remove c0re.operatorPronouns and c0re.contextWindowTokens
Both options are now ignored with a warning (the swarm-peers-removed.nix shape), so a host that still sets one keeps evaluating. - operatorPronouns: the agents' system prompt names the pronouns as she/her, the value the harness fell back to and the option's default. The --operator-pronouns flag, HiveEnv field, meta-flake let binding and HIVE_OPERATOR_PRONOUNS env var are gone. - contextWindowTokens: the per-family defaults (haiku 200000, sonnet 1000000, opus 1000000) move into hive-agent's harness_state as a table; the window the API reports after a turn still wins. The --context-window-tokens flag, HiveEnv field and the rendered HIVE_CONTEXT_WINDOW_TOKENS_<KEY> env vars are gone.
This commit is contained in:
parent
5cd1f16405
commit
4b5707768c
18 changed files with 151 additions and 258 deletions
|
|
@ -367,10 +367,10 @@ pub struct Bus {
|
|||
/// Per-inference context-window size as reported by the Anthropic API
|
||||
/// in the stream-json `result` event (`modelUsage.*.contextWindow`).
|
||||
/// Set by the stdout pump on every completed turn. Takes precedence
|
||||
/// over the Nix-configured `HIVE_CONTEXT_WINDOW_TOKENS_*` env vars
|
||||
/// over the per-model defaults in `harness_state::context_window_tokens`
|
||||
/// for compaction watermark calculations — it reflects the actual
|
||||
/// limit the model enforces, which may differ from what the operator
|
||||
/// configured (e.g. 200 k active window on a 1 M cache-enabled model).
|
||||
/// limit the model enforces, which may differ from the default
|
||||
/// (e.g. 200 k active window on a 1 M cache-enabled model).
|
||||
api_context_window: Arc<Mutex<Option<u64>>>,
|
||||
/// Resolved model id from the most recent turn's `assistant` events
|
||||
/// (the API-echoed `message.model`, e.g. `claude-opus-4-8`), as
|
||||
|
|
|
|||
Loading…
Reference in a new issue