Commit Graph

134 Commits

Author SHA1 Message Date
Vineeth Voruganti f8e7167bdf fix: Migration naming and long held connection 2026-01-16 13:28:00 -05:00
Rajat Ahuja bc0e8efd2b fix: hash namespace 2026-01-16 11:49:03 -05:00
Rajat Ahuja e5e2a3e082 fix: make workspace_name nullable 2026-01-14 13:18:03 -05:00
Rajat Ahuja d75f000b3c fix: CR / opus comments 2026-01-13 15:46:14 -05:00
Rajat Ahuja cae29b7100 feat: refactor to use ReconcilerScheduler 2026-01-13 15:15:03 -05:00
Rajat Ahuja 9ced00e2d5 fix: add test for migration 7c0d9a4e3b1f 2026-01-13 12:59:24 -05:00
Rajat Ahuja 7c155f99a2 fix: coderabbit comments 2026-01-13 12:55:27 -05:00
Rajat Ahuja 788dc0d51d Merge branch 'main' into rajat/turbopuffer 2026-01-13 12:14:51 -05:00
Rajat Ahuja dc1490e30a fix: shorten reconciliation cycle + fix 'IN' equality check 2026-01-13 12:09:09 -05:00
Rajat Ahuja b38a87088b fix: migration order 2026-01-13 11:13:53 -05:00
Rajat Ahuja 774edc0b6c Merge branch 'main' into rajat/turbopuffer 2026-01-13 10:55:15 -05:00
Rajat Ahuja b04770d602 fix: remove composite and pgvector store -> make more specific 2026-01-12 18:11:22 -05:00
Benjamin McCormick 2c66813944 fix: use real stainless releases, update to match 2026-01-12 17:27:54 -05:00
Benjamin McCormick 5b7ae0d82c feat: API renaming and cleanup
- Rename API routes for consistency
- Add backwards-compatible conclusion and queue endpoints
- SDK cleanup and representation improvements
- Add reasoning_level param validation
- Fix thinking budget validation for Anthropic

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-12 16:50:40 -05:00
doria 578ef2c665
feat: agentic dreamer and agentic dialectic (#309)
* feat: add better params to working representation fetch in SDKs, return messages when added

* fix: working representation routes now accepting all parameters properly, with tests

* feat: add metadata/config fields to SDK objects where viable

* fix: tests

* feat: refactor SDKs to use representation config; [TEMP STAINLESS BUILD] update API

* feat: add representation object to sdks

* fix: use stainless sdk on branch

* fix: update TypeScript SDK tsconfig to use node16 module resolution

* fix: add isolatedModules = true to tsconfig

* fix: lol

* chore: coderabbit review

* feat: make delete session real

* feat: add observations routes with delete endpoints for documents. make session deletion real.

* chore: type cleanup

* fix: tests

* chore: coderabbit review

* fix: namespace by workspace

* feat: add ability to customize messages_per_summary at both workspace and session level

* chore: tests for summary config

* chore: coderabbit cleanup

* feat: make session and workspace config totally customizeable

* feat: add search by peer knowledge (#250)

* feat: search by peer perspective

* fix: enforce workspace in filters, make messages distinct in join

* fix: batch and merge migration steps

* fix: add refresh, add config to workspace, add refresh function, make fields readonly

* fix: search distinct

* fix: merge migrations

* fix: merge migrations

* fix: batch deletions, improve comments, limit consolidate dream to 100 docs at a time, auth on observations routes

* chore: review

* chore: coderabbit

* chore: review

* chore: broken comment

* feat: add set peer card route to API

* feat: create advanced configuration parameters with message>session>workspace hierarchy

* [wip] build unified testing harness

* chore: lint

* fix: cache invalidation, naming things, etc

* feat: longmem tests

* chore: peer config refactor

* feat: consolidate dream working, refactor representation

* fix: Various CR Comment Fixes

* feat: Allow configurable Redis port for harness instances and update cleanup methods to be asynchronous.

* feat: agentic ingestion task!!!

* feat: agentic deriver

* feat: dialectic agent and dreamer agent

* chore: browbeat tests into passing

* fix: nits

* chore: remove old code, update config files

* fix: simplify deriver

* feat: dialectic agent prompt updates, re-introduce non_agent deriver, eval tweaks

* feat: fast deriver, dreamer, then dialectic

* fix: tweaks across the board

* feat: add baseline tests

* feat: truncation in tools and client, tweaks for evals

* feat: add locomo, fix longmem judge!!!

* fix: locomo f1 is trash, use llm judge

* feat: trace creation

* feat: add first draft of obex benchmark, fix embedding model, fix locomo methodology

* fix: locomo session-optimized, better logging of cache usage and better cache usage

* chore: use openrouter for baselines

* fix: add test for merge migration

* chore: opus-powered cleanup

* fix: add config for vllm, better client

* chore: clean up clients.py a bit

* chore: move magic numbers to config, add tests for agent tools

* fix: wrong mock in dialectic tests, make ToolContext a dataclass

* feat: tweak prompts, make deriver explicit-only

* feat: more prompt & tool tweaks

* chore: more tweaks

* feat: dream with subagents

* fix: make dream trigger override scheduled, play around with dream agents

* chore: cleanup deriver

* chore: cleanup dialectic

* chore: cleanup orchestrator

* chore: comment out dream stuff, WIPing

* fix: inc temp on retry, typechecking

* feat: tweak dreaming

* feat: contradiction obs

* Add dream trees

* chore: preserve reasoning_details from openrouter in client

* fix: get_observation_context correct params

* fix: use correct message id in tool

* chore: cleanup longmem runner

* chore: clean up tests, remove dream tests for now as rearchitecting around trees

* chore: update stainless deps

* Update threholding mechanism

* chore: pre-commit hooks whitespace

* chore: clean up types

* feat: add explicit bench

* fix: address additional basepyright issues

* fix: adding logging as a fixture on honcho_llm_call and supporting dialectic loging. (#305)

* fix: lock on db for tool calls

* chore: clean up experimental derivers

* chore: coderabbit review cleanup

* feat: add streaming support to agentic dialectic

* feat: prometheus token tracking for deriver and dialectic

* fix: self-loops for isolated nodes

* chore: PascalCase for prometheus parameter typing

* feat: add reasoning levels to dialectic agent

* chore: delete old file, add new fake env vars in unittest.yml

* fix: all fields needed for dialectic reasoning level configs

* feat: track dreaming usage in prometheus

* chore: Create backwards compatabile conclusion and queue endpoints

* fix: remove redundant try-catch, add trace label, move .limit to end of statement

* fix: remove vignettes (for now), review fixes, remove merge migration, config cleanup

* chore: code review / cleanup

* chore: merge fixes

* chore: clean up, remove reasoning_focus, reintroduce peer cards in dreamers

* chore: code rabbit nitpicks

* fix: add unique index for pending dreams in queue

* fix: revert removal of surprisal in dreamer config

---------

Co-authored-by: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
Co-authored-by: 3un01a <3un01a@plasticlabs.ai>
Co-authored-by: 3un01a <3un01a.labs@gmail.com>
Co-authored-by: ajspig <46900795+ajspig@users.noreply.github.com>
2026-01-12 15:12:17 -05:00
Rajat Ahuja cf804ce790 fix: remove hard-delete from critical path and make PgVectorStore deletions a no-op 2026-01-12 13:14:22 -05:00
Rajat Ahuja 52eaaf3f16 fix: clean-up and migration test 2026-01-08 17:15:38 -05:00
Rajat Ahuja e218ab332f fix: add message embedding resilience 2026-01-08 16:32:43 -05:00
Rajat Ahuja fe10959240 fix: reduce batch size; comments; types; add indexes for reconciliation 2026-01-08 16:09:57 -05:00
Rajat Ahuja a8075b9133 feat: sync docs without embeddings 2026-01-08 14:59:03 -05:00
Rajat Ahuja 448905cf4b Merge branch 'main' into rajat/turbopuffer 2026-01-08 14:46:24 -05:00
doria 20e60cb6ba
chore: fix basedpyright warnings (#317) 2026-01-08 14:02:25 -05:00
Rajat Ahuja b0051c009e fix: set up compose vector store and reconciliation loop 2026-01-08 13:21:36 -05:00
Rajat Ahuja 201b5125b3
feat: increase iam role duration. alter s3 file name and add to discord message (#315) 2026-01-07 13:04:13 -05:00
Rajat Ahuja acfade7d4e
feat: run unified tests suite in CI (#291)
* feat: run unified tests in CI

* fix: attempt use aws secrets manager

* fix: temp add verification workflow

* fix: CodeRabbit comments

* fix: remove debugging step

* fix: only run on main

* fix: add UNIFIED_TEST_LOG_LEVEL env var; default to WARNING
2026-01-06 16:03:29 -05:00
Benjamin McCormick f0d24af827 Merge branch 'main' into vince/dev-1259 2025-12-10 10:57:40 -05:00
Rajat Ahuja 1988f18fbe fix: coderabbit comments 2025-12-05 16:29:20 -05:00
Rajat Ahuja 60fde82218 fix: search; protect agaainst failed vector create/delete 2025-12-05 15:53:39 -05:00
Rajat Ahuja 2178fc91ce fix: search and add create_observations 2025-12-04 17:31:13 -05:00
Rajat Ahuja f1ac894713 Merge branch 'main' into rajat/turbopuffer 2025-12-04 16:56:04 -05:00
Rajat Ahuja b207403eb4 fix: turbopuffer 2025-12-04 16:51:09 -05:00
Rajat Ahuja f9a617a911 fix: LanceDB 2025-12-04 15:55:22 -05:00
Vineeth Voruganti ca702cfd10
Resolve SDK Inconsistencies and Add Observation Creation Endpoints (#288)
* feat: Add Observation Creation Endpoints and SDK Cleanup

* fix: Resolve linting errors

* chore: Code Rabbit Nits

* chore: Code Rabbit Nits
2025-12-04 15:24:45 -05:00
Vineeth Voruganti 72eb0827ec
Add session cloning to Ergonomic SDKs (#285)
* feat: Add session cloning to Ergonomic SDKs

* chore: docs nit
2025-12-04 14:51:39 -05:00
Rajat Ahuja 0dd3ee4e45 fix: remove destructive embedding migration 2025-12-04 14:05:00 -05:00
doria e3d345b961
API/SDK updates: configurability, more parameters. Unified test harness (#283)
* feat: add better params to working representation fetch in SDKs, return messages when added

* fix: working representation routes now accepting all parameters properly, with tests

* feat: add metadata/config fields to SDK objects where viable

* fix: tests

* feat: refactor SDKs to use representation config; [TEMP STAINLESS BUILD] update API

* feat: add representation object to sdks

* fix: use stainless sdk on branch

* fix: update TypeScript SDK tsconfig to use node16 module resolution

* fix: add isolatedModules = true to tsconfig

* fix: lol

* chore: coderabbit review

* feat: make delete session real

* feat: add observations routes with delete endpoints for documents. make session deletion real.

* chore: type cleanup

* fix: tests

* chore: coderabbit review

* fix: namespace by workspace

* feat: add ability to customize messages_per_summary at both workspace and session level

* chore: tests for summary config

* chore: coderabbit cleanup

* feat: make session and workspace config totally customizeable

* feat: add search by peer knowledge (#250)

* feat: search by peer perspective

* fix: enforce workspace in filters, make messages distinct in join

* fix: batch and merge migration steps

* fix: add refresh, add config to workspace, add refresh function, make fields readonly

* fix: search distinct

* fix: merge migrations

* fix: merge migrations

* fix: batch deletions, improve comments, limit consolidate dream to 100 docs at a time, auth on observations routes

* chore: review

* chore: coderabbit

* chore: review

* chore: broken comment

* feat: add set peer card route to API

* feat: create advanced configuration parameters with message>session>workspace hierarchy

* [wip] build unified testing harness

* chore: lint

* fix: cache invalidation, naming things, etc

* feat: longmem tests

* chore: peer config refactor

* feat: consolidate dream working, refactor representation

* fix: Various CR Comment Fixes

* feat: Allow configurable Redis port for harness instances and update cleanup methods to be asynchronous.

* fix: version bump, api/sdk updates

* fix: observation endpoints, deletion queue, sdk observation implementation

* chore: Fix migration order

* fix: Use published stainless sdks

* chore: (docs) update api-reference

* fix: (docs) update based on api and sdk changes

* fix: Code Rabbit Comments

* fix: Code Rabbit Final Nits

* fix: dream scheduler

* fix: SDK model type consistency

---------

Co-authored-by: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
2025-12-03 16:49:30 -05:00
doria 4ee2f8bd0c
Merge pull request #270 from plastic-labs/vince/ai-96
feat: beam benchmark initial commit
2025-11-20 17:59:41 -05:00
Benjamin McCormick 298dbbdb85 chore: coderabbit review 2025-11-20 17:56:27 -05:00
Benjamin McCormick f333e64f12 chore: tuning beam bench 2025-11-20 17:19:14 -05:00
Vineeth Voruganti a7520ce21d
Standardize DB Constraint Conventions (#272)
* fix: (db) Add standard naming conventions to SQLAlchemy Declarative Base

* chore: remove unnecessary relationships

* fix: (tests) handle old migrations being made before conventions were applied

* fix: wip migration to standardize naming for constraints

* fix (db): Migration wip)

* chore: rebase migration

* fix (db) Add migration tests

* chore: Code Review Comments

* fix: (db) fix remaining inconsistent index
2025-11-20 11:50:54 -05:00
Rajat Ahuja 0f1e1dec20
metrics for deriver / dialectic input + output tokens (#274)
* feat: separate deriver input / output tokens

* fix: track dialectic input / output tokens

* feat: track dialectic output tokens in streaming API

* fix: add component to metric ad change critical_analysis -> representation

* feat: track summary metrics in prometheus

* test: fix client streaming mocks

* fix: update tokenizer

* fix: add helper method; instrument peer card

* fix: count previous summary if not fallback
2025-11-19 21:20:34 -05:00
Benjamin McCormick 1616304b40 chore: fix up beam script 2025-11-19 17:56:12 -05:00
vintro c8b0aa9cf2
fix: timeout transparency 2025-11-19 13:43:42 -05:00
vintro a88799ca3e
fix: update code to handle 10M 2025-11-19 09:47:49 -05:00
Rajat Ahuja 2945f6bb3c
rm: level_valid constraint (#266)
* rm: level_valid constraint

* fix: create new migration

* fix: normalize data before enforcing check constraint again
2025-11-17 12:56:37 -05:00
Rajat Ahuja 7e8cf4336c
fix: add test for message seq in session (#268) 2025-11-17 12:54:23 -05:00
vintro 6fbb702ae4
feat: beam benchmark initial commit 2025-11-17 10:36:26 -05:00
Benjamin McCormick 5226b84cf3 Merge branch 'main' into ben/dev-1163 2025-11-13 12:24:39 -05:00
doria c8d75c77df
Merge pull request #256 from plastic-labs/ben/better-dedup
feat: better dedup with configurability
2025-11-13 11:46:43 -05:00
Rajat Ahuja d7bdcc3bc1
feat: codify queue columns (#254)
* feat: codify queue columns

* fix: batch with python loop control

* fix: cleanup merge

* fix: down revision

* fix: batch delete in migration

* feat: only run alembic tests for changed migration / test (#264)

* feat: only run alembic tests for changed migration / test
* fix: Run full test suite if alembic testing infra changes

* feat: codify times_derived + level on Document (#260)

* feat: codify times_derived + level on Document
* fix: CR comment

* fix: CodeRabbit comments

* fix: batch migrations; move types; remove fields from payload

* fix: rm duplicate table args

* fix: add messages.id FK
2025-11-07 13:22:24 -05:00