v0.8.2: cleanup + prose + structure + decomposition + budget + errors
Phase 1 — dedup + hardening (~9 items): - Remove duplicate *skill-registry* defvar from core-skills - Merge *backend-registry* into *probabilistic-backends*, delete backend-register - Remove inject-stimulus alias, standardize on stimulus-inject - Add pre-eval sandbox (skill-source-scan) blocks restricted symbols before eval - Remove dead plist-get function; remove duplicate json-alist-to-plist export - Fix read-framed-message whitespace DoS (4096-iteration max) - Add *read-eval* nil to dispatcher-approvals-process read-from-string (RCE) - Add test-op to ASDF; update .asd version 0.4.3→0.7.2 Phase 2 — prose + contracts + reorder: - Split ROADMAP: 2623→1089 lines (TODO only), CHANGELOG: 260→1528 lines (full DONE history, 14 versions reverse chron) - Add Contracts + Overview to 6 channel files + embedding-native + programming-standards + symbolic-scope - Reorder 28 .org files: Contract → Test Suite → Implementation (TDD order) - Add 7-phase inline prose to think() in core-reason - Expand USER_MANUAL: 183→461 lines (10 new sections) Phase 3 — decomposition + export organization: - Decompose think() into think-assemble-prompt, think-call-llm, think-parse-response orchestrator - Organize 188 exports into 16 grouped sections by module Phase 4 — budget enforcement + error protocol: - Per-session budget enforcement (SESSION_BUDGET_USD env var, budget-exhausted-p, guard in think-call-llm) - Error condition hierarchy (6 conditions: pipeline-error, llm-error, gate-error, budget-error, protocol-error) - Restarts in loop-process: skip-signal, use-fallback, abort-pipeline
This commit is contained in:
@@ -7,6 +7,33 @@
|
||||
|
||||
Extracted from gateway-messaging in v0.5.0. Isolated platform — Telegram-specific poll and send logic.
|
||||
|
||||
* Overview
|
||||
|
||||
The Telegram channel provides bidirectional communication via the Telegram Bot
|
||||
API. Messages from Telegram chats are injected into the cognitive pipeline as
|
||||
~:user-input~ signals with ~:source :telegram~. Outbound messages route through
|
||||
the actuator registry when the pipeline targets ~:telegram~.
|
||||
|
||||
The channel uses two functions: ~telegram-poll~ (inbound sensor, getUpdates
|
||||
with offset tracking) and ~telegram-send~ (outbound actuator, sendMessage).
|
||||
Both retrieve the bot token from the credentials vault. The polling offset
|
||||
(~:last-update-id~ in ~*gateway-configs*~) prevents duplicate processing across
|
||||
poll cycles. HITL commands are intercepted before injection so approval flows
|
||||
work identically across all channels.
|
||||
|
||||
** Contract
|
||||
|
||||
1. (telegram-get-token): returns the Telegram bot token from the vault
|
||||
(via ~vault-get-secret :telegram~), or nil if not configured.
|
||||
2. (telegram-poll): polls getUpdates with offset tracking (prevents
|
||||
duplicate processing), injects each message as a ~:user-input~ stimulus
|
||||
with ~:source :telegram~. Updates ~:last-update-id~ per cycle. Handles
|
||||
API and JSON parse errors gracefully. HITL commands are intercepted
|
||||
before injection.
|
||||
3. (telegram-send action context): sends a message via sendMessage.
|
||||
Extracts ~:chat-id~ and ~:text~ from the action plist. Logs send
|
||||
failures without crashing the pipeline.
|
||||
|
||||
* Implementation
|
||||
|
||||
#+begin_src lisp
|
||||
|
||||
Reference in New Issue
Block a user