erllama 0.11.0

Changed

• chat/3 defaults reasoning_format to deepseek: thinking models
  now return their thinking text in reasoning_content instead of
  inline in content (llama-server's default). Opt out per call with
  reasoning_format => none.
• chat_apply/3 returns the template's constraint set alongside
  prompt and params: sampler_opts, stop_sequences,
  generation_prompt, supports_thinking, thinking_start_tag,
  thinking_end_tags. Merge sampler_opts + stop_sequences into
  the stream/3 options (the tool-calls guide shows how).

Added

• erllama:fork_session/3: duplicate a sticky session's live KV into
  a new session (llama_memory_seq_cp), so two continuations explore
  different branches without re-prefilling the shared prefix. Works
  on every model family; never queues (seq_capacity when no
  sequence is free).
• Load progress: progress_to => Pid on load_model delivers
  {erllama_load_progress, ModelId, Float} messages (whole-percent
  throttled, final 1.0) while the GGUF loads.
• Native logs: llama.cpp / ggml log lines are forwarded into logger
  under the domain [erllama, native], gated by the native_log_level
  application env (none | error | warning | info | debug, default
  warning).
• Full llama.cpp sampler surface as request options: typical_p,
  top_n_sigma, xtc_probability / xtc_threshold,
  dynatemp_range / dynatemp_exponent, min_keep,
  frequency_penalty / presence_penalty / penalty_last_n, DRY
  (dry_multiplier, dry_base, dry_allowed_length,
  dry_penalty_last_n, dry_sequence_breakers), mirostat (1 | 2)
  with mirostat_tau / mirostat_eta, logit_bias, ignore_eos
  and infill. Chain order follows llama.cpp's default; see the
  sampling reference in the configuration guide.
• Per-token logprobs: logprobs => N (1..32) emits
  {erllama, Ref, {logprobs, #{token_id, logprob, top}}} stream
  events and adds a logprobs list to complete/3 / collect/2
  results. Full-vocab log-softmax over the raw model distribution
  (OpenAI semantics).
• erllama:vocab_info/1: vocabulary size, add_bos / add_eos, and
  the special / FIM token ids (bos, eos, eot, sep, nl,
  pad, mask, fim_pre, fim_suf, fim_mid, fim_pad,
  fim_rep, fim_sep) for fill-in-the-middle prompt assembly.
• erllama:detokenize/3 with remove_special / unparse_special
  (renders special tokens), backed by llama_detokenize.
  detokenize/2 is untouched: the cache byte-keys are computed over
  its output.
• Tool-call grammar enforcement: chat/3 merges the grammar llama.cpp
  synthesizes from the chat template into the request, so
  tool_choice => required always yields a parsed call and
  tool_choice => auto arms a lazy grammar that constrains the reply
  once the model opens a call. Template-declared stop strings are
  honoured. A caller grammar combined with active tools is rejected.
• json_schema chat option (OpenAI response_format semantics): the
  reply's content is grammar-constrained to the schema. Rejected in
  combination with tools.
• Chat options enable_thinking (default true) and
  continue_final_message (none | auto | content | reasoning) for
  assistant prefill.
• Request options grammar_lazy, trigger_patterns,
  trigger_tokens, grammar_prefill: the lazy / template-grammar
  sampler shape (llama_sampler_init_grammar_lazy_patterns), usable
  directly with stream/3 and friends.

Fixed

• Cache correctness on recurrent / hybrid models (Mamba, RWKV, Jamba,
  Qwen3-Next, LFM2, ...): a warm exact hit no longer duplicates the
  last prompt token when the memory refuses the primer's partial
  removal; the engine falls back to a cold prefill and bumps the new
  restore_failed counter. A failed kv_unpack no longer crashes the
  model process (the row is treated as a miss).
• Partial warm hits (extended prompts) prefill the suffix directly
  instead of dropping and re-decoding the last cached token: one fewer
  decoded token per partial hit, and no partial seq_rm, so the path
  stays warm on recurrent models.
• nif_kv_seq_rm refreshes the per-seq position bookkeeping on
  failure too, keeping Erlang and llama.cpp in agreement when a
  partial removal is refused.

Added

• Model-family probe at load: model_info/1 reports arch,
  n_ctx_train, n_params, n_embd, n_layer, n_swa,
  recurrent and hybrid (llama backend). Encoder-decoder (T5) and
  diffusion archs are rejected at load with
  {error, {unsupported_model, encoder_decoder | diffusion}} instead
  of failing confusingly at the first decode.
• Context option n_rs_seq (recurrent-state rollback snapshots per
  seq); defaults to 1 on recurrent / hybrid models so warm hits work
  where the arch supports rollback.
• split_mode => tensor (experimental upstream tensor-parallel
  split; row is deprecated upstream).
• Cache counter restore_failed; stub backend knobs
  fail_seq_rm_last / fail_kv_unpack to test the fallback paths.