docs: fix model-tag seam for HF-pull users + vision caveat + CITATION version

From the round-2 review:
- The `ollama show janus` note claimed "either path," but the short `janus` tag
only exists after the local build (path B); every inference example hard-codes
model "janus", so a TL;DR/path-A puller hit `model 'janus' not found` on their
first snippet. Corrected the claim and added a note to substitute the full
hf.co/FoolDev/Janus-35B-HERETIC tag (or `ollama cp`).
- llama-server vision block now documents the reasoning_content/content split
and the >=500 max_tokens budget (parity with the Thanatos sibling).
- CITATION.cff gains version 0.1.0 + date-released 2026-05-20 so the HF "Cite
this model" widget generates a dated, versioned citation.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

CHANGELOG.md

@@ -18,6 +18,9 @@ track the **tooling and documentation**, not the underlying base model.
 - **Frontmatter tags `reasoning` + `distillation`.** The card positions Janus
   as reasoning-first and distilled (and `CITATION.cff` already lists both as
   keywords), but neither was a searchable Hub tag — added both.
+- **`CITATION.cff` now carries `version` + `date-released`.** Added `0.1.0` /
+  `2026-05-20` (mirroring the CHANGELOG release anchor) so the HF "Cite this
+  model" widget generates a dated, versioned citation.
 
 ### Changed (default sampling matched to the Fable teacher)
 - **Default sampling raised to a Fable-matched profile** in `params` and the
@@ -29,6 +32,15 @@ track the **tooling and documentation**, not the underlying base model.
   override.
 
 ### Fixed
+- **Inference examples no longer 404 for HF-pull users.** The `ollama show janus`
+  claim said "either path," but the short `janus` tag only exists after the local
+  build (path B); every inference example hard-codes `model: "janus"`, so a
+  TL;DR/path-A puller hit `model 'janus' not found`. Corrected the claim and added
+  a note to substitute the full `hf.co/FoolDev/Janus-35B-HERETIC` tag (or `ollama cp`).
+- **Vision block documents the `reasoning_content` split.** The llama-server
+  vision recipe now notes the thinking trace lands in `message.reasoning_content`
+  and the answer in `message.content`, and to budget ≥500 `max_tokens` so
+  reasoning doesn't crowd out the answer (parity with the Thanatos sibling).
 - **Hardware-table eval disclaimer no longer self-contradicts.** "Known
   limitations" said the table numbers are "estimates, not measured," yet the
   Z13 row records a measured 28.71 tok/s — reworded to carve out that row.

CITATION.cff

@@ -1,4 +1,6 @@
 cff-version: 1.2.0
+version: 0.1.0
+date-released: "2026-05-20"
 title: "Janus-35B: A Mixture-of-Experts Distillation Wrapper for llmfan46's Qwen 3.6 35B-A3B Uncensored Heretic"
 message: "If you use this model card or its accompanying files, please cite as below."
 type: software

README.md

@@ -149,12 +149,14 @@ ollama run hf.co/FoolDev/Janus-35B-HERETIC:Q4_K_M        # same blob, explicit t
 ollama create janus -f Modelfile && ollama run janus
 ```
 
-After either path, `ollama show janus` should list `completion`, `tools`, and `thinking` under Capabilities.
+After the local build (path B), `ollama show janus` lists `completion`, `tools`, and `thinking` under Capabilities. (The HF-pull paths register the model under the full tag `hf.co/FoolDev/Janus-35B-HERETIC`, not `janus`.)
 
 ### Inference examples
 
 Once the model is loaded (via `ollama run janus`, `lms server`, or `llama-server`), all the standard OpenAI-compatible clients work. Examples assume the loader is listening on `http://localhost:11434` (Ollama default) — adjust the port for LM Studio (`:1234`) or llama.cpp (`:8080`). Runnable versions of everything below live in [`examples/`](examples/README.md).
 
+> The examples use `model: "janus"`, the tag from the local build (path B). If you pulled via the TL;DR one-liner instead, use the full tag `hf.co/FoolDev/Janus-35B-HERETIC`, or run `ollama cp hf.co/FoolDev/Janus-35B-HERETIC janus` once to create the short tag.
+
 #### curl
 
 ```bash
@@ -266,6 +268,9 @@ llama-server \
   --host 127.0.0.1 --port 8765 -c 8192 -ngl 99
 # then POST OpenAI-style chat completions with an image_url content block —
 # e.g. {"type":"image_url","image_url":{"url":"data:image/jpeg;base64,..."}}
+# The thinking trace arrives in message.reasoning_content; the visible
+# answer is in message.content. Budget ≥500 max_tokens so the reasoning
+# block doesn't crowd out the final answer.
 
 # B. CLI via llama-mtmd-cli (one-shot). It's a separate cmake target, so a
 #    selective build can skip it; a plain `cmake --build build` produces it.