Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(install): say a transient 4xx is spooled like a 5xx
Vinícius DS Andrade7cdbfe0b011f
diff --git a/docs/install.md b/docs/install.mdindex 411681d4..7937db55 100644--- a/docs/install.md+++ b/docs/install.md@@ -668,8 +668,9 @@ on receipt before persistence.Native `ai-memory hook --event ...` commands spool events locally. The POSIXshell bundle and the PowerShell (`.ps1`) bundle spool too, but only onfailure: they POST first and write the event to the same-`<data_dir>/hook-spool/` contract when the server is unreachable or answers-5xx, then flush the backlog behind the next delivery that succeeds. A 4xx+`<data_dir>/hook-spool/` contract when the server is unreachable, answers+5xx, or answers 408, 425 or 429 (a saturated server asks for a retry), then+flush the backlog behind the next delivery that succeeds. Any other 4xxis a permanent rejection and is not retried. Session startdoes a short bounded cleanup drain before fetching a handoff; cancellation-proneboundary events (`stop`, `pre-compact`, and `session-end`) start a detached@@ -1762,7 +1763,7 @@ instead. For Pi, the generated extension also provides the MCP bridge.The generated TypeScript integrations survive an unreachable server thesame way the native hooks do: a delivery that fails at the network level-(or gets a 5xx) is written to `<data_dir>/hook-spool/` in the exact+(or gets a 5xx, 408, 425 or 429) is written to `<data_dir>/hook-spool/` in the exactformat `ai-memory hook-drain` reads, and the plugin drains that backlogitself once the server is reachable again — so a day of laptop work offthe server's network is captured, not silently dropped. Each spooled