diff options
| author | Adam Malczewski <[email protected]> | 2026-06-22 16:11:55 +0900 |
|---|---|---|
| committer | Adam Malczewski <[email protected]> | 2026-06-22 16:11:55 +0900 |
| commit | 55177d549e60886338f58cb579534dc1a09f94ec (patch) | |
| tree | 369bfd3273c390dcffe3f3c7c7fc83746a0c1652 | |
| parent | e95d526635fd11d75e43e2dd219a6a05b49d43b9 (diff) | |
| download | dispatch-55177d549e60886338f58cb579534dc1a09f94ec.tar.gz dispatch-55177d549e60886338f58cb579534dc1a09f94ec.zip | |
docs: remove context window LIMIT from open items (DONE)
| -rw-r--r-- | tasks.md | 6 |
1 files changed, 0 insertions, 6 deletions
@@ -531,12 +531,6 @@ conversation tab. Short-ID prefix resolution (4+ chars → full ID via `GET /con - [ ] Live-verify end-to-end (CLI → real conversation → FE tab open). ## Open items -- **Context window LIMIT (deferred, sibling of context size):** expose the selected model's max - context-window token limit so the FE can render `contextSize / limit` (e.g. `1286 / 200000`). - Source = the provider/model catalog (`ModelInfo`); likely a field on the models response - and/or stamped alongside `contextSize`. "context size" = current usage (DONE); "context - window" = this limit (GLOSSARY). FE handoff `frontend-context-size-handoff.md` already flags - the denominator as not-yet-available. - **`prefix.fingerprint` / `warm|real` cache-bust attributes (deferred):** decoupled from dedup by the content-addressed decision; also gated on cache-warming being built (not yet) so `warm|real` can't be honestly stamped. Later cache-bust-debug |