Releasesby Ibisposthog Agent skills agent-skills-v0.2994.0
UpdatetodayUnverifiedAdded Oct 13, 2026
Build from 588de869d4989164b913b1b5b64bd82835b688de
Topics: AI agents
More PostHog releases
Every PostHog releaseAgent skills v0.2996.0
Build from c2cd5c6467dbf3306291821b4c421ef09fc5b143
Agent skills v0.2995.0
Build from b1360413139653d791615c609e8d9f7f0ae141c1
Agent skills v0.2921.0
Build from 34a467e9862fd10cc7dc9ee8806bf53fdd54b660
Agent skills v0.2920.0
Build from 9ea40e6edb6137d5e68d765ac6e0305babe72552
Agent skills v0.2919.0
Build from d2cb8a11854230414ba0de4c5e56f2cf12d200ca
Agent skills v0.2918.0
Build from 205c3a323777d16c8d52d4a89d815a88cbfdd052
Agent skills v0.2917.0
Build from a3aa2f4c9ea4210bcfd016489a2c3826b4fe1337
Agent skills v0.2916.0
Build from e604720dce86387accd6c79a25a67224b6d906f9
Also shipped on Oct 13, 2026
PostHog in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
LangSmith SDK 0.14.8
- fix(py): send session_id on RunTree.patch fix: keep punctuation out of freeze guard links chore(deps): bump source-map-js from 1.2.1 to 1.2.2 in /js fix(py): make the /runs/multipart 404 fallback to /runs/batch reachable feat(sandbox): accept any JOSE asymmetric algorithm chosen by the JWKS key (python) feat(sandbox): customer-managed KMS keys for S3...
Retry jobs with narrower API token permissions
Retry automation no longer needs the broader write_builds REST API scope. The new retry_builds scope allows a token to retry failed jobs in existing builds or individual eligible jobs, without granting access to the create-build or rebuild endpoints. When creating or editing an API access token, select Build Retries ( retry_builds ).
Post-training
Post-training lets you write your own training loop and run it against Together AI GPUs. Your code builds each batch and chooses the loss function and learning rate, while the GPUs you provision run the forward and backward passes, optimizer steps, and sampling. It bills per GPU-minute.
2026-10-13 updates
See what changed in Sourcegraph.
truss 0.18.34
- Add include and exclude filters to BDN mount configuration feat: Forward egress_restrictions for BIS and warn about missing hosts Release 0.18.34