* fix(deriver): Remove connection retry logic and add jitter to polling interval
* chore(docs): Update changelog and document new configurations
* chore: increment version numbers
* feat(db): add connection retry, adaptive deriver polling, and pool metrics
Add resilience and visibility for DB connection handling under transaction-
pooler (Supavisor) saturation, where client-connection limits get exhausted
across many tenants.
- get_db/tracked_db now force an eager pool checkout with bounded exponential
backoff (tenacity), retrying SQLAlchemy TimeoutError + OperationalError so
transient pooler rejections degrade gracefully instead of 500ing. Toggle via
DB_CONNECTION_RETRY_ENABLED (+ delay/backoff knobs); ~10s default budget.
- Deriver polling backs off when idle or erroring (base -> max, x2 each cycle)
and snaps back to base on claimed work, cutting steady-state query load.
Toggle via DERIVER_POLLING_BACKOFF_ENABLED (+ max/multiplier).
- Add scrape-time db_pool_connections Prometheus gauge (checked_out/checked_in/
size/overflow, labeled api|deriver), registered in both the API lifespan and
the deriver metrics server.
- Make SqlalchemyIntegration explicit in both Sentry inits; wrap connection
acquisition in a db.pool.acquire span and capture live pool stats on
retry-exhaustion.
* feat(db): add acquisition counter and in-flight query gauge
Build on the pool-connection metrics with two signals that turn detection
into diagnosis under transaction-pooler saturation:
- db_connection_acquisitions{outcome=ok|retried|exhausted}: counts how often
connection checkout retries through pooler rejection — the alertable early
warning before requests start failing.
- db_queries_in_flight: statements actually executing on the wire (via
SQLAlchemy cursor-execute events, drift-proof across query errors). Pairs
with checked_out: the gap reveals connections held but parked (the "idle in
transaction during an external call" antipattern). Labeled namespace +
instance_type only; gated on METRICS.ENABLED for zero overhead when off.
Add DB-free unit tests for retry outcomes, polling backoff, and in-flight
gauge drift handling.
* fix: address CodeRabbit review on PR #758
- db: roll back the session on a retryable checkout failure before
retrying — a failed autobegin can leave it pending-rollback, making the
next db.connection() raise instead of re-checking-out cleanly. Cheap
Python-side cleanup when no connection was bound.
- metrics: guard DBPoolCollector.collect() so a pool-read/import hiccup
can't raise and abort the whole /metrics scrape (Prometheus drops ALL
metrics if any collector raises) — log and fall back to empty.
* fix(db): lazy retrying session + review fixes for connection backoff
Address Codex/CodeRabbit review on PR #758.
- Replace eager checkout with HonchoAsyncSession: a lazy AsyncSession that
checks out its connection (with retry) on the first DB-touching call, not at
construction. Request handlers doing non-DB work (embedding/file/LLM) before
their first query no longer pin a connection across it, while the API path
still gets checkout retry. Only the checkout is retried — the statement runs
once via super(), so writes are never duplicated. Tracing's set_config moves
into the same lazy acquire hook.
- Roll the session back on a retryable checkout failure before retrying, so a
failed autobegin can't leave it pending-rollback.
- Lower default POOL_TIMEOUT to 5s and validate it stays under the retry budget
for pooled (non-null) POOL_CLASS; update config.toml.example and v2/v3 docs.
- Clamp pool overflow gauge to >= 0 (was negative before the pool fills).
- Remove double-sleep in the deriver idle poll (true backoff cap, not 2x);
make in-flight instrumentation registration idempotent.
- Tests: HonchoAsyncSession lazy/idempotent acquire, statement-runs-once,
tracing, commit/rollback flag reset, get_db no-acquire-at-entry, polling-loop
single-sleep, and the POOL_TIMEOUT/retry-budget validator.
* fix(db): cover all DB-touching session methods; clear flag on close/reset
Address Codex follow-up review on PR #758 (polish, no behavior-critical bug).
- HonchoAsyncSession: wrap get/get_one/stream/stream_scalars/delete in addition
to execute/scalar/scalars/flush/merge/refresh/commit, so the "lazy checkout
with retry on first DB use" guarantee has no holes. connection() stays
unwrapped (acquire_connection_with_retry calls it — wrapping would recurse).
- Reset the acquired flag on close()/reset() too, so a session reused after
close/reset re-acquires (and re-wraps retry) on its next DB use.
- Fix stale comments: connection retry now applies lazily to the request path
via HonchoAsyncSession (config.py), and the FakeSession helper note.
- Tests: close/reset flag reset, and get/delete route through acquisition.
* feat: add new cloudevents for api routes
* fix: add total input tokens to RepresentationCompletedEvent
* feat(telemetry): inject honcho_version + emitter health metrics
* feat(telemetry): per-LLM-call event with try/finally emission + sampler
Adds LLMCallCompletedEvent (llm.call.completed) — fires once per provider hit
with full cost-attribution context: transport/provider_label, model, token
counts with cache breakdown, finish_reason, outcome (success or error),
is_final_attempt flag, retry/fallback state, duration, tool-call shape,
streaming flag, and agent correlation (run_id + iteration).
- src/telemetry/events/llm.py: new event class + CallPurpose closed enum
(deriver.representation, dialectic.answer, dream.deduction|induction,
summary.short|long). Resource id includes attempt so multi-attempt retries
in one iteration get distinct deterministic ids.
- src/telemetry/events/base.py: BaseEvent._volume_class ClassVar (default
"ground_truth"); the new event opts into "high_volume".
- src/config.py: TelemetrySettings.HIGH_VOLUME_SAMPLE_RATE (default 1.0).
- src/telemetry/emitter.py: deterministic sampler keyed on run_id (so an
entire agent trace is kept or dropped together). Aggregate envelopes
bypass the sampler. Sampled-out events increment the dedicated counter
separate from buffer_full/send_failed drops.
- src/llm/runtime.py: AttemptPlan gains attempt/retry_attempts/is_fallback
so the executor reads retry state without re-deriving it.
- src/llm/types.py: LLMTelemetryContext dataclass carrying workspace,
call_purpose, run_id, iteration, peer fields. Iteration is mutable so
the tool loop can set it per inner call.
- src/llm/executor.py: honcho_llm_call_inner wraps the backend call in
try/finally — emits on success AND on exception, with is_final_attempt
computed from AttemptPlan. Stream path emits a was_stream=True placeholder
(token totals deferred until streaming completion is wired through).
Telemetry failures swallowed.
- src/llm/api.py: threads telemetry kwarg through all 4 signatures into
both honcho_llm_call_inner and execute_tool_loop.
- src/llm/tool_loop.py: _telemetry_for_iteration helper copies the caller
context with iteration set per call — covers both the normal iteration
loop AND the max-iteration synthesis call (iteration N+1).
Tests cover success/error emission, sampler trace-coherence (same run_id →
same decision), volume_class enforcement, unknown call_purpose tolerance,
provider_label inference, and telemetry failure isolation. 378/378 pass.
* feat(telemetry): emit agent.iteration on every LLM response + synthesis
AgentIterationEvent was defined but never emitted on this branch. Phase 2
wires it up in execute_tool_loop so every LLM call inside an agentic loop
produces one event — including the no-tool terminating iteration and the
max-iteration synthesis call — and threads LLMTelemetryContext from dialectic
and dreamer specialists down through honcho_llm_call.
- src/telemetry/events/agent.py: AgentIterationEvent opts into
_volume_class="high_volume" so the Phase 1 sampler throttles it.
- src/llm/tool_loop.py: _emit_agent_iteration() helper fires once per
honcho_llm_call_inner response, BEFORE the no-tool early return so the
terminating iteration is counted. A second emission fires for the
max-iteration synthesis call BEFORE final_response is mutated with
cumulative totals (otherwise the per-iteration counts would double-count).
Emission is defensively skipped when telemetry context lacks run_id /
agent_type / parent_category / workspace_name; emit failures are swallowed.
- src/dreamer/specialists.py: BaseSpecialist.run passes LLMTelemetryContext
with parent_category="dream", agent_type=self.name, observer/observed,
call_purpose=f"dream.{self.name}".
- src/dialectic/core.py: _telemetry_context() builds a shared context for
both answer() and answer_stream(), using self._run_id (always set) +
workspace + observed peer.
Tests cover fresh-copy semantics, per-iteration vs terminating emission,
defensive skip cases, telemetry-failure isolation, and volume_class. 408/408
pass across telemetry + llm + utils + dreamer + dialectic.
* feat(telemetry): agent.tool.call.completed event + ToolResult metadata
Adds the missing generic per-tool-call event so read-only tools (search_*,
get_recent_history, get_observation_context, etc.) and the four existing
state-change tools all produce a telemetry record. Built on a new internal
ToolResult(content, metadata) contract so handlers can surface
search-specific fields (top_k/used_embedding/query_tokens/results_count)
to Phase 3 and create/delete counts to Phase 5's specialist rollups.
- src/telemetry/events/agent.py: AgentToolCallCompletedEvent at v1 with
_volume_class="high_volume". Resource id = {run_id}:{iteration}:{tool_call_seq}
so two calls to the same tool in one iteration don't collide
deterministic ids and get dedup-dropped downstream.
- src/utils/types.py: ToolResult dataclass; two new ContextVars
(_current_tool_call_seq + _last_tool_metadata) so tool_loop and the
execute_tool closure can communicate per-call telemetry without changing
the public Callable[[str, dict], Any] signature.
- src/utils/agent_tools.py: execute_tool times handlers, unwraps ToolResult,
publishes metadata, emits the event. Handlers updated to ToolResult
where useful: create/delete observations, update_peer_card, search_memory,
search_messages. Other handlers continue to return str.
- src/llm/tool_loop.py: set_current_tool_call_seq before each executor call;
read get_last_tool_metadata after and stash on all_tool_calls[i] for
Phase 5 rollups.
Tests cover ToolResult str-likeness, ContextVar round-trip, full-context
emission with search metadata, resource-id disambiguation, defensive skip
cases, telemetry isolation, truncation metadata, volume_class. 420/420 pass.
* feat(telemetry): RepresentationCompletedEvent v2 token breakdown + tool-less truncation
Bulks out the deriver's per-batch telemetry without bumping the event schema
version. New additive fields capture the full token breakdown (queued vs.
extra-context vs. scaffold), the cap configuration (batch_max_tokens,
max_input_tokens, was_flush_enabled), real cap-hit flags, and observer
fanout. `input_tokens` stays unchanged as the queued-message-tokens billing
key Xatu's Stripe meter reads.
The big enabler: src/llm/api.py now actually enforces max_input_tokens on
the tool-less LLM path. Before this, the deriver passed the kwarg but the
path silently dropped it — so the configured cap was advisory and
hit_input_token_cap couldn't be measured. Phase 4 wires truncation through
the same truncate_messages_to_fit helper the tool loop uses and surfaces
input_was_truncated on HonchoLLMCallResponse.
- src/telemetry/events/representation.py: 12 additive fields, schema_version
stays at 2.
- src/llm/types.py: input_was_truncated on HonchoLLMCallResponse.
- src/llm/api.py: tool-less path truncates messages before dispatch, flips
input_was_truncated on the response when clamping occurs. Split into
Literal[True]/Literal[False] branches for typecheck.
- src/deriver/queue_manager.py: QueueBatchResult dataclass replaces the
3-tuple return from get_queue_item_batch; carries hit_batch_token_cap
(computed from cumulative token sum vs cap), was_flush_enabled snapshot,
and batch_max_tokens. Worker loop unpacks + forwards.
- src/deriver/consumer.py: process_representation_batch gains the three
flag kwargs and forwards.
- src/deriver/deriver.py: derives the breakdown fields locally, populates
the new fields on emit, sources hit_input_token_cap from
response.input_was_truncated.
Tests cover schema stability, defaultable fields, input_tokens semantic
preservation, cap-hit flag round-trip, model_dump completeness, and
HonchoLLMCallResponse.input_was_truncated mutability. Existing
test_queue_processing.py tests updated for QueueBatchResult and mock
process_representation_batch signature. 479/479 pass.
* feat(telemetry): DreamRunEvent v2 scheduler reasons + DreamSpecialistEvent v2 rollups
Bumps both dream events to v2 with additive fields. DreamRunEvent gains
scheduler context (threshold_reason / delay_reason / documents_since_last_dream_at_schedule /
document_threshold / dream_type / enabled_types_count) threaded through the
dream queue payload — the two scheduler gates stay as separate fields rather
than collapsing into one trigger_reason, preserving the WHY-vs-WHEN
semantics. DreamSpecialistEvent gains denormalized rollups
(created_observation_count / deleted_observation_count / peer_card_updated /
search_tool_calls_count) sourced from Phase 3's ToolResult.metadata so the
counts reflect observation truth, not call truth.
- src/telemetry/events/dream.py: schema_version → 2 for both events; new
fields all defaultable so older producers still construct valid events.
- src/utils/queue_payload.py: DreamPayload + create_dream_payload accept
threshold_reason / delay_reason / documents_since_last_dream_at_schedule /
document_threshold.
- src/dreamer/dream_scheduler.py: check_and_schedule_dream computes the two
reasons at decision time and threads them through schedule_dream →
_delayed_dream → execute_dream → enqueue_dream.
- src/deriver/enqueue.py: create_dream_record / enqueue_dream gain the
kwargs and persist on the queue payload.
- src/dreamer/orchestrator.py: process_dream unpacks the payload; run_dream
accepts the kwargs and stamps them on DreamRunEvent.
- src/dreamer/specialists.py: BaseSpecialist.run walks response.tool_calls_made
and sums ToolResult.metadata.created_count / .deleted_count, sets
peer_card_updated, counts search-tool calls by name.
Tests cover schema_version bumps, defaultable Phase 5 fields,
threshold-vs-delay semantics, observation-vs-call-count rollup distinction,
and DreamPayload round-trip. Existing tests updated for the schema bump
and the new enqueue_dream kwargs. 488/488 pass.
* feat(telemetry): AgentToolSummaryCreatedEvent v2 token breakdown
Bumps schema_version to 2 and adds three additive breakdown fields so
analytics can answer "how much of a summary call's cost was the previous-
summary rollup vs. the new messages vs. the scaffold instructions".
- src/telemetry/events/agent.py: previous_summary_tokens, message_tokens,
prompt_scaffold_tokens added with sensible 0 defaults. input_tokens
retains its current semantic (provider-side LLM tokens) — the plan's
proposed `provider_input_tokens` was omitted because input_tokens
already serves that purpose and a duplicate would fork queries.
- src/utils/summarizer.py: emit now populates the three new fields from
values already in scope (messages_tokens, previous_summary_tokens,
prompt_tokens). Hoisted prompt_tokens calculation out of the
is_fallback conditional so both the save-summary path and the emit
share one binding — basedpyright couldn't prove the sibling-scope
binding was safe, and the compute is cheap + idempotent.
Tests cover schema bump, defaultable fields, input_tokens semantic
preservation, first-summary edge case, and breakdown round-trip.
493/493 pass.
* feat(telemetry): embedding.call.completed event + call-purpose ContextVar
Adds the final piece of cost-attribution telemetry: per-embedding-call
events covering every provider hit (single + batch + retry attempts).
Embedding calls are real provider spend that was invisible before this
phase; search-heavy paths (dialectic agentic) can produce more embedding
calls than LLM calls, so the new event participates in the shared
HIGH_VOLUME_SAMPLE_RATE.
- src/telemetry/events/llm.py: EmbeddingCallCompletedEvent at v1 with
_volume_class="high_volume". EmbeddingCallPurpose closed enum
(search_memory / search_messages / create_observations / vector_sync /
summary / message_create). Resource id = run:purpose:provider:model:input_count
so per-iteration calls in one agentic run don't collide.
- src/utils/types.py: _embedding_call_purpose ContextVar plus
@contextmanager wrapper. Nesting-safe via ContextVar.reset(token).
Callers wrap embedding-driving operations in
`with embedding_call_purpose("search_memory"): ...` — no changes to
the embedding client signature.
- src/embedding_client.py: _emit_embedding_call wraps each provider hit
with try/finally so success AND error paths emit. Errors propagate
unchanged. Each retry attempt of _process_batch emits its own event.
Unknown call_purpose slugs drop to None (validation against the enum
happens at emit time, not at context-manager-set time).
- src/utils/agent_tools.py: search_memory / search_messages /
search_messages_temporal / create_observations (batch + fallback) all
tag their embedding calls.
- src/crud/representation.py: save_representation tags with
CREATE_OBSERVATIONS; get_working_representation precompute tags with
SEARCH_MEMORY.
- src/crud/message.py: create_messages batch embed tags with
MESSAGE_CREATE; search_messages/temporal fallback tags with
SEARCH_MESSAGES.
Tests cover event shape, enum closure, ContextVar nesting/exception
cleanup, wrapper success+error emission, unknown-purpose graceful
fallback, telemetry-failure isolation. 550/550 pass across the full
telemetry+llm+utils+dreamer+dialectic+deriver+crud test set.
* chore: fix tests
* fix(telemetry): address review findings on stream events, context propagation, and cap detection
Five findings from a post-Phase-7 review (one resolved by the merge from
main, four addressed here):
- src/llm/executor.py: stream-path LLMCallCompletedEvent now fires AFTER
the stream is set up and drained (or on exception), with real duration
and accurate outcome. Previously the event was emitted before
execute_stream() ran and was always recorded as outcome="success" with
duration_ms=0, which silently masked stream-setup and stream-drain
failures. Wrapping the async generator in try/finally surfaces the real
outcome; token counts stay 0 because we still don't have them at stream
end (aggregate envelopes carry totals).
- src/deriver/deriver.py + src/utils/summarizer.py: deriver and summarizer
LLM calls now thread LLMTelemetryContext into honcho_llm_call. Before
this, the closed CallPurpose enum had DERIVER_REPRESENTATION /
SUMMARY_SHORT / SUMMARY_LONG slugs but those production call sites
didn't actually pass `telemetry=`, so their LLMCallCompletedEvents lost
workspace_name, parent_category, and call_purpose. summarizer threads
workspace_name through _create_and_save_summary → _create_summary →
create_short_summary / create_long_summary.
- src/utils/types.py + src/embedding_client.py: embedding_call_purpose
ctx manager now accepts workspace_name and run_id kwargs, backed by
two new ContextVars. EmbeddingCallCompletedEvent's publisher reads
both via get_embedding_workspace_name / get_embedding_run_id so
embedding events carry workspace and run correlation. All call sites
updated: search_memory / search_messages / search_messages_temporal /
_handle_create_observations_impl pass ctx.workspace_name +
ctx.run_id; create_observations standalone and create_messages pass
workspace_name; RepresentationManager.save_representation and
get_working_representation pass self.workspace_name.
- src/deriver/queue_manager.py: hit_batch_token_cap detection rewritten.
Previously summed kept-rows' token_count and checked against
batch_max_tokens, but the SQL filter `cumulative_token_count <= cap`
guarantees kept rows stay under the cap, so the flag almost never
fired. Now uses two follow-up queries: total token_count across the
included id range + EXISTS check for any session message past the
last-kept id. Both true → cap was actually binding.
(The fifth finding — deriver scaffold-token computation needing
estimate_deriver_prompt_tokens(custom_instructions) — was resolved by
the merge from main; the Phase 4 emit at src/deriver/deriver.py:283
already sources prompt_scaffold_tokens from the wrapped helper.)
567/567 telemetry+llm+utils+dreamer+dialectic+deriver+crud tests pass.
ruff + basedpyright clean.
* chore: ruff linting
* chore: clean AI generated comments references specs
* fix: address coderabbit changes
* fix(telemetry): address remaining PR review findings
Six findings from the PR 637 telemetry review batched into one commit.
- src/llm/executor.py + src/embedding_client.py: asyncio.CancelledError
now surfaces as outcome="cancelled" on both stream and sync paths,
distinct from "error". Client disconnects mid-stream and server
shutdowns are normal control flow and should not feed error-rate
alerting. LLMCallCompletedEvent and EmbeddingCallCompletedEvent
outcome Literal extended; docstrings + tests cover the new state.
- src/utils/types.py + src/llm/tool_loop.py: new iteration_scope()
context manager captures and resets the four per-tool-loop
ContextVars (_current_iteration, _current_tool_call_seq,
_current_provider_tool_call_id, _last_tool_metadata). Applied as a
typed decorator to execute_tool_loop so back-to-back loops in the
same asyncio Task (worker batches, tests) don't observe stale state.
- src/telemetry/events/api.py + src/routers/messages.py:
MessageCreatedEvent schema v1 → v2. Added required last_message_id
(nanoid public_id of the trailing message); get_resource_id now keys
on it instead of message_count, eliminating the collision case where
two same-size batches in the same session+source produced identical
event ids. message_count stays on the body for analytics.
- src/deriver/queue_manager.py: hit_batch_token_cap now computed from
the FINAL post-config-filter batch. Previously the flag used the
pre-filter messages_context[-1].id, which produced false positives
when _resolve_batch_configuration trimmed the trailing queue item —
telemetry reported a cap-hit when the actual returned batch was
short for unrelated reasons. Cap-detection block moved inside the
async with after the filter; no extra DB connection.
- src/config.py + src/telemetry/emitter.py: documented the
HIGH_VOLUME_SAMPLE_RATE orphan trade-off (rate<1.0 keeps aggregates
but drops children, so JOIN ON run_id queries see partial traces).
Behavior unchanged — rate defaults to 1.0.
- src/deriver/deriver.py: WARNING-level invariant logs when
response.input_tokens < messages_tokens (provider tokenization
drift) or prompt_scaffold_tokens <= 0 (estimator silent failure).
Best-effort — telemetry never bleeds into the deriver path
* fix(telemetry): stream retry, embed attempts, truncation, dedup
Address remaining audit findings on the cloudevents PR:
- Stream setup now runs inside the awaited honcho_llm_call_inner so
tenacity's retry wrapper in stream_final_response catches transient
setup failures (rate-limit, auth, network). Previously the returned
generator deferred execute_stream until first iteration — outside
the retry wrapper — crashing the request and bypassing telemetry.
- Embedding _emit_embedding_call gains an is_final_attempt parameter;
_process_batch threads the real retry index so dashboards stop
conflating one-shot, mid-retry, and exhausted-retry calls.
- _truncate_tool_output returns (text, original_chars, was_truncated)
and a new _maybe_truncated_result helper wraps in ToolResult when
truncation happens. Five handlers migrated. AgentToolCallCompletedEvent
fields was_truncated and result_chars_before_truncation are now
populated instead of always None/False.
- execute_tool_loop tracks any_iteration_truncated and stamps
input_was_truncated on the final response (both HonchoLLMCallResponse
and StreamingResponseWithMetadata). Dialectic now reports
hit_input_token_cap correctly.
- GetContextEvent.get_resource_id uses empty-string sentinel instead
of literal "none" so a peer named "none" can't collide with absent.
- generate_event_id folds honcho_version into the deterministic id so
same logical event from different deploys produces distinct ids.
* fix(telemetry): address audit findings across LLM/embed/event paths
Three rounds of telemetry audit findings, grouped by area:
Retry correctness
- Stream LLM setup now runs inside the awaited honcho_llm_call_inner so
tenacity's outer retry catches setup failures (Fix 1). Previously the
inner generator deferred execute_stream past the retry wrapper.
- stream_final_response bumps the per-retry attempt index via
dataclasses.replace so emitted events show [1, 2, 3] instead of
[1, 1, 1] (Fix 13).
- Embedding _emit_embedding_call takes is_final_attempt; _process_batch
threads the real retry index (Fix 2).
Token + cost reporting
- HonchoLLMCallResponse.hit_input_token_cap (renamed from
input_was_truncated) uses a token-based rule so single-message
over-cap inputs are correctly flagged — the deriver's prompt-only
path used to silently fly through. Propagated through tool_loop's
per-iteration check (Fix 4) and into RepresentationCompletedEvent.
- DialecticCompletedEvent gains hit_input_token_cap; output_tokens now
folds in the final-stream's cumulative usage via
StreamingResponseWithMetadata.__aiter__ (Fix 7).
Event emission completeness
- AgentToolCallCompletedEvent's was_truncated /
result_chars_before_truncation populated by _truncate_tool_output via
a new _maybe_truncated_result wrapper; 5 handlers migrated (Fix 3).
- DreamSpecialistEvent emits on failure with success=False + new
error_class field, via try/finally (Fix 11).
- DeletionCompletedEvent emits on failure paths via try/finally
(Fix 12).
- CleanupStaleItemsCompletedEvent.queue_items_cleaned populated from
deleted_count (Fix 8).
Embedding call attribution (Fix 9)
- embedding_call_purpose context manager accepts parent_category.
- 4 new EmbeddingCallPurpose enum values: DIALECTIC_PREFETCH,
SESSION_CONTEXT_SEARCH, PREFERENCE_EXTRACTION, GENERIC_DOCUMENT_SEARCH.
- Wrapped previously-unattributed sites: dialectic prefetch, session
context search, preference extraction, conclusions search, vector
sync (×2).
Deterministic event ID + dedup
- generate_event_id folds honcho_version into the hash so cross-deploy
events don't silently collide on ID (Fix 6).
- GetContextEvent resource_id uses empty-string sentinel instead of
"none" so a peer literally named "none" can't collide (Fix 5).
Queue batch cap detection (P2.1)
- hit_batch_token_cap keys on the pre-config-filter SQL boundary so the
"kept=900 of 1000 cap, next=300 excluded by cap" case reports True
while still avoiding the config-filter false positive.
Tool result metadata
- search_messages_temporal returns ToolResult with the same search_meta
shape as search_memory / search_messages (P2.3) — top_k,
used_embedding, embedding_query_count, query_tokens, results_count.
Tests: stream-setup retry, stream-retry attempt sequence, post-stream
output_tokens write-back, is_final_attempt matrix, truncation E2E,
tool-loop hit_input_token_cap propagation, honcho_version in event id,
GetContextEvent disambiguation, queue_items_cleaned round-trip.
* fix(telemetry): address audit findings across LLM/embed/event paths
Four rounds of telemetry audit findings (initial + 3 follow-ups), grouped
by area:
Retry correctness
- Stream LLM setup now runs inside the awaited honcho_llm_call_inner so
tenacity's outer retry catches setup failures (Fix 1). The inner
generator previously deferred execute_stream past the retry wrapper.
- stream_final_response bumps the per-retry attempt index via
dataclasses.replace so emitted events show [1, 2, 3] instead of
[1, 1, 1] (Fix 13).
- Embedding _emit_embedding_call takes is_final_attempt; _process_batch
threads the real retry index (Fix 2).
Token + cost reporting
- HonchoLLMCallResponse.hit_input_token_cap (renamed from
input_was_truncated) uses a token-based rule so single-message
over-cap inputs are correctly flagged — the deriver's prompt-only
path used to silently fly through. Propagated through tool_loop's
per-iteration check (Fix 4) and into RepresentationCompletedEvent.
- DialecticCompletedEvent gains hit_input_token_cap; output_tokens now
folds in the final-stream's cumulative usage via
StreamingResponseWithMetadata.__aiter__ (Fix 7).
Queue batch cap detection
- hit_batch_token_cap previously required total_in_range >= cap, which
produced false negatives whenever the kept range didn't fully exhaust
the budget. Replaced with a pre-config-filter SQL boundary check
(P2.1), then further refined to a queue-item boundary comparison
(Fix 14) so trailing-context trimming doesn't false-negative either.
Event emission completeness
- AgentToolCallCompletedEvent's was_truncated /
result_chars_before_truncation now populated by _truncate_tool_output
via _maybe_truncated_result; 5 handlers migrated (Fix 3).
- DreamSpecialistEvent emits on failure with success=False + new
error_class field, via try/finally (Fix 11). except BaseException
catches cancellations too (Fix 16).
- DeletionCompletedEvent emits on failure paths via try/finally
(Fix 12), and uses ValidationException for unsupported types per
project guideline (Fix 17).
- CleanupStaleItemsCompletedEvent.queue_items_cleaned populated from
deleted_count (Fix 8).
Embedding call attribution (Fix 9)
- embedding_call_purpose accepts parent_category.
- 4 new EmbeddingCallPurpose values: DIALECTIC_PREFETCH,
SESSION_CONTEXT_SEARCH, PREFERENCE_EXTRACTION, GENERIC_DOCUMENT_SEARCH.
- Wrapped previously-unattributed sites: dialectic prefetch, session
context search, preference extraction, conclusions search, vector
sync (×2).
Reconciler no longer holds DB session during embedding (Fix 15)
- _sync_documents and _sync_message_embeddings refactored into
three phases per CLAUDE.md guideline: fetch+detach in a small DB
scope, external embedding call without DB locks, writes in a fresh
short-lived DB scope. New _apply_*_sync helpers; orchestrators
expunge ORM objects before invoking. Vector store upsert + sync_state
updates stay in the apply phase together.
Deterministic event ID + dedup
- generate_event_id folds honcho_version into the hash so cross-deploy
events don't silently collide on ID (Fix 6).
- GetContextEvent resource_id uses empty-string sentinel instead of
"none" so a peer literally named "none" can't collide (Fix 5).
Tool result metadata
- search_messages_temporal returns ToolResult with the same search_meta
shape as search_memory / search_messages (P2.3).
- Dialectic.prefetched_conclusion_count uses Representation.len() so
inductive + contradiction observations count too (Fix 10).
* fix(telemetry): orchestrator emit + review feedback
Three more rounds of audit findings + inline PR review, grouped:
Orchestration / emit reliability
- run_dream wrapped in try/finally so DreamRunEvent always emits, even
on unexpected exceptions including CancelledError (`finally` still
runs while cancellation propagates). Specialist except clauses
broadened from SpecialistExecutionError (never raised in src/) to
Exception so provider/DB/tool failures are recorded with
deduction_success=False / induction_success=False instead of crashing
past the emit.
- BaseSpecialist.run() telemetry state initialization + try/finally
hoisted above the preflight phase (peer lookup, peer-card preload,
create_tool_executor, get_model_config, prompt construction) so
preflight failures emit DreamSpecialistEvent(success=False) instead
of being dropped on the floor.
- Reverted the Round-4 _sync_documents / _sync_message_embeddings
phase split. The split introduced a race: rows were released from
FOR UPDATE SKIP LOCKED before the embed call, allowing two workers
to claim and clobber the same batch. Long-held DB transaction
restored (pre-existing CLAUDE.md violation accepted as a deliberate
trade-off; proper fix requires a claim/in_flight migration tracked
separately).
Schema + naming (PR-internal — none of these have shipped)
- threshold_reason → trigger_reason on DreamRunEvent, DreamPayload, and
every emit/scheduler/router/test call site (~45 src + 21 test lines).
Name now accurately reflects the field's role across "manual",
"surprisal", and "document_threshold" values.
- MessageCreatedEvent reset to schema v1 (was internally bumped to v2
for last_message_id but never shipped at v1 — downstream sees it
for the first time at merge).
- DreamSpecialistEvent gains created_counts_by_level /
deleted_counts_by_level: dict[str, int] keyed on the closed
level taxonomy. Per-tool-call events use list[str] (≤10 items),
but specialist runs aggregate 20+ — dict keeps emissions compact.
- QueueBatchResult marked frozen=True.
Per-call embedding attribution
- Agent tool embedding_call_purpose wraps for search_memory,
search_messages, search_messages_temporal, create_observations now
driven embedding cost rolls up under the right workflow.
- create_observations() signature gains parent_category kwarg
(mirrors existing run_id pattern).
Manual dream scheduling
- Manual /schedule_dream route now passes trigger_reason="manual" and
delay_reason="immediate". Previously both arrived as null in
DreamRunEvent, breaking analytics joins.
Queue-batch SQL perf
- next_exists_check folded into the main CTE query via
bool_or(cumulative_token_count > batch_max_tokens) OVER () in a
nested subquery. Cap detection is now one roundtrip per batch
instead of two.
Code/doc cleanup
- representation.py docstring uses generic "downstream metering key"
language (was "Xatu's Stripe meter"). bench runner --base-url help
uses a generic example host (was "groudon.fly.dev"). Public-facing
code/docs shouldn't reference internal service names.
Tests added for: orchestrator failure-path DreamRunEvent emission,
specialists preflight try/finally coverage, manual-dream
trigger_reason/delay_reason round-trip, dict-rollup accumulation across
multiple tool calls in a specialist run, CTE-fold one-roundtrip
behavior. Full Python suite passes (1236).
* fix(telemetry): correctness + attribution + emitter robustness
- Dreamer iteration count: read response.iterations directly so
one-shot runs no longer report iterations=0 and tool-using runs
include the terminal/synthesis LLM call.
- RepresentationCompletedEvent.observer_count counts successful
saves, not attempts.
- search_memory empty-memory fallback reports the snippet count when
message context is returned (was always 0).
- Wire parent_category through every embedding emit path: message
create (api), save_representation (representation), per-observation
fallback (caller-supplied), and the peer/session context routes
(api). get_working_representation accepts parent_category and
embedding_purpose so the internal fallback embed lands in the same
analytics bucket as the route-level precompute even when the
precompute is suppressed.
- BatchItem carries token_count so _process_batch reuses chunk-prep
counts instead of re-encoding every chunk for the telemetry proxy.
- Drop vestigial EmbeddingCallCompletedEvent.batch_size (always ==
input_count).
- Emitter: release the lock during HTTP send so a failing endpoint's
retry+backoff (~36s worst case) doesn't block other flushers;
edge-trigger the 80%-capacity warning so sustained backpressure
doesn't flood logs; defer event_id generation past the high-volume
sampler for events with run_id so sampled-out children don't pay
the sha256; harden emit() against sync callers with no running
loop; track threshold-flush tasks so shutdown() drains in-flight
sends before closing the HTTP client.
* fix(telemetry): tool cancellation emit, nanoid run_ids, version unification
- execute_tool: wrap post-work in finally so AgentToolCallCompletedEvent
fires on CancelledError; explicit handler sets is_error/result_str
before re-raising.
- run_id: replace str(uuid.uuid4())[:8] with generate_nanoid() across
dialectic/dreamer/specialists; matches project-wide nanoid convention.
- Bump _schema_version on events touched by run_id widening:
DialecticCompletedEvent v1→v2 (also covers hit_input_token_cap field),
AgentIterationEvent v1→v2, AgentToolConclusionsCreatedEvent v1→v2,
AgentToolConclusionsDeletedEvent v2→v3, AgentToolPeerCardUpdatedEvent
v1→v2.
- Unify honcho_version: single HONCHO_VERSION constant in src/_version.py
read from pyproject.toml (importlib.metadata fallback). Drop
TELEMETRY.HONCHO_VERSION setting. Use the constant for the FastAPI app
version (no more hardcoded "3.0.6") and for emitter body injection.
- Delete 17 tautological per-event test_schema_version methods; the
parametrized contract test still enforces version >= 1 across all events.
---------
Co-authored-by: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
* feat(embedding): add dimensions_mode for OpenAI dimensions= forwarding
Add EMBEDDING_MODEL_CONFIG__DIMENSIONS_MODE (auto|always|never) controlling
whether the dimensions= parameter is forwarded on OpenAI embeddings.create
calls. auto (default) sends it when the operator explicitly set
EMBEDDING_VECTOR_DIMENSIONS and the configured model is not on the
known-rejecting allowlist (currently text-embedding-ada-002).
The provenance check (was VECTOR_DIMENSIONS explicitly set?) lives as
EmbeddingSettings.resolve_send_dimensions() because it needs access to
model_fields_set, which the standalone resolver does not have. The
resolved boolean is passed into _EmbeddingClient at construction time;
the client never inspects mode or provenance.
Also pins cloudevents <2.0 — 2.0.0 reorganized the package and dropped
cloudevents.conversion and cloudevents.http, which src/telemetry/emitter.py
imports. The original `>=1.12.0` constraint allowed the broken 2.0 resolve.
With the pin, the imports resolve cleanly and the basedpyright warning
cascade (37+ warnings about unknown types) disappears.
Drive-by cleanups (all unnecessary cast/ignore comments flagged by
basedpyright after the cloudevents downgrade):
- vector_store/lancedb.py, tests/conftest.py, and
tests/deriver/test_vector_reconciliation.py — drop dead pyright ignores
- sdks/python/src/honcho/http/{async_,}client.py — drop unnecessary
cast(datetime, ...) (parsedate_to_datetime already returns datetime)
- vector_store/turbopuffer.py — cast(Any, rows) for the upsert_rows
TypedDict that the SDK exposes but our row builder doesn't satisfy
- tests/test_datetime_parsing.py — ignore reportArgumentType on the
test that deliberately passes wrong types to assert raises
* feat(models): honor EMBEDDING_VECTOR_DIMENSIONS in pgvector columns
* feat(startup): atomic swap dim-vs-MIGRATED guard for runtime schema validator
Add src/startup/embedding_validator.py that introspects the actual pgvector
column dim at boot and refuses to start if it does not match
EMBEDDING_VECTOR_DIMENSIONS. Runs after the DB pool is up and before the
embedding client is constructed, in both src/main.py (FastAPI lifespan) and
src/deriver/__main__.py.
Implementation details:
- Schema-qualified pg_attribute join through pg_class/pg_namespace respects
DB.SCHEMA rather than relying on search_path
- Bounded retry (3 attempts, 1s backoff) for transient introspection failure,
then fail-closed with "could not validate embedding schema" — uncertainty
is not a green light to serve traffic
- External-store sampler (turbopuffer, lancedb) enumerates workspaces from
the application DB and probes their lazy-created namespaces; current
per-namespace probe is a no-op stub since the SDKs do not expose
uniform dim introspection — full enumeration is left to
`configure_embeddings --report` in Phase 3
Atomic guard swap: deletes the old dim-vs-MIGRATED config validator (which
forbade non-1536 pgvector unless MIGRATED=True) in the same commit as the
new runtime validator. There is no release window where non-1536 pgvector
can start unprotected. The 9 dual-write branches that use VECTOR_STORE.MIGRATED
remain untouched and load-bearing for legacy-tenant backend swaps.
VECTOR_STORE_DIMENSIONS deprecation: drop the "must match" raise; in
propagate_namespace, check model_fields_set and emit logger.warning +
DeprecationWarning (DeprecationWarning alone is filtered by Python's default
config and would not reach operators). Always overwrite with
EMBEDDING.VECTOR_DIMENSIONS regardless.
Test changes:
- tests/test_models_vector_dim.py: Phase 1's VECTOR_STORE_TYPE=lancedb +
MIGRATED=true escape hatches removed; the test now passes on plain
EMBEDDING_VECTOR_DIMENSIONS=768
- tests/llm/test_model_config.py: the two tests asserting the old guards
replaced with tests for the new deprecation + acceptance behavior
- tests/startup/test_embedding_validator.py: 10 new tests — dim assertion
logic (pass/mismatch/missing/unbounded/non-public-schema), fail-closed
retry budget, real-test-DB pass, real-DB ALTER-then-validate, deprecation
warning capture, non-1536 + pgvector + MIGRATED=false at config time
* feat(scripts): add configure_embeddings bootstrap CLI
Adds scripts/configure_embeddings.py alongside the other one-off scripts
(provision_db, migrate_db, generate_jwt_secret, etc.). Invoked as
`uv run python scripts/configure_embeddings.py` — same convention as the
existing scripts in that directory, including the sys.path shim that
lets src.* imports resolve when run directly.
Bootstrap step for self-hosted installs at a non-default
EMBEDDING_VECTOR_DIMENSIONS — runs between `alembic upgrade head` and
starting the API/deriver.
pgvector ALTER safety (single transaction):
- LOCK TABLE {schema}.documents, {schema}.message_embeddings IN ACCESS
EXCLUSIVE MODE — closes the TOCTOU window between population check
and ALTER
- COUNT(*) WHERE embedding IS NOT NULL on both tables; refuse with a
non-zero exit if either is populated (ALTER ... USING NULL would
silently wipe those vectors)
- Snapshot HNSW index DDL from pg_indexes; drop, ALTER, recreate from
the captured DDL so operator-set HNSW params (m, ef_construction)
survive the round trip
External vector stores (turbopuffer, lancedb) are never created or
modified — namespaces are per-workspace and lazy-created on first write.
The --report mode enumerates workspaces and collections from the
application DB, derives the expected namespaces via
get_vector_namespace(), and prints a per-namespace status table.
CLI modes (mutually exclusive):
- (default) interactive: print plan, prompt to confirm
- --dry-run: print plan and exit 0 without touching the DB
- --yes: apply without prompt
- --report: print external-store namespace inventory and exit
Also updates src/startup/embedding_validator.py error-message paths and
docs/v3/contributing/configuration.mdx invocations to point at the new
script location.
Tests cover plan no-op, plan needs-alter, plan raises on missing column,
ALTER + HNSW round-trip, refuse-when-populated (monkeypatched count to
avoid wiring the full workspace/peer/collection/document FK chain just
to land one vector row), and idempotency.
* docs: add changing-embeddings operations page
Document the supported way to change EMBEDDING_VECTOR_DIMENSIONS or
EMBEDDING_MODEL_CONFIG__MODEL on a Honcho deployment: provision a new
deployment at the desired configuration, replay source data out of
band, cut over at the application layer.
The page explains the asymmetry:
- Dimension is machine-enforced as immutable. The startup validator
introspects pg_attribute and crashes the API/deriver on mismatch.
- Model is operator-owned. There is no persistent metadata recording
which model produced each vector, so a same-dim model swap is
silently undetectable — flagged with a Warning callout.
Also documents the truncation edge case (text-embedding-3-large truncated to 1536 with EMBEDDING_VECTOR_DIMENSIONS left at default)
and the DIMENSIONS_MODE=always mitigation, plus a pointer that
storage-backend swap (VECTOR_STORE_MIGRATED + reconciler) is a distinct operation unaffected by this work.
Registers the page in docs/docs.json under the Self-Hosting nav group
and cross-links from configuration.mdx.
* fix(embedding): correct turbopuffer regex + tighten DIMENSIONS_MODE docs
- Turbopuffer attribute type for a vector column is `[N]f32` / `[N]f16` /
`[N]i8`, not `f32_vector(N)` as the earlier probe assumed. The earlier
regex returned None for the real SDK format, so existing Turbopuffer
namespaces would have been reported as "missing" instead of validated
for mismatch. Regex switched to `\[(\d+)\]` which is the
vendor-stable shape. Test cases rewritten to lock the actual format.
- docs/v3/contributing/configuration.mdx had a contradictory pair of
bullets: 223 said explicit 1536 makes `auto` forward dimensions=, 224
said `auto` would skip the parameter because 1536 is the default.
Operators reading both would (rightly) conclude they need `always`
even when `auto` would work. Rewrote both bullets so:
- `auto` is provenance-driven (explicit-set, not non-default-value).
- `always` is positioned as defense-in-depth for config layers that
might strip explicit default-valued envs, not the only path for
same-as-default truncation.
* fix(embedding): address PR #678 review comments
CodeRabbit + Rajat review feedback. All actionable items addressed
except two false-positives (responded on PR).
Bug fixes:
- deriver telemetry leak: validator was called outside try/finally so
shutdown_telemetry() did not run on validation failure. Moved inside.
- _emit_report printed "no effect with pgvector" unconditionally,
including from implicit post-apply calls. Added is_report_mode flag;
only print on explicit --report.
- LanceDB and Turbopuffer probes returned None when the namespace
existed but its schema was malformed (no vector field / unparseable
type string), silently bucketing real corruption as "missing"
(lazy-create) and letting it pass the startup validator. Now raise
VectorStoreError with actionable diagnostics; None remains valid only
for "namespace does not exist."
- Startup validator only sampled message namespaces; added a parallel
Collection-row sample so document namespaces are probed too, with the
same dim assertion. Mirrors the --report path.
Hygiene:
- StartupValidationError now subclasses HonchoException so existing
exception handlers recognize it. ValidationException is @final and
has 422 request-validation semantics that would be misleading here.
- scripts/configure_embeddings.py main() no longer spins up two event
loops. engine.dispose() moved into a try/finally inside _async_main
so cleanup runs in the same loop as the pipeline.
- Replaced hand-rolled retry loop with tenacity.AsyncRetrying; same
fail-closed semantics, less code, before_sleep_log for visibility.
- Added _validate_identifier() defense-in-depth: DB.SCHEMA and HNSW
index names are regex-checked against [A-Za-z_][A-Za-z0-9_]* before
SQL interpolation. Operator config + DB catalog are not user input
under the current threat model, but the constraint is cheap to gate.
Test + docs:
- test_app_settings_accepts_non_1536_with_any_vector_store_configuration
now actually exercises turbopuffer (was missing); supplies a dummy
TURBOPUFFER_API_KEY to satisfy the model_validator.
- changing-embeddings.mdx: hyphenated "out-of-band" per reviewer style.
* fix: modify conftest to fix ci
* fix: ci tests for typescript server
* docs(readme): repositioning pass + staleness fixes (P0-P4 audit)
Restructure README to match dual audience (AI-tool users + product
developers) per Vineeth's audit. No content deleted - long internal
sections collapsed under `<details>` for scannability.
Staleness fixes:
- Replace 404'd doc links (.../tutorial/SDK, /api-reference/introduction)
with verified replacements under /v3/documentation/reference/sdk
and /v3/api-reference/introduction
- Fix Python quickstart to pass api_key (managed default api.honcho.dev
would 401 otherwise)
- Drop hardcoded `gpt-4` model reference; read OPENAI_MODEL from env
- Replace archived Dialectic blog link with current Chat Endpoint docs
- Drop M3-Macbook-specific note; minor grammar ("deriver's" -> "derivers")
- Replace TL;DR Python-only example with side-by-side Python + TypeScript
framed around the "Honcho Loop" (store / reason / query / inject)
New sections:
- Start Here: three-path table (AI tools / building product / self-host)
- The Honcho Loop: operation model before code
- What Honcho Gives You: API-at-a-glance table
- Integrations: verified install commands for Claude Code (plugin + raw
MCP), OpenCode, OpenClaw, Hermes
- Honcho vs RAG: stubbed with TODO; copy deferred to marketing
- SDKs section with clearer Python/TypeScript landing pointers
Restructured:
- Core Concepts moved above Architecture; Collections/Documents reframed
as internal mechanism (Conclusions is the public surface)
- Storage / Reasoning / Retrieving deep-dive wrapped in <details>
- Local Development, Pre-commit hooks, Fly deployment, full config
matrix wrapped in <details>
Known follow-up (not in this branch): SDK docs at docs.honcho.dev and
PyPI PKG-INFO advertise `HONCHO_BASE_URL`, but the actual SDK code
(sdks/python/src/honcho/client.py:234, sdks/typescript/src/client.ts:154)
reads `HONCHO_URL`. README aligned with code; docs + PKG-INFO need
separate fix.
* docs(readme): restore "stateful agents" in opening sentence
Plastic Labs' canonical positioning uses "stateful agents" across
materials, and the original README opened with "for building stateful
agents." The repositioning pass in d6d60435 dropped the term entirely
(now zero occurrences) by following Vineeth's suggested opening copy
verbatim - but his audit's executive summary explicitly praised the
"stateful agents" positioning and didn't ask to remove it. Restoring
it in the bolded thesis sentence.
* docs(readme): drop self-referential "observations" in Conclusions bullet
The Conclusions definition shouldn't define itself in terms of
"observations." Per Plastic's positioning, "conclusions" is the
documentation-facing name for what the Deriver produces;
"observations" remains the internal code symbol. The README's
two remaining "observations" references (inside the <details>
Internal storage block and the Storage primitives block) are
explicit code-internal framing and stay.
* docs(readme): restore content dropped without audit instruction
Self-audit against Vineeth's audit found seven items I'd dropped that weren't in the audit's instructions to drop: outcome-marketing line, Contents TOC (audit said rename, not remove), multi-repo prose, org-onboarding detail, peer-paradigm feature bullets, Architecture "Key Features" bullets, and Learn More pointers. Also fixes two residual "Dialectic API" → "Chat Endpoint" mentions the original P0 sweep missed.
* docs(readme): add "Why Honcho" capability table + agent-skill onboarding
Closes the two gaps flagged in the freshness/repositioning audit: adds Vineeth's recommended "Why Honcho" capability table between Start Here and The Honcho Loop, and adds the `npx skills add plastic-labs/honcho` + `/honcho-integration` agent-skill path as a subsection of Integrations (verified against current docs).
* docs: split contributor-only sections out of README; trust auth for local postgres
- Move pre-commit hooks setup from README to CONTRIBUTING.md (pure
contributor content; the README still links to it).
- Move Fly.io deployment notes from README to the self-hosting docs.
- Wrap remaining <details>/<summary> blocks with markdownlint
disable/enable to clear pre-existing MD033/MD001 failures.
- Add POSTGRES_HOST_AUTH_METHOD=trust to the example compose template
with an inline warning, so host-side tests and tooling can connect
without supplying a password.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: (docs) update docs and evals urls and split pre-commit into contributing docs
---------
Co-authored-by: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: refresh CLAUDE.md to match current architecture
Bring the project CLAUDE.md in line with the codebase as of main:
- API prefix /v1 -> /v3; add Conclusions + Webhooks to route listing;
note that Collections/Documents are now partially exposed via the
Conclusions API
- New Runtime Architecture section describing the API server / deriver
worker split and the in-process Reconciler scheduler
- Rewrite Agent Architecture:
* Deriver - "minimal" single-LLM-call architecture (no agentic tool
loop); current entry point and prompts
* Dialectic - actual DIALECTIC_TOOLS list, 5 reasoning tiers,
DIALECTIC_TOOLS_MINIMAL for the minimal level
* Dreamer - orchestrator + DeductionSpecialist + InductionSpecialist,
surprisal-based prioritization, reasoning trees
* Summarizer documented as a distinct agent
- Refresh project structure tree: add cache/, llm/ (+backends/),
reconciler/, telemetry/, vector_store/; correct schemas/ (now a
directory); drop nonexistent dialectic/agent/, deriver/agent/,
dreamer/agent.py + dreamer.py
- Architectural decisions: fill in the missing #2 (Peer Paradigm); add
hybrid search (FTS + vector), pluggable external vector stores,
composite-FK multi-tenancy, dialectic reasoning tiers
* docs(CLAUDE.md): rename "observations" -> "conclusions" in agent prose
Per Plastic's positioning, "conclusions" is the documentation-facing
term for what the Deriver produces; "observations" remains the
internal code-symbol vocabulary (`create_observations`,
`get_observation_context`, etc.). Swap conceptual prose, preserve
all backticked code references.
- New terminology callout at the top of Agent Architecture so the
mapping is explicit for coding agents reading this file
- Deriver/Dreamer prose: observations -> conclusions for the abstract
noun; specialist tool lists keep their `get_recent_observations`,
`create_observations_deductive`, etc. unchanged
- Reasoning-trees bullet rephrased to "each conclusion links to its
premises and downstream conclusions" (the original "observations
link to premises/conclusions" becomes recursive after the swap;
rephrasing makes intent clearer)
- Tree comment for surprisal.py updated to prose-style "conclusion
prioritization"
Companion to a3fa16ef on kass/readme-refresh, which made the same
swap in the README's Conclusions definition.
* docs(CLAUDE.md): align "Dialectic API" with README's "Chat Endpoint" rename
Two spots framed the public surface as "Dialectic API" — preserve the code-agent name (Dialectic) while matching the documentation-facing "Chat Endpoint" we standardized on in the README.
* chore: nits in CLAUDE.md
---------
Co-authored-by: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
The previous mutual-exclusion check compared --test-dir against its
default string literal, so passing --test-file together with an
explicit --test-dir tests/unified/test_cases silently bypassed the
check. Replace with argparse.add_mutually_exclusive_group() and apply
the default path post-parse so the bare invocation still works.
Add "Use the Skill" section recommending `npx skills add plastic-labs/vercel-ai-sdk`
with the manual symlink approach as a collapsed alternative.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* docs(integrations): add @honcho-ai/vercel-ai-sdk guide
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(integrations): rewrite Vercel AI SDK guide as cookbook style (DEV-1485)
Reshapes the guide to cookbook formula, adds Full Script section, fixes
maxSteps → stopWhen for ai-sdk v5, renames package, and prunes stale notes.
See PR for full decision log.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(integrations): lead Vercel AI SDK verification with direct-inspection check
- Restructure Verifying section: direct inspection (token delta + dashboard) is now step 1 so readers isolate Honcho's contribution before grading model behavior
- Behavioral tests (first turn, multi-turn, cross-session, tool calling) follow as steps 2-5
- Note `result.toolCalls` as the way to confirm which Honcho tool fired (tool names don't appear in `result.text`)
- Signpost the Full Script from Complete Example so the two snippets read as a staircase, not a duplicate
Addresses review comments on PR #635.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(tests): satisfy basedpyright in test_representation_manager
The save-representation tests added in #615 were structurally correct but
failed strict typing in two places. Static Analysis has been red on main
since the merge.
- `mock_save.await_args` is `_Call | None`; assert it's not None before
reading `.kwargs` / `.args` so basedpyright can narrow the type
- `SimpleNamespace(...)` passed as `message_level_configuration` is an
intentional duck-typed mock (only `.dream.enabled` is read by
`save_representation`), so opt out at the call site with
`# pyright: ignore[reportArgumentType]` rather than constructing a
full `ResolvedConfiguration` (matches the existing `reportPrivateUsage`
ignore pattern in this file)
No runtime behavior changes; `uv run basedpyright` is now clean
project-wide.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(tests): pad timestamp windows in test_messages for clock skew
Three timestamp tests captured `before_request` / `after_request` with
`datetime.now(UTC)` on the host and asserted the server's `created_at`
fell within. Under Docker, the Postgres container's clock can skew tens
of ms from the macOS host, flipping the assertion intermittently under
parallel pytest load.
Pad each window by 1 second on both sides — wide enough to absorb
realistic skew, narrow enough that the test still proves the timestamp
is server-current.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(integrations): tighten Verifying section after end-to-end smoke
Smoke-tested all five verification steps against a fresh Sonnet 4.6 + Honcho integration. Three findings, all reflected here:
- Cross-session recall (#4): added Note about DERIVER_REPRESENTATION_BATCH_MAX_TOKENS=1024 — short warmups don't accumulate enough content to flush observations, so cross-session recall returns empty even on a working integration.
- Tool calling prompt (#5): replaced the honcho_chat patterns prompt with a verbatim-retrieval honcho_search prompt. Sonnet skips honcho_chat when middleware-injected context already answers; verbatim retrieval forces a fire.
- Tool inspection (#5): replaced result.toolCalls reference with result.steps[i].toolCalls + flatMap snippet. Top-level toolCalls is empty in multi-step calls (stopWhen: stepCountIs(N)) — the fires are nested inside steps.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(integrations): make Step 4 cross-session test durable via honcho_search
Replace the prose-recall test ("Based on what we've talked about, what do you know about me?") with a forced honcho_search call. Prose recall depended on the model getting deriver-built representation/peer-card in its system prompt, which is gated behind DERIVER_REPRESENTATION_BATCH_MAX_TOKENS=1024 — short tutorial-length conversations don't trigger it, producing false negatives on a working integration.
honcho_search hits message embeddings, which are computed synchronously at message persist time (src/crud/message.py:262-276), so peer-scoped retrieval works regardless of how short the prior session was. Also folds the result.steps[i].toolCalls inspection snippet from the old Step 5 into Step 4 — same prompt, no need for two sections.
Drops Step 5 entirely.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(dreamer): threshold and time-guard semantics
Finding 2: filter count_stmt on documents.level == 'explicit' in
check_and_schedule_dream. Dreamer-created levels (deductive, inductive,
contradiction) are consolidation output, not input, and would otherwise
inflate the threshold count and create a feedback loop.
Finding 3 (code-level): relocate last_dream_at write from enqueue_dream
(enqueue.py) to process_dream (orchestrator.py), inside the
'if result is not None' block. Duplicate enqueues can no longer reset
the 8-hour time guard clock. Failed/never-run dreams don't advance it.
Success criteria: lenient (any non-null DreamResult counts). Pending
Vineeth confirmation — will adjust to strict/middle if requested.
Tests pending in follow-up commits.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* test(dreamer): threshold filter + last_dream_at relocation regression tests
Tests for Finding 2 and Finding 3 (code-level):
- TestThresholdFilter (tests/dreamer/test_dream_scheduler.py):
* Mixed levels below explicit threshold: 30 explicit + 40 deductive
+ 10 inductive → no trigger (core regression, buggy count would trigger)
* Explicit-only at threshold: 60 explicit → triggers
* Contradiction excluded: 100 contradiction + 10 explicit → no trigger
(confirms positive == "explicit" filter excludes all dreamer output)
- TestEnqueueDreamMetadataShape (tests/deriver/test_enqueue_dream.py):
* AsyncMock-patched update_collection_internal_metadata verifies
enqueue writes last_dream_document_count but NOT last_dream_at
- TestLastDreamAtCompletionWrite (tests/dreamer/test_dreamer_integration.py):
* Happy path: run_dream returns DreamResult → last_dream_at written
* Failure path: run_dream returns None → last_dream_at absent
* Exception path: run_dream raises → last_dream_at absent,
process_dream swallows exception (queue-processed semantics preserved)
Docstring on check_and_schedule_dream tightened: "document threshold"
-> "explicit-observation threshold" to reflect filter semantics.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(dreamer): preserve last_dream_document_count in completion write
CodeRabbit caught this: update_collection_internal_metadata uses a
top-level JSONB `||` merge, so passing {"dream": {"last_dream_at": ...}}
replaces the entire "dream" subkey and drops last_dream_document_count
that was written by enqueue_dream.
Symptom: after every completed dream, the baseline drops to 0. Next
check_and_schedule_dream reads documents_since_last_dream as
current_count - 0 = current_count, so any collection with >= 50
explicit observations can re-trigger immediately once the 8h guard
expires, even with no new raw material.
Fix: read-modify-write. Fetch current collection, merge last_dream_at
into the existing "dream" dict, write the merged dict back. Preserves
sibling keys (current: last_dream_document_count; future-proof for
telemetry fields that might land in PR 4).
Regression test added to tests/dreamer/test_dreamer_integration.py:
pre-seeds {"dream": {"last_dream_document_count": 42}}, runs
process_dream, asserts both last_dream_at is written AND
last_dream_document_count == 42 is preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(dreamer): address CodeRabbit feedback on b89997c
- enqueue.py: read-modify-write preserves last_dream_at when writing baseline
- dream_scheduler.py: explicit-level filter on execute_dream count query
- test fixture: pin DOCUMENT_THRESHOLD and ENABLED_TYPES for stability
- integration test: timezone-aware assertion on last_dream_at
Regression test added for enqueue sibling-drop (symmetric to c8fe40a).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(dreamer): session lookup symmetry + row lock on dream metadata RMW
- dream_scheduler.py: explicit-level filter on execute_dream session lookup
(baseline and session pick must agree on the same document set)
- crud.collection.get_collection: optional with_for_update flag for callers
that need serialized read-modify-write on internal_metadata
- enqueue.py + orchestrator.py: pass with_for_update=True on the RMW reads
to close the TOCTOU between concurrent enqueue and completion writes
Follow-up filed for jsonb_set-based nested updates (docs/factory/backlog/).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(dreamer): explicit-only count on manual schedule_dream route
The third caller of enqueue_dream — POST /workspaces/{id}/schedule_dream —
was passing an all-levels document count as the baseline, breaking symmetry
with check_and_schedule_dream and execute_dream after Loop 2's filter fixes.
Filter the manual route's count to match.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(dreamer): document explicit-only invariant on enqueue_dream.document_count
Loop 3 follow-up on d76627a. The parameter's semantic tightened across Loop
2 (check_and_schedule_dream, execute_dream) and Loop 3 (schedule_dream route)
to "explicit-level count, used as the baseline," but the signature still read
"Current document count for metadata update." The next caller would have no
way to know from the function contract.
Docstring now spells out: (1) the value is explicit-only, (2) it's written
as last_dream_document_count, (3) it's the baseline that
check_and_schedule_dream subtracts from to compute
documents_since_last_dream, (4) passing a count that includes non-explicit
levels (deductive, inductive, contradiction) inflates the baseline and
suppresses the next scheduled dream.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor(dreamer): rename current_document_count → current_explicit_count
Loop 3 follow-up on d4e10e3. After Loop 2's filter landed, the local in
check_and_schedule_dream held an explicit-only count but was still named
current_document_count — asymmetric with execute_dream's current_explicit_count
(line 201) and contradicting the filter on line 269 that produces the value.
Pure rename: three occurrences (definition at 271, subtraction at 274, log
extra key at 282). No test references. Naming-as-invariant alignment with
d76627a (query filters), d4e10e3 (parameter docstring), and Loop 1's local
rename in execute_dream.
The persisted JSONB key last_dream_document_count is the one remaining
drift-layer; filed as plastic-claudebook backlog item for a separate PR
with an intentional migration path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(dreamer): atomic guard-pair write + in-flight stampede defense
Loop 4 response to Vineeth's CHANGES_REQUESTED on PR #573.
The pre-Loop-4 enqueue-time write of last_dream_document_count was serving
double duty: rate limiter AND stampede latch. By arming the 8h guard the
moment a dream entered the pipeline, it implicitly blocked a second dream
from being scheduled during the in-flight window. Loop 3 relocated the
last_dream_at write to completion without moving its sibling baseline,
splitting the semantic pair and exposing the latch role that had lived
only in Vineeth's head.
Invariant (now pinned to check_and_schedule_dream's docstring): from the
moment a dream is scheduled until it completes or fails, no second dream
may be enqueued for the same (workspace, observer, observed) — and the
baseline count advances only when consolidation actually happened.
Changes:
- enqueue_dream: remove the last_dream_document_count write entirely and
drop the document_count parameter. enqueue no longer touches dream
metadata; the implicit stampede latch is replaced by an explicit
queue-backed defense.
- process_dream: extend the existing row-locked RMW to write both guard
fields atomically. Current explicit-doc count is recomputed inside the
locked block (not carried on DreamPayload) so the pair reflects the
actual consolidation moment.
- check_and_schedule_dream: query QueueItem for pending dreams on this
collection's work_unit_keys (mirrors uq_queue_dream_pending_work_unit_key)
before arming a timer. Uses queue state as source of truth rather than
reflecting it into metadata.
- Tests: two new coherence tests under TestGuardPairCoherence —
test_pending_queue_item_blocks_second_schedule walks the stampede timeline,
test_silent_failure_allows_retry_on_same_corpus verifies failed dreams
don't consume the baseline. Existing tests updated to the new contract.
* chore(dreamer): trim comment slop from loop-4 atomic pair work
Compress three verbose comments added in d24958d — the invariant itself
is captured in check_and_schedule_dream's docstring, so the inline
narrative restates what the code already says.
- dream_scheduler.py defense C block: 5 lines → 2
- orchestrator.py atomic pair write: 4 lines → 1
- enqueue.py docstring paragraph: 5 lines → 2
Net: +5/-14. Follows Eri's eef27be precedent on sillytavern-honcho PR #7.
---------
Co-authored-by: lilyplasticlabs <lily@plasticlabs.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(deriver): ignore blank observations before embedding
* Address PR review on observation normalization
* Harden mock await arg access in tests
* Unify blank observation filtering across tool paths
* Move soft-delete query test back to fixture class
The Surprisal module passes `{"level": levels}` directly to
`get_all_documents()`, but `apply_filter()` expects operator syntax:
`{"level": {"in": levels}}`.
Without the `in` operator, the filter is silently ignored, causing
`_fetch_level_observations()` to return 0 results. This makes the
entire Surprisal phase of the Dream cycle a no-op.
Fixes#559
- New Group Chats subsection: documents per-character peer routing
(each group member gets their own peer, not a collapsed group-<id>
peer) and lazy peer registration for characters joining mid-chat.
- Session Naming: documents the freeze-on-first-assign invariant
(changing the naming mode doesn't reroute existing chats) and
the Reset button for explicit session rollover.
- Tool table: add honcho_save_conclusion — prior fix undercounted
(2 -> 3 tools). The extension registers all three.
The plugin also writes to a root-level `sessions` map (ST dir → last
Honcho session ID), not only to `hosts.sillytavern.*`. The earlier
phrasing overstated the isolation claim.
- Add Prerequisites section with SillyTavern install link + Node >= 18
requirement (was buried in Next Steps; users hit install step with no
awareness ST needed to exist first).
- Expand restart step into a callout: restart required for server-plugin
reload, not for client-side edits.
- Configure step now documents the three editable inputs (API key,
Workspace ID, Your peer name) and where each saves.
- Fix 'three-cubes icon' -> 'puzzle piece icon'.
- Installer step list fleshed out: 6 steps (was 4), including config.yaml
bootstrap and enableServerPlugins flip. Dropped the false claim that
the plugin seeds a minimal ~/.honcho/config.json on first run.
- Global Config section rewritten: resolution order now generalized to
apiKey / workspace / peerName (was apiKey-only); documents panel
write-back to hosts.sillytavern.*; dropped aiPeer references (it's a
telemetry-only field, not user-facing).
- Add a Disable / Enable global config subsection covering the opt-out
toggle and the Inherit / Push local / Cancel diff dialog.
- Troubleshooting: two new rows (stale peer name on new chat, cancelled
diff dialog).
- Clarify installer step 4 — the plugin seeds config.json if absent
- 'Puzzle piece' -> 'three-cubes' for the Extensions icon (current ST UI)
- API key step notes the UI-overrides-config precedence explicitly
- 'Honcho workspace ID' -> 'default Honcho workspace ID (configurable)'
- Add Note after Context-modes table — Context only is session-scoped
and returns empty until enough messages accumulate; Reasoning is the
better default for fresh peers
- Next Steps gains two cards: Install SillyTavern (upstream docs) and
the Claude Code setup skill (skills/setup/SKILL.md)
Follow-ups tracked separately — tool rename (observation -> conclusion,
matching the /conclusion endpoint), architecture Excalidraw.
Vineeth Voruganti
ajspig
adavyas
Rajat Ahuja
Xiangzhe
ShellyBot
Marianne
Lily
Lily
Phil
banteg
Lily
Erosika
Sanjay Santhanam
qxxaa