
-- NVFP4 target quantization
-- baked activation-divisor tuning
-- NVFP4 KV cache validation in the production benchmark path
-- NInfer upstream GDN/runtime changes
-- production prefill chunk **2048**
-
-No runtime DX override environment variables are required for this artifact.
-
-[☕ Support My Work](https://buymeacoffee.com/Schestex)
-
-I'm an independent AI developer working on model optimization, quantization, fine-tuning, and high-performance inference.
-
-If you find my models or research useful, consider supporting my work. Every contribution helps fund GPU experiments, new model releases, and further open-source AI development.
-
-All support is voluntary and greatly appreciated!
+# ThinkingCap Qwen3.8-27B — NInfer releases
 
-## Primary artifact
+NInfer-format conversions of [bottlecapai/ThinkingCap-Qwen3.8-27B](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-27B), based on [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B), for NVIDIA Blackwell inference.
 
-`combined-147590/thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer`
+**These artifacts are native `.ninfer` files, not Safetensors, GGUF, or Transformers checkpoints.** They require a compatible [NInfer](https://github.com/Xtravaganz/ninfer) runtime and are not intended for direct loading with `transformers.AutoModel` or vLLM.
 
-| Field | Value |
-|---|---|
-| File size | `16308912900 bytes` / `15.19 GiB` |
-| SHA256 | `d030303f73b658399810a1be097c3b682610c47df8ea1cd24eb0c1eb53255b27` |
-| Conversion sidecar | `combined-147590/thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer.conversion.json` |
-| Public vocabulary | `147,590` |
-| Physical vocabulary | `147,712` |
-| Proposal rows | `131,072` |
-| Components | `text, mtp` |
-| Conversion device | CPU |
-| Converter rows/chunk | `512` |
+## Releases
 
-The final V1 artifact was rebuilt directly from the BF16 source checkpoint.
-Existing `.ninfer` artifacts were **not** requantized.
+| Release | Public vocabulary | Physical rows | MTP proposal rows | Status |
+| --- | ---: | ---: | ---: | --- |
+| **Indexed88 v6.4 / 135K / R2** | **135,000** | **135,168** | **88,064** | Locally deployed; tagged container reports `canary` |
+| **Original V1 / 147K** | 147,590 | 147,712 | 131,072 | Previously published, separately versioned |
 
-## Frozen V1 quantization / activation profile
+**The 135K and 147K releases are different artifacts. Do not mix their tokenizers, proposal rankings, runtime settings, or conversion sidecars.** The original V1 remains in [`combined-147590/`](./combined-147590/).
 
-| Family | Activation input divisor |
-|---|---:|
-| D48 — MLP down | **3.5** |
-| O_GDN — GDN output | **1.0** |
-| O_ATTN — attention output | **6.0** |
-| I_GDN — GDN input parent | **1.0** |
-| I_ATTN — attention input parent | **1.0** |
-| G64 — MLP gate/up | **1.0** |
-| MTP GateUp | **15.40** |
+## Indexed88 v6.4 — 135K / R2
 
-The selected layer families remain the previously frozen:
+This release uses one physical Q8-backed MTP output head and evaluates only 88,064 selected vocabulary rows for speculative proposals. It is **not** a second output head or a second complete head projection.
 
-- **D48**
-- **O44**
-- **I53**
-- **G64**
+### Release components
 
-Only the activation divisor calibration was re-optimized for the new upstream
-runtime where required.
+| Component | Description |
+| --- | --- |
+| Model artifact | `indexed88-v6.4-135k-r2/thinkingcap-135000-q8-repack.ninfer` |
+| Selected-row IDs | `indexed88-v6.4-135k-r2/selected_88064_135k_v64_40_R2.i32le` |
+| Chat template | `indexed88-v6.4-135k-r2/qwen3_8_sharp.jinja` |
+| Checksums | `indexed88-v6.4-135k-r2/SHA256SUMS` |
+| Release metadata | `indexed88-v6.4-135k-r2/RELEASE.json` |
 
-## Runtime recommendation
+The public model filename above is a **distribution name** for the local artifact `thinkingcap-135000-q8-repack-EXPERIMENTAL.ninfer`. Renaming/copying it does not change the model bytes. Verify its SHA-256 before publication and record the checksum in `SHA256SUMS`; a public model SHA-256 has not been asserted here.
 
-Validated production settings:
+Known source facts:
 
-```text
-kv-dtype       = nvfp4
-spec           = mtp
-draft-tokens   = 5
-lm-head-draft  = enabled
-prefill-chunk  = 2048
-```
+| Item | Value |
+| --- | --- |
+| Local model artifact size | **15,820,439,556 bytes** (approximately 14.73 GiB) |
+| Model vocabulary | 135,000 public / 135,168 physical rows |
+| Indexed proposal selection | 88,064 original token IDs |
+| Selection file SHA-256 | `b578828c0b517ba47abe90a130fda7cde5a56d94add1afeac7623e7c8f6234b4` |
+| Sharp chat-template SHA-256 | `cdff39fb26b60dc90faa292e726655c6b21f62db497846e02e4c4bbab942a84a` |
+| Local deployment image tag | `thinkingcap-v1:indexed88-v6.4-135k-r2` |
+| Local deployment image label | `org.thinkingcap.release.status=canary` |
 
-The production binary was built for Blackwell CUDA architecture `120a`,
-Release mode, using CUDA 13.1.2.
+**Important:** The Docker tag is a local runtime/deployment identifier, not a Hugging Face model filename and not evidence of a published OCI image. This repository distributes model assets; a container image must be distributed separately through an OCI registry if desired.
 
-Validated local production image:
+### Requirements
 
-```text
-ninfer-upstream-combined-147k:v1
-```
+- A NInfer build that includes **135K Indexed88 v6.4 direct Q8 MTP support**. A generic upstream NInfer binary is not guaranteed to load or run this release correctly.
+- Linux with an NVIDIA Blackwell GPU supported by that build (tested on an RTX PRO 4000 Blackwell with 24 GB VRAM, CUDA architecture `sm_120a`).
+- Compatible CUDA runtime/driver and sufficient device memory. The referenced local builds used CUDA 13.3, `sm_120a`, Release mode.
+- The exact 135K ranking and chat template supplied with this release.
 
-The corresponding public source is available in:
+### Download
 
-```text
-https://github.com/Xtravaganz/ninfer
-```
+After the release directory has been uploaded:
 
-Source tag:
+```bash
+hf download Schestex/ThinkingCap-Qwen3.8-27B-NInfer \
+  --include 'indexed88-v6.4-135k-r2/*' \
+  --local-dir ./thinkingcap-ninfer
 
-```text
-thinkingcap-upstream-v1-2026-10-05
+cd thinkingcap-ninfer
+(cd indexed88-v6.4-135k-r2 && sha256sum --check SHA256SUMS)
 ```
 
-## V1 source provenance
-
-| Item | Commit |
-|---|---|
-| Published `master` | `ba8c4e726834c5e00cf5f68255ea6430c66e5319` |
-| Exact tested V1 source tag | `883d0e434ecb54cb6d6a9274c6a1a680988fab9d` |
-| Compact-vocab/Q8 support | `b8685532` |
-| Runtime NVFP4 divisor hooks | `883d0e43` |
-
-The V1 production binary was proven byte-identical to the binary built from the
-validated worktree before publication.
-
-### Production binary hashes
-
-```text
-ninfer
-ee41f5be3a4f6b77148420b1bda8cf8fe12479ad8de9be5f9bcc63539557e7e3
-
-ninfer-serve
-2137f5c7d3d54343e5769735ca5103585b53d872ffb8422d3758b45bdf75058d
+### Example: native NInfer server
+
+This command assumes you have **built a compatible 135K Indexed88 v6.4 NInfer server**. On a host with multiple GPUs, `--device 0` refers to the first GPU visible to the process.
+
+```bash
+export CUDA_VISIBLE_DEVICES=0  # change to the intended physical GPU index if needed
+export NINFER_MTP_INDEXED_SHADOW=1
+export NINFER_MTP_INDEXED_MODE=indexed96
+export NINFER_MTP_INDEXED_RANKING="$PWD/indexed88-v6.4-135k-r2/selected_88064_135k_v64_40_R2.i32le"
+
+./ninfer-serve \
+  "$PWD/indexed88-v6.4-135k-r2/thinkingcap-135000-q8-repack.ninfer" \
+  --host 127.0.0.1 --port 8080 \
+  --model-id thinkingcap-135k-indexed88 \
+  --device 0 \
+  --spec mtp --draft-tokens 5 \
+  --kv-dtype nvfp4 \
+  --max-context 8192 --kv-capacity 8192 \
+  --max-concurrency 1 --prefill-chunk 512 \
+  --preserve-thinking \
+  --chat-template "$PWD/indexed88-v6.4-135k-r2/qwen3_8_sharp.jinja"
 ```
 
-## Baked V1 equivalence
+The historical environment variable `NINFER_MTP_INDEXED_SHADOW=1` enables the Indexed-MTP configuration. **`NINFER_MTP_INDEXED_MODE=indexed96` selects the direct path** in the tested runtime, notwithstanding the older internal name. The runtime's `indexed96` enum uses 88,064 selected rows for this release. In direct mode the selected Q8 proposal is authoritative and the full MTP proposal projection is skipped. No external Q5/Q6 head is required.
 
-The final CPU-built artifact was tested **without any runtime DX override
-environment variables**.
+Do not set `NINFER_MTP_INDEXED_MODE=shadow` if you want the one-projection Indexed88 direct configuration.
 
-Its speculative acceptance matched the tuned runtime model exactly:
+### Validation and performance scope
 
-| Workload | Runtime-tuned | Final baked V1 | Delta |
-|---|---:|---:|---:|
-| Mixed 8k | 0.7509293680 | **0.7509293680** | 0 |
-| Mixed 32k | 0.6134185304 | **0.6134185304** | 0 |
-| Mixed 48k | 0.5483870968 | **0.5483870968** | 0 |
-| Mixed 110k | 0.5864197531 | **0.5864197531** | 0 |
+The 135K Indexed88 configuration was evaluated on **one RTX PRO 4000 Blackwell GPU (24 GB)** using native NInfer builds, `--spec mtp --draft-tokens 5`, NVFP4 KV cache, `temperature=0`, and three consecutive requests capped at 3,500 output tokens each. Each kernel variant used the same model, ranking, and template.
 
-**Baked equivalence: PASS**
+| Indexed88 Q8 kernel tested | Turn 1 | Turn 2 | Turn 3 | Acceptance across the test |
+| --- | ---: | ---: | ---: | ---: |
+| R0 reference | 95.34 tok/s | 94.75 tok/s | 90.44 tok/s | 55.33% |
+| Experimental R2 (row-ID hoisting) | 95.19 tok/s | 94.66 tok/s | 90.42 tok/s | 55.33% |
+| Experimental R3 (hoisting + occupancy) | 95.30 tok/s | 94.80 tok/s | 90.43 tok/s | 55.33% |
 
-## Old production vs V1
+All three experimental builds produced **identical complete response hashes for each corresponding turn**, and matched draft/acceptance counts. The R2/R3 optimizations were **experimental isolated builds, not changes to the local production image**. These results are not a standardized model-quality benchmark or a guarantee of performance on other hardware, prompts, contexts, or decoding settings. The model and the actual published image/build should be matched using separately recorded hashes before making reproducibility claims.
 
-End-to-end comparison on the same physical GPU1.
+### Limitations
 
-Old production used the previous runtime with prefill chunk 1024.
-V1 uses the new upstream runtime, re-optimized D48 divisor, and prefill chunk 2048.
+- The selected 88,064-row proposal vocabulary is a performance/coverage trade-off; it is **not** a reduction of the public tokenizer to 88,064 IDs. The model's public vocabulary is 135,000.
+- Generated content can be inaccurate, unsafe, or unsuitable for unsupervised code/agent execution. Validate outputs before use.
+- This release is NInfer-runtime-specific, not a drop-in HF Transformers distribution.
+- CUDA Graph and runtime behavior depend on the exact NInfer build. The tested direct `indexed96` path supports CUDA Graph integration; other versions may differ.
+- Release status is still marked `canary` in the known local image metadata; do not interpret this page as a universal production-readiness or support guarantee.
 
-| Context | Acceptance old | Acceptance V1 | Delta | Decode old | Decode V1 | Decode gain | Prefill old | Prefill V1 | Prefill gain |
-|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|
-| Mixed 8k | 54.02% | **75.09%** | **+21.07 pp** | 82.15 t/s | **116.99 t/s** | **+42.41%** | 3390.4 t/s | **3664.2 t/s** | **+8.07%** |
-| Mixed 32k | 40.91% | **61.34%** | **+20.43 pp** | 64.00 t/s | **93.16 t/s** | **+45.56%** | 2866.7 t/s | **3027.2 t/s** | **+5.60%** |
-| Mixed 48k | **55.33%** | 54.84% | -0.49 pp | 75.78 t/s | **83.33 t/s** | **+9.96%** | 2551.6 t/s | **2707.2 t/s** | **+6.10%** |
-| Mixed 110k | 54.52% | **58.64%** | **+4.12 pp** | 67.55 t/s | **76.57 t/s** | **+13.35%** | 1798.4 t/s | **1919.2 t/s** | **+6.72%** |
+## Provenance and attribution
 
-This is an **end-to-end production-stack comparison**, not an isolated
-measurement of one kernel or one quantization parameter.
+- **Base model:** [Qwen/Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B).
+- **ThinkingCap fine-tune:** [bottlecapai/ThinkingCap-Qwen3.8-27B](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-27B).
+- **NInfer:** [Xtravaganz/ninfer](https://github.com/Xtravaganz/ninfer) (the repository linked by the previous release; a matching 135K Indexed88 runtime commit/tag has not yet been publicly verified here).
 
-## Why prefill chunk 2048
+This is an independently packaged NInfer conversion and runtime configuration of the upstream ThinkingCap model; it should not be presented as a new pretraining or fine-tuning run.
 
-On the final V1 runtime, chunk 2048 also beat chunk 1024 directly:
-
-| Context | Acc. 1024 | Acc. 2048 | Delta | Decode gain | Prefill gain |
-|---|---:|---:|---:|---:|---:|
-| Mixed 32k | 55.29% | **61.34%** | **+6.05 pp** | **+6.28%** | **+4.89%** |
-| Mixed 110k | 43.53% | **58.64%** | **+15.11 pp** | **+22.45%** | **+4.79%** |
-
-For this V1, `prefill-chunk=2048` is therefore part of the validated
-production configuration.
-
-## Compact vocabulary
-
-The source tokenizer exposes 248,077 public tokens with a 248,320-row aligned
-NInfer embedding/output head.
-
-V1 uses the validated combined Script + CJK cut:
-
-```text
-Original public vocabulary     248,077
-V1 public vocabulary           147,590
-V1 physical vocabulary         147,712
-Removed                        100,487
-Reduction                       40.51%
-Padding rows                       122
-```
-
-The compact vocabulary was produced conservatively using:
-
-- Unicode/script classification
-- workload protection
-- BPE dependency closure
-- special/added-token protection
-- tokenizer parity checks
-- teacher-output audits
-- runtime A/B validation
-
-The MTP proposal vocabulary remains **131,072 rows** and is independent from
-the full target vocabulary cut.
-
-## Benchmark corpus
-
-The V1 runtime tuning used mixed-context benchmark corpora intended to better
-match real coding/agent workloads than pure text-only or code-only streams.
-
-Primary validation points:
-
-- 8,192-token mixed context
-- 32,768-token mixed context
-- 49,152-token mixed context
-- 112,640-token mixed context
-
-The 112,640-token test is intended to approximate the long-context
-summary/compaction regime.
-
-These benchmark-corpus acceptance values should not be interpreted as universal
-chat or coding acceptance rates.
-
-## Reproducibility
-
-Final model:
-
-```text
-thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer
-SHA256: d030303f73b658399810a1be097c3b682610c47df8ea1cd24eb0c1eb53255b27
-```
-
-Conversion sidecar SHA256:
-
-```text
-62eff698b11f1d393b518cf62937f918dc131e6893f65ec9cb57d5c5d8a9843b
-```
-
-Exact V1 source:
-
-```text
-git clone https://github.com/Xtravaganz/ninfer.git
-cd ninfer
-git checkout thinkingcap-upstream-v1-2026-10-05
-```
-
-The V1 tag is intentionally kept on the exact tested source commit, while
-`master` also contains the repository's previous origin history.
-
-
-## Repository layout
-
-```text
-combined-147590/
-  thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer
-  thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer.conversion.json
-  thinkingcap-v1-upstream-d48dx3p5-oattndx6-ogdndx1-igdndx1-iattndx1-g64dx1-mtpgateupdx15p40-combined-147590.ninfer.sha256
-
-provenance/
-  V1-PRODUCTION.md
+## License
 
-benchmarks/
-  V1-RESULTS.md
+ThinkingCap is licensed under **PolyForm Small Business License 1.0.0**, with an additional personal, noncommercial use permission from BottleCap AI. The underlying Qwen materials carry **Apache-2.0** requirements. See the original [ThinkingCap LICENSE](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-27B/blob/main/LICENSE) and [NOTICE](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.8-27B/blob/main/NOTICE).
 
-MODEL_FILE.txt
-FACTS.json
-PROVENANCE.md
-SHA256SUMS
-README.md
-```
+Keep the upstream license texts, copyright notices, and attribution files when redistributing these derived weights. This release does not grant broader commercial rights than the upstream license.
 
-Older RC/experimental artifacts are retained for historical comparison.
-The artifact listed in `MODEL_FILE.txt` is the current V1 production model.
-
-## License
+---
 
-See `LICENSE`.
+For historical 147K V1 artifacts and results, retain the existing [`combined-147590/`](./combined-147590/), `provenance/`, and `benchmarks/` directories until older references have been verified and archived cleanly.

indexed88-v6.4-135k-r2/RELEASE.json

@@ -0,0 +1,26 @@
+{
+  "release": "indexed88-v6.4-135k-r2",
+  "model_repo": "Schestex/ThinkingCap-Qwen3.8-27B-NInfer",
+  "created_at_utc": "2026-11-01T12:43:22.651143+00:00",
+  "model_file": "thinkingcap-135000-q8-repack.ninfer",
+  "source_model_filename": "thinkingcap-135000-q8-repack-EXPERIMENTAL.ninfer",
+  "model_size_bytes": 15820439556,
+  "selected_rows": 88064,
+  "public_vocab": 135000,
+  "physical_vocab_rows": 135168,
+  "checksums_sha256": {
+    "thinkingcap-135000-q8-repack.ninfer": "df1ab1bfc8dc4ac119b3c064993423f3e4f351796db43468f4180b2e20ab7ad6",
+    "selected_88064_135k_v64_40_R2.i32le": "b578828c0b517ba47abe90a130fda7cde5a56d94add1afeac7623e7c8f6234b4",
+    "qwen3_8_sharp.jinja": "cdff39fb26b60dc90faa292e726655c6b21f62db497846e02e4c4bbab942a84a"
+  },
+  "mtpspec_draft_window": 5,
+  "selected_row_mode": "indexed96",
+  "proposal_head": "one direct Q8 projection",
+  "local_docker_image_tag": "thinkingcap-v1:indexed88-v6.4-135k-r2",
+  "local_docker_image_status_label": "canary",
+  "local_docker_image_id": "sha256:32a4388fa74a174d42de9a39ea6e93d3e830f95c271efb4931408945abea8021",
+  "runtime_source_commit": null,
+  "artifact_conversion_provenance": null,
+  "oci_image_registry_url": null,
+  "note": "null fields must be resolved or clearly documented before claiming full reproducibility"
+}

indexed88-v6.4-135k-r2/SHA256SUMS

@@ -0,0 +1,3 @@
+df1ab1bfc8dc4ac119b3c064993423f3e4f351796db43468f4180b2e20ab7ad6  thinkingcap-135000-q8-repack.ninfer
+b578828c0b517ba47abe90a130fda7cde5a56d94add1afeac7623e7c8f6234b4  selected_88064_135k_v64_40_R2.i32le
+cdff39fb26b60dc90faa292e726655c6b21f62db497846e02e4c4bbab942a84a  qwen3_8_sharp.jinja

indexed88-v6.4-135k-r2/qwen3_8_sharp.jinja

@@ -0,0 +1,488 @@
+{%- set template_version = "qwen3.8-froggeric-v22.5.0" %}
+{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
+{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}
+{%- if preserve_reasoning is defined and preserve_reasoning is not none %}
+    {%- set _preserve_thinking = preserve_reasoning %}
+{%- elif preserve_thinking is defined and preserve_thinking is not none %}
+    {%- set _preserve_thinking = preserve_thinking %}
+{%- else %}
+    {%- set _preserve_thinking = true %}
+{%- endif %}
+{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}
+{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}
+{%- set _default_reasoning_effort = 'medium' %}
+{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}
+{%- set _effort_raw = (reasoning_effort | string | lower) if reasoning_effort is defined and reasoning_effort is not none else _default_reasoning_effort %}
+{%- set _initial_thinking = enable_thinking %}
+{%- if _effort_raw in ('none', 'off') %}
+    {%- set _initial_thinking = false %}
+    {%- set _initial_effort = 'medium' %}
+{%- elif _effort_raw in ('minimal', 'low') %}
+    {%- set _initial_effort = 'low' %}
+{%- elif _effort_raw in ('high', 'xhigh', 'max', 'ultracode', 'extreme') %}
+    {%- set _initial_effort = 'xhigh' %}
+{%- else %}
+    {%- set _initial_effort = 'medium' %}
+{%- endif %}
+{%- set ns_state = namespace(thinking=_initial_thinking, effort=_initial_effort) %}
+{%- if auto_disable_thinking_with_tools and _has_tools %}
+    {%- set ns_state.thinking = false %}
+{%- endif %}
+{%- for msg in messages %}
+    {%- if msg.role == 'system' or msg.role == 'developer' or msg.role == 'user' %}
+        {%- if msg.content is string %}
+            {%- if '<|think_off|>' in msg.content %}
+                {%- set ns_state.thinking = false %}
+            {%- elif '<|think_on|>' in msg.content %}
+                {%- set ns_state.thinking = true %}
+            {%- elif '<|think_xhigh|>' in msg.content or '<|think_high|>' in msg.content or '<|think_ultracode|>' in msg.content or '<|think_extreme|>' in msg.content or '<|think_max|>' in msg.content %}
+                {%- set ns_state.thinking = true %}
+                {%- set ns_state.effort = 'xhigh' %}
+            {%- elif '<|think_low|>' in msg.content or '<|think_minimal|>' in msg.content %}
+                {%- set ns_state.thinking = true %}
+                {%- set ns_state.effort = 'low' %}
+            {%- elif '<|think_medium|>' in msg.content %}
+                {%- set ns_state.thinking = true %}
+                {%- set ns_state.effort = 'medium' %}
+            {%- endif %}
+        {%- elif msg.content is iterable and msg.content is not mapping %}
+            {%- for item in msg.content %}
+                {%- if item is string %}
+                    {%- set _item_text = item %}
+                {%- elif item is mapping and 'text' in item and item.text is string %}
+                    {%- set _item_text = item.text %}
+                {%- else %}
+                    {%- set _item_text = '' %}
+                {%- endif %}
+                {%- if _item_text %}
+                    {%- if '<|think_off|>' in _item_text %}
+                        {%- set ns_state.thinking = false %}
+                    {%- elif '<|think_on|>' in _item_text %}
+                        {%- set ns_state.thinking = true %}
+                    {%- elif '<|think_xhigh|>' in _item_text or '<|think_high|>' in _item_text or '<|think_ultracode|>' in _item_text or '<|think_extreme|>' in _item_text or '<|think_max|>' in _item_text %}
+                        {%- set ns_state.thinking = true %}
+                        {%- set ns_state.effort = 'xhigh' %}
+                    {%- elif '<|think_low|>' in _item_text or '<|think_minimal|>' in _item_text %}
+                        {%- set ns_state.thinking = true %}
+                        {%- set ns_state.effort = 'low' %}
+                    {%- elif '<|think_medium|>' in _item_text %}
+                        {%- set ns_state.thinking = true %}
+                        {%- set ns_state.effort = 'medium' %}
+                    {%- endif %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- set reasoning_instructions = '' %}
+{%- if ns_state.thinking %}
+    {%- if ns_state.effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif ns_state.effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if item is mapping %}
+                {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain images.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set image_count.value = image_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+                {%- elif item.type == 'video' or 'video' in item or 'video_url' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain videos.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set video_count.value = video_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Video ' ~ video_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+                {%- elif 'text' in item %}
+                    {{- item.text }}
+                {%- else %}
+                    {{- raise_exception('Unexpected item type in content.') }}
+                {%- endif %}
+            {%- else %}
+                {{- item | string }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set head = namespace(count=0, seen_non_system=false) %}
+{%- for message in messages %}
+    {%- set _is_sys = (message.role == 'system' or message.role == 'developer') %}
+    {%- if _is_sys and not head.seen_non_system %}
+        {%- set head.count = head.count + 1 %}
+    {%- else %}
+        {%- set head.seen_non_system = true %}
+    {%- endif %}
+{%- endfor %}
+{%- set sys_state = namespace(content='') %}
+{%- for message in messages[:head.count] %}
+    {%- set _part = render_content(message.content, false, true) | trim %}
+    {%- if '<|think_off|>' in _part %}{%- set _part = _part.split('<|think_off|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_on|>' in _part %}{%- set _part = _part.split('<|think_on|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_xhigh|>' in _part %}{%- set _part = _part.split('<|think_xhigh|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_high|>' in _part %}{%- set _part = _part.split('<|think_high|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_ultracode|>' in _part %}{%- set _part = _part.split('<|think_ultracode|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_extreme|>' in _part %}{%- set _part = _part.split('<|think_extreme|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_max|>' in _part %}{%- set _part = _part.split('<|think_max|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_medium|>' in _part %}{%- set _part = _part.split('<|think_medium|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_low|>' in _part %}{%- set _part = _part.split('<|think_low|>') | join('') | trim %}{%- endif %}
+    {%- if '<|think_minimal|>' in _part %}{%- set _part = _part.split('<|think_minimal|>') | join('') | trim %}{%- endif %}
+    {%- if _part %}
+        {%- if sys_state.content %}
+            {%- set sys_state.content = sys_state.content ~ '\n\n' ~ _part %}
+        {%- else %}
+            {%- set sys_state.content = _part %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- set _sc = sys_state.content %}
+{%- set _msgs = messages[head.count:] %}
+{%- if ns_state.thinking %}
+    {%- set _terse_lead = 'Answer directly, after thinking. Lead with the answer, then only what it needs to be correct and usable.' %}
+{%- else %}
+    {%- set _terse_lead = 'Answer directly and concisely. Give the answer with only what it needs to be correct and usable.' %}
+{%- endif %}
+{%- set _terse_core %}
+Never: open with preamble or pleasantries; restate the question; add filler transitions; hedge with niceties; or repeat a point you've already made.
+Always: keep essential steps, caveats, uncertainties, and specifics — never drop correctness or a needed warning for brevity. Keep the final answer lean. Use the least structure that conveys it (plain prose when short; lists or code only when they earn their place). If genuinely uncertain, say so and explain why — never omit uncertainty for the sake of brevity.
+If a user request is genuinely ambiguous, ask a sharp question, don't guess.
+{%- endset %}
+{%- set _terse = _terse_lead ~ '\n' ~ (_terse_core | trim) %}
+{#- `terse` chat-template kwarg: default true, so behaviour is unchanged unless a caller opts out.
+    Pass {"terse": false} via chat_template_kwargs to serve the model with only its own system
+    prompt -- useful for A/B-ing the terseness effect, or when a downstream prompt conflicts. #}
+{%- set _terse_on = terse if terse is defined else true %}
+{%- if _terse_on %}
+    {%- if not _sc %}
+        {%- set _sc = _terse | trim %}
+    {%- else %}
+        {%- set _sc = (_sc | trim) ~ '\n\n' ~ (_terse | trim) %}
+    {%- endif %}
+{%- endif %}
+{#- Some runtimes (LM Studio's MLX backend) have no native tool-call parser and prepend their own
+    protocol into the system content. Emitting ours as well gives the model two contradictory tool
+    protocols and it follows one at random. Detect that marker and stand down; the
+    `suppress_tool_instructions` kwarg overrides either way where a runtime can pass template kwargs. #}
+{%- set _runtime_tool_protocol = (_sc is defined and _sc and '[TOOL_REQUEST]' in _sc) %}
+{%- set _suppress_tools = suppress_tool_instructions if suppress_tool_instructions is defined else _runtime_tool_protocol %}
+{%- if _has_tools and not _suppress_tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- '# Tools\n\nYou have access to the following functions:\n\n<tools>' }}
+    {%- for tool in tools %}
+        {{- '\n' }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>' }}
+    {%- if _tool_format == 'json' %}
+        {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n' }}
+        {%- if ns_state.thinking %}
+            {{- '<think>\nBrief explanation of tool call\n</think>\n' }}
+        {%- endif %}
+        {{- '<tool_call>\n{"name": "example_function_name", "arguments": {"example_parameter_1": "value_1", "example_parameter_2": "This is the value for the second parameter"}}\n</tool_call>\n\n<IMPORTANT>\nReminder:\n' }}
+        {%- if ns_state.thinking %}
+            {{- '- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.\n- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.\n' }}
+        {%- endif %}
+        {{- '- Function calls MUST follow the specified format: a single JSON object with "name" and "arguments" keys inside <tool_call></tool_call> XML tags.\n' }}
+        {%- if ns_state.thinking %}
+            {{- '- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.\n' }}
+        {%- else %}
+            {{- '- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY, with NO conversational text before it.\n' }}
+        {%- endif %}
+        {{- '- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.\n- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.\n- If you have all necessary data, provide your final answer directly to the user without any tool call.\n</IMPORTANT>' }}
+    {%- else %}
+        {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n' }}
+        {%- if ns_state.thinking %}
+            {{- '<think>\nBrief explanation of tool call\n</think>\n' }}
+        {%- endif %}
+        {{- '<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n' }}
+        {%- if ns_state.thinking %}
+            {{- '- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.\n- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.\n' }}
+        {%- endif %}
+        {{- '- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.\n' }}
+        {%- if ns_state.thinking %}
+            {{- '- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.\n' }}
+        {%- else %}
+            {{- '- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY, with NO conversational text before it.\n' }}
+        {%- endif %}
+        {{- '- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.\n- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.\n- If you have all necessary data, provide your final answer directly to the user without any tool call.\n</IMPORTANT>' }}
+    {%- endif %}
+    {%- if _sc %}
+        {{- '\n\n' + _sc }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if _sc %}
+        {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + _sc + '<|im_end|>\n' }}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set _last_idx = _msgs | length - 1 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}
+{%- for message in _msgs[::-1] %}
+    {%- set index = (_msgs | length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == 'user' %}
+        {%- set _rc = render_content(message.content, false) | trim %}
+        {%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {%- if _last_idx > 50 %}
+        {%- set ns.last_query_index = _last_idx %}
+    {%- else %}
+        {%- set ns.last_query_index = 0 %}
+    {%- endif %}
+{%- endif %}
+{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}
+{%- for message in _msgs %}
+    {%- set is_system = (message.role == "system" or message.role == "developer") %}
+    {%- set content = render_content(message.content, true, is_system) | trim %}
+    {%- if is_system or message.role == 'user' %}
+        {%- if '<|think_off|>' in content %}{%- set content = content.split('<|think_off|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_on|>' in content %}{%- set content = content.split('<|think_on|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_xhigh|>' in content %}{%- set content = content.split('<|think_xhigh|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_high|>' in content %}{%- set content = content.split('<|think_high|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_ultracode|>' in content %}{%- set content = content.split('<|think_ultracode|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_extreme|>' in content %}{%- set content = content.split('<|think_extreme|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_max|>' in content %}{%- set content = content.split('<|think_max|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_medium|>' in content %}{%- set content = content.split('<|think_medium|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_low|>' in content %}{%- set content = content.split('<|think_low|>') | join('') | trim %}{%- endif %}
+        {%- if '<|think_minimal|>' in content %}{%- set content = content.split('<|think_minimal|>') | join('') | trim %}{%- endif %}
+    {%- endif %}
+    {%- if is_system %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'user' %}
+        {%- set ns2.consecutive_failures = 0 %}
+        {{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {%- set reasoning_content = '' %}
+        {%- set _explicit_reasoning = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- if message.reasoning_content is string %}
+                {%- set _explicit_reasoning = message.reasoning_content %}
+            {%- else %}
+                {%- set _explicit_reasoning = message.reasoning_content | string %}
+            {%- endif %}
+        {%- elif message.thinking is defined and message.thinking is not none %}
+            {%- if message.thinking is string %}
+                {%- set _explicit_reasoning = message.thinking %}
+            {%- else %}
+                {%- set _explicit_reasoning = message.thinking | string %}
+            {%- endif %}
+        {%- elif message.reasoning is defined and message.reasoning is not none %}
+            {%- if message.reasoning is string %}
+                {%- set _explicit_reasoning = message.reasoning %}
+            {%- else %}
+                {%- set _explicit_reasoning = message.reasoning | string %}
+            {%- endif %}
+        {%- endif %}
+        {%- if _explicit_reasoning %}
+            {%- set _lead_end = '' %}
+            {%- if content.startswith('<think>') and '</think>' in content %}
+                {%- set _lead_end = '</think>' %}
+            {%- elif content.startswith('<thinking>') and '</thinking>' in content %}
+                {%- set _lead_end = '</thinking>' %}
+            {%- elif content.startswith('</think>') %}
+                {%- set _lead_end = '</think>' %}
+            {%- elif content.startswith('</thinking>') %}
+                {%- set _lead_end = '</thinking>' %}
+            {%- endif %}
+            {%- if _lead_end %}
+                {%- set content = content.split(_lead_end)[-1].lstrip('\n') %}
+            {%- endif %}
+            {%- set reasoning_content = _explicit_reasoning %}
+        {%- else %}
+            {%- set _think_end = '' %}
+            {%- if content.startswith('</think>') %}
+                {%- set _think_end = '</think>' %}
+            {%- elif content.startswith('</thinking>') %}
+                {%- set _think_end = '</thinking>' %}
+            {%- elif '\n</think>' in content %}
+                {%- set _think_end = '\n</think>' %}
+            {%- elif '\n</thinking>' in content %}
+                {%- set _think_end = '\n</thinking>' %}
+            {%- elif '\n</ think>' in content %}
+                {%- set _think_end = '\n</ think>' %}
+            {%- elif '\n</think >' in content %}
+                {%- set _think_end = '\n</think >' %}
+            {%- elif content.startswith('<think>') and '</think>' in content %}
+                {%- set _think_end = '</think>' %}
+            {%- elif content.startswith('<thinking>') and '</thinking>' in content %}
+                {%- set _think_end = '</thinking>' %}
+            {%- endif %}
+            {%- if _think_end %}
+                {%- if 'thinking' in _think_end %}
+                    {%- set _think_start = '<thinking>' %}
+                {%- else %}
+                    {%- set _think_start = '<think>' %}
+                {%- endif %}
+                {%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
+                {%- if _think_start in reasoning_content %}
+                    {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
+                {%- endif %}
+                {%- set content = content.split(_think_end)[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content | trim %}
+        {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) %}
+            {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>assistant\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined and tool_call.function is not none %}
+                    {%- set tc = tool_call.function %}
+                {%- else %}
+                    {%- set tc = tool_call %}
+                {%- endif %}
+                {%- set tc_name = tc.name if (tc.name is defined and tc.name is not none) else '' %}
+                {%- if _tool_format == 'json' %}
+                    {%- if loop.first %}
+                        {%- if content | trim %}
+                            {{- '\n\n' }}
+                        {%- endif %}
+                    {%- else %}
+                        {{- '\n' }}
+                    {%- endif %}
+                    {%- set _args = '{}' %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- set _args = tc.arguments | tojson %}
+                        {%- elif tc.arguments is string %}
+                            {%- if tc.arguments %}
+                                {%- set _args = tc.arguments %}
+                            {%- endif %}
+                        {%- else %}
+                            {%- set _args = tc.arguments | tojson %}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '<tool_call>\n{"name": ' }}{{- tc_name | tojson }}{{- ', "arguments": ' }}{{- _args }}{{- '}\n</tool_call>' }}
+                {%- else %}
+                    {%- if loop.first %}
+                        {%- if content | trim %}
+                            {{- '\n\n<tool_call>\n<function=' + tc_name + '>\n' }}
+                        {%- else %}
+                            {{- '<tool_call>\n<function=' + tc_name + '>\n' }}
+                        {%- endif %}
+                    {%- else %}
+                        {{- '\n<tool_call>\n<function=' + tc_name + '>\n' }}
+                    {%- endif %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- for args_name, args_value in tc.arguments.items() %}
+                                {{- '<parameter=' + args_name + '>\n' }}
+                                {%- if args_value is string %}
+                                    {%- set _av = args_value %}
+                                {%- else %}
+                                    {%- set _av = args_value | tojson %}
+                                {%- endif %}
+                                {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}
+                                    {{- _av[:max_tool_arg_chars] + '\n[TRUNCATED - original length ' ~ (_av | length | string) ~ ' chars]' }}
+                                {%- else %}
+                                    {{- _av }}
+                                {%- endif %}
+                                {{- '\n</parameter>\n' }}
+                            {%- endfor %}
+                        {%- else %}
+                            {%- if tc.arguments is string %}
+                                {%- set _raw_args = tc.arguments %}
+                            {%- else %}
+                                {%- set _raw_args = tc.arguments | tojson %}
+                            {%- endif %}
+                            {%- if _raw_args %}
+                                {%- if max_tool_arg_chars > 0 and _raw_args | length > max_tool_arg_chars %}
+                                    {{- _raw_args[:max_tool_arg_chars] + '\n[TRUNCATED - original length ' ~ (_raw_args | length | string) ~ ' chars]' }}
+                                {%- else %}
+                                    {{- _raw_args }}
+                                {%- endif %}
+                            {%- endif %}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '</function>\n</tool_call>' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- set _content_lower = content | lower %}
+        {%- set _content_head = _content_lower[:120] %}
+        {%- set _is_code_or_grep = ('throw new ' in _content_lower or 'throw error' in _content_lower or 'console.error' in _content_lower or 'logger.error' in _content_lower or 'logging.error' in _content_lower or 'import ' in _content_head or 'def ' in _content_head or 'function ' in _content_head) %}
+        {%- set _exit_code_zero = ('exit code: 0' in _content_head or 'process exited with code 0' in _content_head) %}
+        {%- set _error_field_ok = ('"error": null' in _content_head or '"error":null' in _content_head or '"error": false' in _content_head or '"error":false' in _content_head or '"error": ""' in _content_head or '"error":""' in _content_head) %}
+        {%- set _strong_error = (('"error":' in _content_head and not _error_field_ok) or '"status": "error"' in _content_head or '"status":"error"' in _content_head or 'traceback (most recent call last):' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'fatal:' in _content_head or (('exit code: ' in _content_head or 'process exited with code' in _content_head) and not _exit_code_zero) or _content_head.startswith('exception:') or _content_head.startswith('failed to ')) %}
+        {%- set _weak_error = ('error:' in _content_head or 'err!' in _content_head) %}
+        {%- set _weak_suppressed = ('$ ' in _content_head or 'took ' in _content_head or content | length >= 600) %}
+        {%- if not _is_code_or_grep and (_strong_error or (_weak_error and not _weak_suppressed)) %}
+            {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}
+        {%- else %}
+            {%- set ns2.consecutive_failures = 0 %}
+        {%- endif %}
+        {%- if ns2.prev_role != 'tool' %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {%- set _is_json_payload = (_tool_format == 'json' and content | trim | length > 0 and (content | trim)[:1] in ('{', '[')) %}
+        {%- if not _is_json_payload and max_tool_response_chars > 0 and content | length > max_tool_response_chars %}
+            {%- set content = content[:max_tool_response_chars] + '\n[TRUNCATED - original length ' ~ (content | length | string) ~ ' chars]' %}
+        {%- endif %}
+        {{- '\n<tool_response>\n' + content }}
+        {%- if ns2.consecutive_failures >= 2 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}
+        {%- elif ns2.consecutive_failures == 1 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- set _next_role = _msgs[loop.index0 + 1].role %}
+            {%- if _next_role != 'tool' %}
+                {{- '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
+    {%- endif %}
+    {%- set ns2.prev_role = message.role %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if not ns_state.thinking %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

indexed88-v6.4-135k-r2/selected_88064_135k_v64_40_R2.i32le

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b578828c0b517ba47abe90a130fda7cde5a56d94add1afeac7623e7c8f6234b4
+size 352256

indexed88-v6.4-135k-r2/thinkingcap-135000-q8-repack.ninfer

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1ab1bfc8dc4ac119b3c064993423f3e4f351796db43468f4180b2e20ab7ad6
+size 15820439556