fix(pi): prepare runtime state and agent workdir

2026-06-10 00:02:28 -04:00
parent 86374ab293
commit 504144eb9c
13 changed files with 236 additions and 18 deletions
@@ -66,12 +66,20 @@ Supported keys:
 - `api_key`: string, defaults to `ollama`
 - `api_key_env`: string, optional host env var name for egress auth injection
 - `models`: non-empty array of strings, defaults to `["qwen2.5-coder:7b"]`
+- `context_window`: positive integer, defaults to `4096`; this is the Ollama
+  runtime context, and bot-bottle subtracts `max_tokens` before writing Pi's
+  `contextWindow` so output space is reserved
+- `max_tokens`: positive integer, defaults to `1024`
+- `max_tokens_field`: `max_tokens` or `max_completion_tokens`, defaults to
+  `max_tokens`
 - `supports_developer_role`: boolean, defaults to `false`
 - `supports_reasoning_effort`: boolean, defaults to `false`

 The snake-case manifest keys are converted into Pi's JSON field names:
-`baseUrl`, `apiKey`, `supportsDeveloperRole`, and
-`supportsReasoningEffort`.
+`baseUrl`, `apiKey`, `contextWindow`, `maxTokens`,
+`supportsDeveloperRole`, and `supportsReasoningEffort`. `context_window`
+describes the server's total context; Pi's `contextWindow` receives
+`context_window - max_tokens` because Pi uses it as an input compaction target.

 `api_key` and `api_key_env` are mutually exclusive. When targeting a hosted
 provider through bot-bottle's egress sidecar, omit `api_key` and set