| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | fix(newos4): `if test …` was always false and `for` items never globbed | Agando | 10 days | 1 | -1/+1 |
| * | fix(newos4): send num_ctx to Ollama, and make one auto-connect failure read a... | Agando | 10 days | 4 | -21/+57 |
| * | fix(newos4): piped grep searched the working directory instead of its input | Agando | 10 days | 3 | -1/+33 |
| * | feat(newos4): the script runner runs scripts — control flow, variables, glo... | Agando | 10 days | 3 | -23/+108 |
| * | fix(newos4): the loop guard reads the config it documents | Agando | 10 days | 3 | -13/+49 |
| * | fix(newos4): agent registration is absolute-path and honest about what it stored | Agando | 10 days | 5 | -43/+129 |
| * | fix(newos4): help names the owner of an undocumented command; loop lessons le... | Agando | 10 days | 4 | -35/+73 |
| * | fix(newos4): bound one turn's tool context, honest skill-create, quarantine a... | Agando | 10 days | 4 | -5/+135 |
| * | fix(newos4): name the real Ollama failure, bound auto-connect, fix the review... | Agando | 10 days | 4 | -43/+141 |
| * | fix(newos4): connect to Ollama on first use, honest write_file, list_files se... | Agando | 10 days | 4 | -82/+112 |
| * | fix(newos4): never overwrite a directory node; ls honours a path after its flags | Agando | 10 days | 4 | -9/+51 |
| * | fix(newos4): rollback keeps scaffolding, checkpoints cannot collide, tests ga... | Agando | 10 days | 4 | -15/+81 |
| * | fix(newos4): print the checkpoint name actually saved (auto) | Agando | 11 days | 3 | -8/+6 |
| * | fix(newos4): checkpoint() returns resolved name (auto) | Agando | 11 days | 1 | -1/+1 |
| * | feat(newos4): cut/copy in Files, paste into WebDAV (Issue D2) | Agando | 11 days | 1 | -1/+1 |
| * | fix(newos4): four phone-test defects — no preview close, single-file share,... | Agando | 11 days | 1 | -1/+1 |
| * | feat(newos4): mobile download/share UX — deferred blob revoke, multi-select... | Agando | 11 days | 1 | -1/+1 |
| * | feat(feedback): review dashboard, public guide, terminal commands (v4.6.94) | Agando | 11 days | 3 | -3/+317 |
| * | feat(newos4): context window warns at 80% and says what trimming dropped (v4.... | Agando | 2026-10-23 | 3 | -7/+53 |
| * | fix(newos4): the virtual /sys entry leaked into listings, trees and counts (v... | Agando | 2026-10-23 | 4 | -13/+45 |
| * | fix(newos4): audit names broken refs instead of counting documentation (v4.6.... | Agando | 2026-10-23 | 1 | -1/+1 |
| * | fix(newos4): the audit stops inventing '999d unused' (v4.6.85) | Agando | 2026-10-23 | 3 | -5/+11 |
| * | fix(newos4): world_model_query default path parses again (v4.6.83-84) | Agando | 2026-10-23 | 4 | -21/+73 |
| * | fix(newos4): skill-create stops mangling what the agent wrote (v4.6.82) | Agando | 2026-10-23 | 1 | -1/+1 |
| * | fix(newos4): outboxResult scoped, markdown mime, old reply path retired (v4.6... | Agando | 2026-10-23 | 3 | -5/+15 |
| * | fix(chat): GLM review batch — corruption, traversal, cursor truncation, dou... | Agando | 2026-10-23 | 3 | -15/+29 |
| * | fix(chat): three concurrency holes found reviewing my own patch (v4.6.77) | Agando | 2026-10-23 | 4 | -5/+15 |
| * | fix(newos4): agent read gets its own chat cursor (v4.6.76) | Agando | 2026-10-23 | 3 | -11/+31 |
| * | fix(newos4): skill points at the served contract URL, not a VFS path (v4.6.75) | Agando | 2026-10-23 | 1 | -1/+1 |
| * | docs(newos4): seed a chatting-with-hermes skill (v4.6.74) | Agando | 2026-10-23 | 1 | -1/+1 |
| * | feat(newos4): hermes command, auto-poll, chat_hermes tool, token reset (v4.6.73) | Agando | 2026-10-23 | 4 | -53/+359 |
| * | feat(newos4): on-demand worker labels and a server-canonical predictor store ... | Agando | 2026-10-23 | 4 | -13/+239 |
| * | fix(newos4): grep, head and tail take every path argument (v4.6.67) | Agando | 2026-10-23 | 3 | -65/+143 |
| * | docs(newos4): merge the two shell-composition skills into one seeded skill (v... | Agando | 2026-10-23 | 1 | -1/+1 |
| * | fix(newos4): an invalid grep pattern returns a message, not an exception (v4.... | Agando | 2026-10-23 | 4 | -7/+37 |
| * | feat(newos4): agent status says never-scheduled vs waiting; `guides` command ... | Agando | 2026-10-23 | 4 | -9/+101 |
| * | fix(newos4): tokenised body-aware skill search for load_skills (v4.6.62) | Agando | 2026-10-23 | 3 | -15/+153 |
| * | fix(newos4): one error counter for errors/dashboard/world-model (v4.6.61) | Agando | 2026-10-23 | 6 | -27/+129 |
| * | fix(newos4): refuse shell composition, wc takes multiple paths (v4.6.58) | Agando | 2026-10-23 | 4 | -29/+121 |
| * | fix(newos4): predictor arithmetic, deployed-source viewer, ls text output (v4... | Agando | 2026-10-23 | 5 | -51/+105 |
| * | fix(newos4): measure predictor accuracy over paired predictions (v4.6.56) | Agando | 2026-10-23 | 4 | -192/+428 |
| * | fix(newos4): empty-pipeline crash, stacks in reports, frame in digest + dashb... | Agando | 2026-10-23 | 5 | -17/+75 |
| * | fix(newos4): define VirtualFS.emptyTrash() — empty-trash threw since 2026-1... | Agando | 2026-10-23 | 3 | -1/+41 |
| * | fix(newos4): unmeasured skills are untracked, world-model writes verified, sk... | Agando | 2026-10-23 | 2 | -7/+33 |
| * | fix(newos4-debug): idempotent ingest, admin-gated reads, honest counts (v4.6.... | Agando | 2026-10-23 | 3 | -12/+164 |
| * | fix(newos4): dashboard shows the real world model and stops dying after 10 s ... | Agando | 2026-10-22 | 4 | -23/+125 |
| * | feat(newos4): world-model-ask answers with the LLM, grounded in the model (v4... | Agando | 2026-10-22 | 4 | -27/+237 |
| * | fix(newos4): coreutils flags + loop-guard arg key, both found by the agent's ... | Agando | 2026-10-22 | 4 | -49/+193 |
| * | fix(newos4): GLM review follow-ups for AI read/context (v4.6.47) | Agando | 2026-10-21 | 3 | -47/+141 |
| * | feat(newos4): AI paged file reads, durable tool traces, 12k context budget, r... | Agando | 2026-10-21 | 3 | -33/+140 |
