Override the agent output/input directory for manual testing.
Sets POC_AGENT_OUTPUT_DIR so output() writes there and
{{input:key}} reads from there.
Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
- output(key, value): write named results to agent state dir,
readable via {{input:key}} placeholder
- journal_tail(count): read last N journal entries
- journal_new(title, body): start new ## timestamped entry
- journal_update(body): append to last entry
Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
Split agent prompts on === PROMPT === delimiter. Each step runs as
a new user message in the same LLM conversation, so context carries
forward naturally between steps. Single-step agents are unchanged.
- AgentDef.prompt -> AgentDef.prompts: Vec<String>
- AgentBatch.prompt -> AgentBatch.prompts: Vec<String>
- API layer injects next prompt after each text response
- {{conversation:N}} parameterized byte budget for conversation context
Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
Replaced debug_visible bool with an Overlay enum. F1 shows the
context/debug screen (Ctrl+D still works as alias), F2 shows the
agents screen (placeholder for now — will show surface, observe,
reflect, journal status). Esc closes any overlay.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Personality is identity, not memory. Memory is nodes loaded during
the session via tool calls — things I've actively looked at.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
mem% was always 0 because memory_tokens was hardcoded to 0. Now
counts personality context + loaded nodes from memory tool calls.
Also calls measure_budget + publish_context_state after memory tool
dispatch so the debug screen updates immediately.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Exposes the full query language as a tool: filtering, sorting, field
selection, neighbor walks. Examples:
degree > 10 | sort weight | limit 5
neighbors('identity') | select strength
key ~ 'journal.*' | count
Also added query_to_string() in the parser so queries return strings
instead of printing to stdout. Updated memory-instructions-core to
list all current tools (added memory_query and journal, removed
CLI commands section and nonexistent memory_search_content).
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Links now show just the key name instead of `poc-memory render KEY`.
The agent uses memory_render tool calls, not bash commands.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
ContextSource::Store was handled identically to File — reading .md
files from disk. Now uses MemoryNode::load() to read from the capnp
store. This is why personality wasn't showing correctly in poc-agent:
store-sourced context groups (cognitive-modes, stuck-toolkit,
instructions, memory-instructions-core) were being looked up as
flat files and silently missing.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
- Removed write/search/mark_used static methods from MemoryNode —
those are store ops, not MemoryNode concerns
- Removed SearchResult duplicate — use query::engine::SearchResult
- Simplified Link to (String, f32) tuple — inline detection moved
to render()
- Collapsed tool definitions to one-liners
- Consolidated store-mutation tools into with_store() helper
- Supersede uses store directly instead of MemoryNode round-trip
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
MemoryNode moved from agent/memory.rs to hippocampus/memory.rs — it's
a view over hippocampus data, not agent-specific.
Store operations (set_weight, set_link_strength, add_link) moved into
store/ops.rs. CLI code (cli/graph.rs, cli/node.rs) and agent tools
both call the same store methods now. render_node() delegates to
MemoryNode::from_store().render() — 3 lines instead of 40.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Memory tools now dispatch through a special path in the runner (like
working_stack) instead of the generic tools::dispatch. This gives them
&mut self access to track loaded nodes:
- memory_render/memory_links: loads MemoryNode, registers in
context.loaded_nodes (replace if already tracked)
- memory_write: refreshes existing tracked node if present
- All other memory tools: dispatch directly, no tracking needed
The debug screen (context_state_summary) now shows a "Memory nodes"
section listing all loaded nodes with version, weight, and link count.
This is the agent knowing what it's holding — the foundation for
intelligent refresh and eviction.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Every memory tool call was spawning a poc-memory subprocess. Now uses
MemoryNode and direct Store API calls:
- memory_render: MemoryNode::load() + render()
- memory_write: MemoryNode::write() via store.upsert_provenance()
- memory_search: MemoryNode::search() via search engine
- memory_links: MemoryNode::load() + iterate links
- memory_link_add: store.add_relation() with Jaccard strength
- memory_link_set: direct relation mutation
- memory_used: store.mark_used()
- memory_weight_set: direct node.weight mutation
- memory_supersede: MemoryNode::load() + write() + weight_set()
No more Command::new("poc-memory") in this module.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
MemoryNode is the agent's live view of a loaded memory node — key,
content, links, version, weight. Operations (load, write, search,
mark_used) go directly through the store API instead of spawning
poc-memory subprocesses.
This is the foundation for context-aware memory: the agent can track
which nodes are loaded in its context window, detect changes, and
refresh regions when nodes are updated.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
The agent was shelling out to poc-hook which shells out to memory-search.
Now that everything is one crate, just call the library function. Removes
subprocess overhead on every user message.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Generic session state (session_id, seen set, state directory) doesn't
belong in the memory search module. Now at crate root, re-exported
from memory_search for backwards compatibility.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Both hippocampus/config.rs and agent/config.rs read from the same
config file (~/.config/poc-agent/config.json5). Having two separate
implementations was a footgun — load_context_groups() was duplicated
three times across the codebase.
Merged into src/config.rs:
- Config (memory settings, global get()/reload())
- AppConfig (agent backend/model settings, figment-based loading)
- SessionConfig (resolved agent session, renamed from agent's Config)
- Single ContextGroup/ContextSource definition used everywhere
Eliminated: duplicate load_context_groups(), duplicate ContextGroup
definition in identity.rs, duplicate config file path constants.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
agents/*.agent definitions and prompts/ now live under
src/subconscious/ alongside the code that uses them.
No more intermediate agents/ subdirectory.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
hippocampus/ — memory storage, retrieval, and consolidation:
store, graph, query, similarity, spectral, neuro, counters,
config, transcript, memory_search, lookups, cursor, migrate
subconscious/ — autonomous agents that process without being asked:
reflect, surface, consolidate, digest, audit, etc.
All existing crate::X paths preserved via re-exports in lib.rs.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
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>
poc-daemon (notification routing, idle timer, IRC, Telegram) was already
fully self-contained with no imports from the poc-memory library. Now it's
a proper separate crate with its own Cargo.toml and capnp schema.
poc-memory retains the store, graph, search, neuro, knowledge, and the
jobkit-based memory maintenance daemon (daemon.rs).
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Category was a manually-assigned label with no remaining functional
purpose (decay was the only behavior it drove, and that's gone).
Remove the enum, its methods, category_counts, the --category search
filter, and all category display. The field remains in the capnp
schema for backwards compatibility but is no longer read or written.
Status and health reports now show NodeType breakdown (semantic,
episodic, daily, weekly, monthly) instead of categories.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Replace hardcoded "identity" lookups with config.core_nodes so
experience mining and init work with whatever core nodes are
configured, not just a node named "identity".
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Graph-wide decay is the wrong approach — node importance should emerge
from graph topology (degree, centrality, usage patterns), not a global
weight field multiplied by a category-specific factor.
Remove: Store::decay(), Store::categorize(), Store::fix_categories(),
Category::decay_factor(), cmd_decay, cmd_categorize, cmd_fix_categories,
job_decay, and all category assignments at node creation time.
Category remains in the schema as a vestigial field (removing it
requires a capnp migration) but no longer affects behavior.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Replace key prefix matching (journal#j-, daily-, weekly-, monthly-)
with NodeType filters (EpisodicSession, EpisodicDaily, EpisodicWeekly,
EpisodicMonthly) for all queries: journal-tail, digest gathering,
digest auto-detection, experience mining dedup, and find_journal_node.
Add EpisodicMonthly to NodeType enum and capnp schema.
Key naming conventions (journal#j-TIMESTAMP-slug, daily-DATE, etc.)
are retained for key generation — the fix is about how we find nodes,
not how we name them.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
All nodes in the store are memory — none should be excluded from
knowledge extraction, search, or graph algorithms by name. Removed
the MEMORY/where-am-i/work-queue/work-state skip lists entirely.
Deleted where-am-i and work-queue nodes from the store (ephemeral
scratchpads that don't belong). Added orphan edge pruning to fsck
so broken links get cleaned up automatically.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Journal and digest nodes are episodic memory — they should participate
in the graph on the same terms as everything else. Remove all
journal#/daily-/weekly-/monthly- skip filters from knowledge
extraction, connector pairs, challenger, semantic keys, and link
candidate selection. Use node_type field instead of key name matching
for episodic/semantic classification.
Operational nodes (MEMORY, where-am-i, work-queue, work-state) are
still filtered — they're system state, not memory.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
replay_nodes now tracks all UUIDs per key using a temporary multimap.
Warns on duplicates so they can be manually resolved.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
Keys were a vestige of the file-based era. resolve_key() added .md
to lookups while upsert() used bare keys, creating phantom duplicate
nodes (the instructions bug: writes went to "instructions", reads
found "instructions.md").
- Remove .md normalization from resolve_key, strip instead
- Update all hardcoded key patterns (journal.md# → journal#, etc)
- Add strip_md_keys() migration to fsck: renames nodes and relations
- Add broken link detection to health report
- Delete redirect table (no longer needed)
- Update config defaults and config.jsonl
Migration: run `poc-memory fsck` to rename existing keys.
Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
The clear sequence (Escape q C-c C-u) was disrupting Claude Code's
input state, causing nudge messages to arrive as blank prompts.
Simplified to just literal text + Enter.
Without -l, tmux send-keys treats spaces as key-name separators,
so multi-word messages like "This is your time" get split into
individual unrecognized key names instead of being typed as text.
This caused idle nudges to arrive as blank messages.
Add `poc-daemon afk` to immediately mark Kent as away, allowing the
idle timer to fire without waiting for the session active timeout.
Add `poc-daemon session-timeout <secs>` to configure how long after
the last message Kent counts as "present" (default 15min, persisted).
Fix block_reason() to report "kent present" and "in turn" states
that were checked in the tick but not in the diagnostic output.
Decay is metadata, not content. Bumping version caused unnecessary
log churn and premature cache invalidation.
Also disable auto-decay in scheduler — was causing version spam
and premature demotion of useful nodes.
Add optional progress callback to mine_transcript/mine_and_store so
the daemon can display per-chunk status. Sort fact-mine queue by file
size so small transcripts drain first. Write empty marker for
transcripts with no facts to avoid re-queuing them.
Also hardens the extraction prompt suffix.
Reads each capnp log message sequentially, validates framing and
content. On first corrupt message, truncates to last good position
and removes stale caches so next load replays from repaired log.
Wired up as `poc-memory fsck`.
Claude Code doesn't create new session files on context compaction —
a single UUID can accumulate 170+ conversations, producing 400MB+
JSONL files that generate 1.3M token prompts.
Split at compaction markers ("This session is being continued..."):
- extract_conversation made pub, split_on_compaction splits messages
- experience_mine takes optional segment index
- daemon watcher parses files, spawns per-segment jobs (.0, .1, .2)
- seg_cache memoizes segment counts across ticks
- per-segment dedup keys; whole-file key when all segments complete
- 150K token guard skips any remaining oversized segments
- char-boundary-safe truncation in enrich.rs and fact_mine.rs
Backwards compatible: unsegmented calls still write content-hash
dedup keys, old whole-file mined keys still recognized.
Track activity level as an EWMA (exponentially weighted moving average)
driven by turn duration. Long turns (engaged work) produce large boosts;
short turns (bored responses) barely register.
Asymmetric time constants: 60s boost half-life for fast wake-up, 5-minute
decay half-life for gradual wind-down. Self-limiting boost formula
converges toward 0.75 target — can't overshoot.
- Add activity_ewma, turn_start, last_nudge to persisted state
- Boost on handle_response proportional to turn duration
- Decay on every tick and state transition
- Fix kent_present: self-nudge responses (fired=true) don't update
last_user_msg, so kent_present stays false during autonomous mode
- Nudge only when Kent is away, minimum 15s between nudges
- CLI: `poc-daemon ewma [VALUE]` to query or set
- Status output shows activity percentage
The early return on line 343 when the LLM found no missed experiences
bypassed the dedup key writes at lines 397-414, despite the comment
saying "even if count == 0, to prevent re-runs." This caused sessions
with nothing to mine to be re-mined every 60s tick indefinitely.
Fix: replace the early return with a conditional print, so the dedup
keys are always written and saved.
Transcripts mined before the filename-key feature was added had
content-hash keys (#h-) but no filename keys (#f-). The daemon's
fast-path check only looks at filename keys, so these sessions were
re-queued every tick, hitting the content-hash dedup (0.0s) but
returning early before writing the filename key — a self-perpetuating
loop burning Sonnet quota on ~560 phantom re-mines per minute.
Fix: when the content-hash dedup fires and no filename key exists,
backfill it before returning.
Experience-mined journal entries were all getting created_at = now(),
causing them to sort by mining time instead of when the event actually
happened. Parse the conversation timestamp and set created_at to the
event time so journal-tail shows correct chronological order.
Only extract content blocks with "type": "text". Previously relied on
tool_use/tool_result blocks lacking a "text" field, which worked but
was fragile. Now explicitly checks block type.
Skip session files under 100KB (daemon-spawned LLM calls, aborted
sessions). This drops ~8000 spurious pending jobs.
Decouple fact-mine from experience-mine: fact-mine only queues when
the experience-mine backlog is empty, ensuring experiences are
processed first.
Session-watcher progress now shows breakdown by type:
"N extract, N fact, N open" instead of flat "N pending".
upsert() now checks POC_PROVENANCE env var for provenance label,
falling back to Manual. This lets external callers (Claude sessions,
scripts) tag writes without needing to use the internal
upsert_provenance() API.
Add from_env() and from_label() to Provenance for parsing.
Move provenance_label() from query.rs private function to a pub
label() method on Provenance, eliminating duplication. History command
now shows provenance, human-readable timestamps, and content size for
each version.
Handle pre-migration nodes with bogus timestamps gracefully instead
of panicking.
Show running/pending tasks with elapsed time, progress, and last 3
output lines. Show last 20 completed/failed jobs from daemon log.
Both displayed before the existing grouped task view.
Add 'poc-memory history KEY' command that replays the append-only node
log to show all versions of a key with version number, weight, timestamp,
and content preview. Useful for auditing what modified a node.
The cache staleness mechanism (log-size headers, tmp+rename) was sound,
but save() was re-reading the current log size from the filesystem
instead of using the size at load time. With concurrent writers, this
caused the cache to claim validity for log data it didn't contain.
Fix: track loaded_nodes_size/loaded_rels_size through the Store
lifecycle. Set them on load (all three paths: rkyv snapshot, bincode
cache, log replay) and update after each append via fstat on the
already-open fd.
Also fix append atomicity: replace BufWriter (which may issue multiple
write() syscalls) with serialize-to-Vec + single write_all(), ensuring
O_APPEND atomicity without depending on flock.
Make from_capnp() pub for use by the history command.
- Send PING after 120s of silence, disconnect after 30s with no PONG
- Reset backoff to base when a working connection drops (was registered)
- Validate channel membership before sending to channels
The ping timeout catches silent disconnects where the TCP connection
stays open but OFTC has dropped us. Previously we'd sit "connected"
indefinitely receiving nothing.
