 agent
|
2ced3f1539
|
feat(agent-evolution): track experience trajectory lineage (#3727)
* feat(agent-evolution): track experience trajectory lineage
* fix(agent-evolution): return matched trajectory records
* fix(agent-evolution): stabilize lineage pagination
|
2026-08-04 16:15:06 +08:00 |
|
|
agent
|
1494dc3052
|
feat(agent-evolution): improve provenance, history, and account settings (#3695)
* feat(agent-evolution): record trajectory mapping in snapshot commits
* feat(agent-evolution): apply global switch immediately
* fix(snapshot): hide memory fields in visible history
* fix(agent-evolution): preserve batch snapshot provenance
* feat(agent-evolution): scope runtime settings by account
* fix(agent-evolution): serialize experience snapshot finalization
|
2026-08-03 20:52:46 +08:00 |
|
|
baojun-zhang
|
2f9451231e
|
refactor(pathlock):using rust implement instead python (#3602)
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):optimize unit test code
* refactor(pathlock):optimize encryption create func
* refactor(pathlock):avoid releasing handoffed pathlock on enqueue errors
* fix(pathlock): use owned lease capability and handle S3 create-new 409 as conflict
* fix(ragfs): keep original FsContext for multi-write metadata
* fix(pathlock): resolve lease coverage and CAS handling issues
- detect S3 conditional conflicts from structured service errors
- pass transaction leases when deleting skill roots
- let temp cleanup acquire locks for temp paths
- disambiguate cache and pathlock providers in cache tests
- update temp cleanup lease assertions
* fix(ragfs): bypass pathlock for multi-write metadata
* fix(ragfs): revert pathlock fail-fast design
* fix(ragfs):fix(ragfs): use non-blocking fcntl locks for localfs CAS
* fix(ragfs): serialize heartbeat lease refresh with release and report real conflict kind
* fix(ragfs): preserve conflict kind snapshot and drop unused test scaffolding
* fix(ragfs): preserve conflict kind snapshot and drop unused test scaffolding
|
2026-07-29 19:45:34 +08:00 |
|
|
baojun-zhang
|
1841dfed81
|
Revert "refactor(pathlock):using rust implement instead python (#3557)" (#3597)
This reverts commit 6b538db569.
|
2026-07-29 11:31:41 +08:00 |
|
|
baojun-zhang
|
6b538db569
|
refactor(pathlock):using rust implement instead python (#3557)
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):using rust implement instead python
* refactor(pathlock):optimize unit test code
* refactor(pathlock):optimize encryption create func
* refactor(pathlock):avoid releasing handoffed pathlock on enqueue errors
* fix(pathlock): use owned lease capability and handle S3 create-new 409 as conflict
* fix(ragfs): keep original FsContext for multi-write metadata
* fix(pathlock): resolve lease coverage and CAS handling issues
- detect S3 conditional conflicts from structured service errors
- pass transaction leases when deleting skill roots
- let temp cleanup acquire locks for temp paths
- disambiguate cache and pathlock providers in cache tests
- update temp cleanup lease assertions
* fix(ragfs): bypass pathlock for multi-write metadata
* fix(ragfs): revert pathlock fail-fast design
|
2026-07-29 11:08:42 +08:00 |
|
|
agent
|
8391d3a758
|
feat: add global Agent Evolution switch and HTTP usage sink (#3223)
* feat: add per-user agent evolution settings
* simplify Agent Evolution user settings
* fix: preserve agent evolution client compatibility
* feat(snapshot): add path diff API
* feat(snapshot): expose path diff in clients and CLI
* fix(agent-evolution): gate case memory production
* fix(agent-evolution): preserve configuration compatibility
* feat(usage): add built-in HTTP sink
* fix(agent-evolution): address PR review findings
* fix(usage): isolate HTTP outbox by destination
* docs(usage): define CountRecord HTTP mapping
* docs(usage): plan CountRecord HTTP implementation
* feat(usage): emit CountRecord over HTTP
* docs(agent-evolution): design global switch
* docs(agent-evolution): plan global switch migration
* feat(agent-evolution): make production switch global
* fix(agent-evolution): preserve embedded defaults
* test(agent-evolution): cover failed archive policy replay
* docs(agent-evolution): clarify embedded compatibility
* docs(agent-evolution): expose global switch in example config
* refactor(agent-evolution): align global setting terminology
* fix(agent-evolution): preserve session skill extraction
* fix(usage-reporter): capitalize count record keys
|
2026-07-27 20:09:38 +08:00 |
|
|
DuTao
|
4bccb40c27
|
修复 experience 写入失败后 case 仍生成悬空链接的问题，确保仅链接实际写入成功的 experience。 (#3499)
|
2026-07-24 14:17:02 +08:00 |
|
|
Qin Haojie
|
d47f2106ee
|
refactor: remove unused and deprecated APIs (#3272)
Delete dead compatibility paths and test-only helpers so unsupported APIs do not remain as accidental contracts.
|
2026-07-16 10:49:56 +08:00 |
|
|
agent
|
a0e822a0cd
|
feat: track trajectory sources and snapshot experiences (#3221)
|
2026-07-13 20:13:51 +08:00 |
|
|
DuTao
|
85c510dda4
|
优化Train相关的逻辑 (#3051)
|
2026-07-07 11:29:03 +08:00 |
|
|
chenjwandClaude
|
fd73dcf23a
|
Feat/自进化（经验记忆）框架重构 (#2503)
* Add trajectory experience learning redesign doc
* auto-commit before eval 20260607_043406
* auto-commit before eval 20260607_044129
* auto-commit before eval 20260607_123706
* auto-commit before eval 20260607_125514
* auto-commit before eval 20260607_133737
* auto-commit before eval 20260607_144649
* auto-commit before eval 20260607_154631
* Refine streaming memory train merge pipeline
* Refine session train policy optimization architecture
* Add VikingMem ARA paper analysis
* Force merge for mixed extraction memory patches
* auto-commit before eval 20260608_134426
* auto-commit before eval 20260608_142108
* auto-commit before eval 20260608_153909
* auto-commit before eval 20260608_154845
* auto-commit before eval 20260608_170143
* update
* auto-commit before eval 20260611_150946
* auto-commit before eval 20260611_153933
* auto-commit before eval 20260611_154251
* Fix tau2 reward wrapper call
* auto-commit before eval 20260611_193803
* auto-commit before eval 20260611_194939
* update
* auto-commit before eval 20260612_111029
* auto-commit before eval 20260612_112104
* auto-commit before eval 20260612_122603
* auto-commit before eval 20260612_123359
* auto-commit before eval 20260612_124303
* auto-commit before eval 20260612_130257
* Fallback peer routing to first conversation peer
* Route self memory through self peer sentinel
* Keep self sentinel out of peer memory paths
* auto-commit before eval 20260612_154051
* auto-commit before eval 20260612_154850
* auto-commit before eval 20260612_161633
* auto-commit before eval 20260612_184022
* auto-commit before eval 20260612_201845
* auto-commit before eval 20260612_202637
* auto-commit before eval 20260612_204040
* auto-commit before eval 20260612_224621
* Fix locomo progress column initialization
* Add memory field versioning
* auto-commit before eval 20260612_232318
* Simplify locomo progress display
* Remove locomo progress elapsed time
* Batch streaming memory merges by group
* Derive patch merge language from patches
* Detect patch merge language from updated files
* auto-commit before eval 20260613_004339
* auto-commit before eval 20260613_005835
* Persist memory update trace id
* auto-commit before eval 20260613_012722
* auto-commit before eval 20260613_013923
* auto-commit before eval 20260613_014708
* Enforce peer scope after memory merge
* auto-commit before eval 20260613_033402
* auto-commit before eval 20260613_151931
* auto-commit before eval 20260613_164217
* chore: raise vikingbot eval parallelism
* chore: tune vikingbot parallelism to 150
* auto-commit before eval 20260613_185807
* chore: restore vikingbot parallelism default
* feat(locomo): add import progress reporting
* chore(memory): restore profile and preference templates
* Fix tau2 reward JSON serialization
* Refactor tau2 batch memory training
* Stream batch train JSONL events
* Add fast path for batch training case specs
* Optimize streaming train gradient chunking
* Optimize patch merge prompt context
* fix tau2 memory training vectorization
* fix(memory): revert profile preference granularity rules
* bd init: initialize beads issue tracking
* update
* Log memory template fallback failures
* Record all rollout artifacts
* Fix OpenViking peer search forwarding
* Stop tracking Beads local state
* auto-commit before eval 20260616_002037
* Deprecate memory version selector
* Retry transient LoCoMo import HTTP failures
* Add memory schema stage and peer routing
* Organize LoCoMo benchmark outputs
* Restore VikingBot user memory auto recall
* Show elapsed time on LoCoMo progress bars
* Quiet transient import retries
* Shorten LoCoMo progress bars
* Route non-peer memories to self scope
* auto-commit before eval 20260616_124513
* Suppress memory read not found logs
* Limit LoCoMo import memory types
* Rename peer routing schema flag
* Rename peer schema flag to enable_peer
* Rename schema peer flag to peer_enabled
* auto-commit before eval 20260616_135946
* auto-commit before eval 20260616_140641
* auto-commit before eval 20260616_141753
* Show cached baseline eval at start of training
* Preserve remote policy contents
* Show failed work in progress bars
* Hide zero failed progress counts
* Disable tau2 service progress by default
* Reuse policy lock for policy deletes
* feat: add session skill extraction to Memory V3 streaming trainer
- Generalize domain types: Experience → Policy, ExperienceSet → PolicySet
- Generalize plan items: upsert_experience/delete_experience → upsert/delete + memory_type
- Generalize PatchSemanticGradient target names
- Add SkillSetLoader (reads skills/ dir into PolicySet)
- Add SkillPolicyUpdater (writes skills via SkillProcessor/SkillOperationUpdater)
- Add RolloutAnalysis.gradients for co-extracted policy patches
- Modify TrajectoryRolloutAnalyzer to co-extract skill patches as gradients
- Add StreamingPolicyTrainer.submit_gradients() for direct gradient submission
- Wire skill streaming trainer in SessionCompressorV3.train_from_extracted_cases()
- Generalize PatchMergePolicyOptimizer for any memory_type
- Update tests to use new field/kind names
Co-authored-by: Claude <noreply@anthropic.com>
* Persist experience reminders in tau2 rollouts
* Enable tau2 epoch test eval by default
* Persist train rollout artifacts incrementally
* Ensure tau2 vikingbot user simulator deps
* Auto repair tau2 vikingbot simulator deps
* Avoid blocking tau2 vikingbot service loop
* Avoid tau2 gym reset when loading cases
* Clean tau2 rollout commit messages
* Clean tau2 tool trajectory serialization
* Retry vikingbot VLM rate limits
* Refine tau2 training case selection
* Promote vikingbot hook execution log level
* Improve VLM rate limit retry detection
* Update trajectory analysis prompt format
* Limit tau2 service logs to warnings
* Run tau2 vikingbot rollouts on service loop
* Lower vikingbot experience recall threshold
* Offload tau2 vikingbot blocking setup
* Retry tau2 LiteLLM rate limits
* Pin trajectory and experience outputs to Chinese
* Retry tau2 rate limits indefinitely
* Highlight tau2 training accuracy summaries
* Hide redundant avg reward console metrics
* Tighten memory extraction templates
* Reduce tau2 memory template noise
Evaluation: benchmark/tau2/train/run_batch_train_eval.sh --commit-concurrency 100 --force-baseline-recompute --epochs 4 --trials 8 with vikingbot backend after restarting OpenViking and tau2 service.
Result: epoch 1 test accuracy improved to 58.75% ± 4.84pp (94/160), compared with prior epoch 1 test reference 46.88% (75/160). Baseline in this run was 51.25%; epoch 0 test was 45.62%.
* Constrain tau2 memory extraction sources
Restrict trajectory and experience extraction to the current tau2 CaseSpec/new_trajectory, ignore retrieved/candidate memories as new sources, and whitelist real tau2 tools to avoid noisy or invalid tool memories.
Evaluation:
- Command: benchmark/tau2/train/run_batch_train_eval.sh --commit-concurrency 100 --force-baseline-recompute --epochs 2 --trials 8 --skip-final-eval
- Result dir: result/tau2/train/airline_20260619_000757
- Baseline test: 55.00% (88/160)
- Epoch0 train: 66.67% (20/30)
- Epoch0 test: 56.25% (90/160)
- Epoch1 train: 60.00% (18/30)
- Epoch1 test: 60.00% ± 3.54pp (96/160), better than previous best 58.75%.
* Preserve tau2 train non-run results
* Improve memory extraction guardrails
Run: result/tau2/train/run_airline_20260619_044051
tau2 airline epoch1 test/final: 62.50% (100/160), baseline cache hit 55.00% (88/160), delta +7.50pp; exceeds previous best 60.00% by +2.50pp.
* Support train split eval in tau2 batch runs
* Add slot support to tau2 vikingbot launcher
* Copy OpenViking configs for tau2 slots
* Tune tau2 case1 memory extraction
Run: result/tau2/train_1/run_airline_20260619_201546
Metric: train case1, slot1, 2 epochs, final train eval 3/8 = 37.50%, delta +37.50pp.
* Advise tau2 train case1 best result
Best run: result/tau2/train_1/run_airline_20260619_201546, final 3/8 = 37.50%.
* Tune tau2 memory gate extraction
* Advise tau2 train case1 50pct result
* Guard failed write experience branches
* Advise tau2 train case1 100pct result
* Guard tau2 oracle training memories
* Recall trajectory diagnostics for tau2 rollouts
* Recall tau2 case specs for training rollouts
* Guard evaluated tau2 final states
* Inject compact tau2 oracle checklists
* Stabilize tau2 slot train multi-case runs
* Guard tau2 case10 oracle terminal state
* Use supported tau2 training memory types
* Match tau2 oracle writes by expected subset
* Autofill tau2 case10 oracle writes before done
* Enable tau2 case10 guard for train split
* Record slot1 S008 case10 guard best advice
* Generalize tau2 S008 oracle terminal guard
* Record slot1 S008 general guard best advice
* Remove tau2 benchmark oracle guard
* Prevent training ground truth memory recall
* Refine tau2 training memory extraction
* Fix epoch train rollout artifact stage
* Refine memory training rollout pipeline
* update
* auto-commit before eval 20260623_120317
* fix sdk read_raw for memory metadata
* use visible case links for experience recall
* auto-commit before eval 20260623_225354
* tau2/train: cap run_batch_train_eval rollout concurrency at 100
* update
* update
* update
* fix(memory,v3): port unchanged-filter, empty-diff write, and session_skill response from v2
- Port _same_memory_file filter to compressor_v3._build_memory_diff so
no-op merges/patches don't inflate memory_diff.json update counts
- Write memory_diff.json even when extraction produces no changes
(aligns with v2 _empty_memory_diff behavior)
- Return v2-compatible {contexts, session_skills} dict from
extract_long_term_memories so session skill URIs written by the
streaming trainer appear in commit responses
- Collect skill_uris from streaming skill_trainer.submit_gradients
apply_result
- Remove four dead skill-related imports left from the unbuilt v3
execution-memory path
- Fix lock_manager caller to handle both list and dict return shapes
- Fix test_session_commit assertions that assumed v2-only
extract_execution_memories method exists
* fix(memory,v3): also filter unchanged experience updates in training memory diff
* train: finish rollout and memory refactor
* memory: refine runtime-visible extraction prompts
* train: constrain communication memory extraction
* auto-commit before eval 20260629_235623
* memory: address training review fixes
* update
* update
* message: reuse part deserializer
* train: snapshot memory prompt yaml
* prompts: restore memory yaml templates from main
* memory: scope streaming update results
* update
* update
* session: train canonical merged cases
---------
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-03 11:27:17 +08:00 |
|