@gencode/console 0.3.21 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/CHANGELOG.md +32 -0
  2. package/package.json +2 -2
package/CHANGELOG.md CHANGED
@@ -1,5 +1,37 @@
1
1
  # @gencode/console
2
2
 
3
+ ## 0.4.0
4
+
5
+ ### Minor Changes
6
+
7
+ - 5af5e22: Add an opt-out switch for LLM session title generation. New sessions now generate a conversational title via the flash model by default (unchanged), but you can skip that LLM call for runs that don't need it — for example batch/one-shot jobs, embedded API usage, or CI.
8
+
9
+ - CLI: pass `--disable-title` on `aimax run` or `aimax resume`. It overrides the new env var `AIMAX_DISABLE_TITLE=true`.
10
+ - Programmatic: set `titleGeneration: { enabled: false }` on `AgentRunParams`.
11
+
12
+ When the switch is off, the session still gets a title — it falls back to a truncated version of the first user message, so the session list is never blank. No token cost and no network call happen. The switch controls only title generation; topic segmentation is unaffected. Start-up logs now show the resolved state as `titleGen: enabled|disabled`.
13
+
14
+ ### Patch Changes
15
+
16
+ - cbd1dba: AIMax now treats `LLMRequestError` model failures as retryable transient LLM failures even when the upstream gateway also reports non-retryable-looking metadata such as `BadRequestError` or HTTP 400. Runs still avoid replaying an attempt after assistant text or tool results have already been produced, and the agent log now records why a retry was skipped with fields such as `reason`, `retryableError`, `attemptRecordCount`, `recordsWithToolResults`, and `recordsWithAssistantText`.
17
+ - cbd1dba: AIMax now retries LLM turns when the streaming connection is torn down mid-response by the network or upstream, instead of failing the whole run on the first attempt.
18
+
19
+ Previously, if the HTTP socket was closed while the model was still streaming (for example an upstream gateway or load balancer dropping the connection, surfacing in logs as `streamErrorType="TypeError"`, `streamErrorMessage="terminated"`, `streamErrorCauseCode="UND_ERR_SOCKET"`, or Node errno codes such as `ECONNRESET`/`EPIPE`/`ETIMEDOUT`), the error reached the turn-retry loop without any retryable metadata, so it was treated as a final failure and the run stopped at `attempt=1` even though `maxAttempts` was higher.
20
+
21
+ Such transport-level failures are now recognized as transient and replayed within the existing turn-retry budget (default 3 attempts, exponential backoff). No configuration is required — the new behavior is on by default. User-initiated aborts and genuine non-retryable provider errors (e.g. HTTP 4xx with a real status code) are still not retried, and an attempt is still never replayed once assistant text or tool results have been produced.
22
+
23
+ - Updated dependencies [cbd1dba]
24
+ - Updated dependencies [cbd1dba]
25
+ - Updated dependencies [5af5e22]
26
+ - @gencode/cli@0.13.0
27
+
28
+ ## 0.3.22
29
+
30
+ ### Patch Changes
31
+
32
+ - Updated dependencies [8782104]
33
+ - @gencode/cli@0.12.1
34
+
3
35
  ## 0.3.21
4
36
 
5
37
  ### Patch Changes
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@gencode/console",
3
- "version": "0.3.21",
3
+ "version": "0.4.0",
4
4
  "type": "module",
5
5
  "bin": {
6
6
  "aimax-console": "./dist/server/index.js"
@@ -26,7 +26,7 @@
26
26
  "react": "^18.3.1",
27
27
  "react-dom": "^18.3.1",
28
28
  "ws": "^8.18.0",
29
- "@gencode/cli": "0.12.0",
29
+ "@gencode/cli": "0.13.0",
30
30
  "@gencode/shared": "0.3.0"
31
31
  },
32
32
  "devDependencies": {