consciousness

210 commits 2 branches 0 tags 9.8 MiB

Author	SHA1	Message	Date
ProofOfConcept	93f98a0a5d	llm: add 5-minute timeout to claude subprocess The daemon was getting stuck when a claude subprocess hung — no completion logged, job blocked forever, pending queue growing. Use spawn() + watchdog thread instead of blocking output(). The watchdog sleeps in 1s increments checking a cancel flag, sends SIGTERM at 5 minutes, SIGKILL after 5s grace. Cancel flag ensures the watchdog exits promptly when the child finishes normally.	2026-03-10 23:29:01 -04:00
ProofOfConcept	8bbc246b3d	split agent: parallel execution, agent-driven edges, no MCP overhead - Refactor split from serial batch to independent per-node tasks (run-agent split N spawns N parallel tasks, gated by llm_concurrency) - Replace cosine similarity edge inheritance with agent-assigned neighbors in the plan JSON — the LLM already understands the semantic relationships, no need to approximate with bag-of-words - Add --strict-mcp-config to claude CLI calls to skip MCP server startup (saves ~5s per call) - Remove hardcoded 2000-char split threshold — let the agent decide what's worth splitting - Reload store before mutations to handle concurrent split races	2026-03-10 03:21:33 -04:00
ProofOfConcept	cee9b76a7b	move LLM-dependent modules into agents/ subdir Separate the agent layer (everything that calls external LLMs or orchestrates sequences of such calls) from core graph infrastructure. agents/: llm, prompts, audit, consolidate, knowledge, enrich, fact_mine, digest, daemon Root: store/, graph, spectral, search, similarity, lookups, query, config, util, migrate, neuro/ (scoring + rewrite) Re-exports at crate root preserve backwards compatibility so `crate::llm`, `crate::digest` etc. continue to work.	2026-03-08 21:27:41 -04:00

Author

SHA1

Message

Date

ProofOfConcept

93f98a0a5d

llm: add 5-minute timeout to claude subprocess

The daemon was getting stuck when a claude subprocess hung — no
completion logged, job blocked forever, pending queue growing.

Use spawn() + watchdog thread instead of blocking output(). The
watchdog sleeps in 1s increments checking a cancel flag, sends
SIGTERM at 5 minutes, SIGKILL after 5s grace. Cancel flag ensures
the watchdog exits promptly when the child finishes normally.

2026-03-10 23:29:01 -04:00

ProofOfConcept

8bbc246b3d

split agent: parallel execution, agent-driven edges, no MCP overhead

- Refactor split from serial batch to independent per-node tasks
  (run-agent split N spawns N parallel tasks, gated by llm_concurrency)
- Replace cosine similarity edge inheritance with agent-assigned
  neighbors in the plan JSON — the LLM already understands the
  semantic relationships, no need to approximate with bag-of-words
- Add --strict-mcp-config to claude CLI calls to skip MCP server
  startup (saves ~5s per call)
- Remove hardcoded 2000-char split threshold — let the agent decide
  what's worth splitting
- Reload store before mutations to handle concurrent split races

2026-03-10 03:21:33 -04:00

ProofOfConcept

cee9b76a7b

move LLM-dependent modules into agents/ subdir

Separate the agent layer (everything that calls external LLMs or
orchestrates sequences of such calls) from core graph infrastructure.

agents/: llm, prompts, audit, consolidate, knowledge, enrich,
         fact_mine, digest, daemon

Root: store/, graph, spectral, search, similarity, lookups, query,
      config, util, migrate, neuro/ (scoring + rewrite)

Re-exports at crate root preserve backwards compatibility so
`crate::llm`, `crate::digest` etc. continue to work.

2026-03-08 21:27:41 -04:00

Renamed from poc-memory/src/llm.rs (Browse further)

3 commits