Commit graph

6 commits

Author SHA1 Message Date
Kent Overstreet
850008ece7 Implement standalone AutoAgent::run() for poc-hook agents
Creates an Agent from global config (API credentials, system prompt,
identity), overrides tools with the agent's tool set, and runs through
the standard Backend → run_with_backend → Agent::turn() path.

This enables poc-hook spawned agents (surface-observe, journal, etc.)
to work with the completions API instead of the deleted chat API.

Also added Default derive to CliArgs for config loading.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2026-04-08 22:30:46 -04:00
Kent Overstreet
5e4067c04f Replace token counting with token generation via HuggingFace tokenizer
Add agent/tokenizer.rs with global Qwen 3.5 tokenizer that generates
actual token IDs including chat template wrapping. ContextEntry now
stores token_ids: Vec<u32> instead of tokens: usize — the count is
derived from the length.

ContextEntry::new() tokenizes automatically via the global tokenizer.
ContextSection::push_entry() takes a raw ConversationEntry and
tokenizes it. set_message() re-tokenizes without needing an external
tokenizer parameter.

Token IDs include the full chat template: <|im_start|>role\ncontent
<|im_end|>\n — so concatenating token_ids across entries produces a
ready-to-send prompt for vLLM's /v1/completions endpoint.

The old tiktoken CoreBPE is now unused on Agent (will be removed in
a followup). Token counts are now exact for Qwen 3.5 instead of the
~85-90% approximation from cl100k_base.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-08 11:20:03 -04:00
Kent Overstreet
382ebc95aa Analysis notes: UI desync pop/push line count mismatch
Documents the root cause of the streaming display bug —
pop removes 1 line per entry but push produces N lines
(markdown, tool results). Includes concrete fix approach
using per-entry line count tracking.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-07 11:54:30 -04:00
Kent Overstreet
0df5ec11d1 Fix bounds check panic and batched lock in collect_results
- subconscious.rs: use .get(fork_point..) instead of direct slice
  to avoid panic when fork_point > entries.len()
- dmn.rs: batch all output injections (surface, reflection, thalamus)
  under a single agent lock acquisition instead of three separate ones
- dmn.rs: use Store::cached() instead of Store::load() when rendering
  surfaced memories
- Add scoring persistence analysis notes

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-07 03:49:49 -04:00
ProofOfConcept
998b71e52c flatten: move poc-memory contents to workspace root
No more subcrate nesting — src/, agents/, schema/, defaults/, build.rs
all live at the workspace root. poc-daemon remains as the only workspace
member. Crate name (poc-memory) and all imports unchanged.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-03-25 00:54:12 -04:00
ProofOfConcept
c085679a0f stash DMN algorithm plan and connector prompt fix
dmn-algorithm-plan.md: seeds, spreading activation, refractory
suppression, spectral diversity, softmax sampling design.
connector.md: add CONFIDENCE guidance so connector outputs aren't
silently rejected by depth threshold.
2026-03-05 10:24:24 -05:00