bitterbot 1.11.0 → 1.13.0
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.
- package/README.md +4 -2
- package/bitterbot.mjs +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -214,6 +214,8 @@ The gate observes whether the agent actually reads the skill. A skill that does
|
|
|
214
214
|
|
|
215
215
|
**You can inspect the evidence.** The Evolution tab and `bitterbot skills evidence` expose validation results, credited uses, model information, and lineage. Young nodes may produce few promotions while evidence accumulates.
|
|
216
216
|
|
|
217
|
+
Production skill evolution is **on by default**, subject to evidence, model availability and budgets. An idle dream tick can now run failure-driven experiments without waiting for a full creative cycle. Candidates must pass the existing task gates before canary exposure; monitoring and rollback continue afterward. The separate [Learning Strategy Lab](docs/memory/learning-strategy-lab.md) remains a host-invoked shadow facility, and its research candidates do not become live skills. Set `memory.proceduralLearning.automation.enabled: false` to disable the idle coordinator, `memory.proceduralLearning.mode: "off"` to disable its evidence service, or `skills.evolution.enabled: false` to disable production evolution altogether.
|
|
218
|
+
|
|
217
219
|
Skills can also include **pre-action interceptors**: code that checks proposed tool calls and can modify parameters, add context, require prerequisites, or block execution. Because an interceptor is a code path rather than a prompt, it runs on every matching tool call.
|
|
218
220
|
|
|
219
221
|
Passing a task suite is a bounded result, not a guarantee of improvement on every task. Published benchmarks include their caveats; broad learning gains remain an active evaluation target.
|
|
@@ -239,13 +241,13 @@ There is no public feed or follower count. Expense tracking records a shared tab
|
|
|
239
241
|
|
|
240
242
|
The longer-term ambition is a network where agents turn experience into useful capabilities and share those capabilities with evidence attached.
|
|
241
243
|
|
|
242
|
-
Bitterbot implements signed skill exchange over a P2P mesh, receiver quarantine and validation, peer reputation, and retractions. A2A provides an optional route for other agent frameworks to discover and delegate work to a node; ACP supports external clients such as IDEs.
|
|
244
|
+
Bitterbot implements signed skill exchange over a P2P mesh, receiver quarantine and validation, peer reputation, and retractions. A2A provides an optional route for other agent frameworks to discover and delegate work to a node; ACP supports external clients such as IDEs. The Gateway can also serve an OpenAI-compatible `/v1/chat/completions` endpoint (off by default), so any tool that speaks the OpenAI API can use a Bitterbot agent as its model.
|
|
243
245
|
|
|
244
246
|
An experimental economic layer adds USDC wallets on Base, x402 payments, and skill-marketplace infrastructure. **The wallet, payments, A2A HTTP, marketplace, and bounties are opt-in.** The wallet starts on testnet. Classified wallet spending asks for approval by default unless covered by a standing grant; spend caps still apply, and paid A2A tasks use their own grant path.
|
|
245
247
|
|
|
246
248
|
The marketplace is early and has not carried meaningful paid volume. Payment functionality has not had a third-party audit. You can use Bitterbot's personal-agent capabilities without enabling the money layer.
|
|
247
249
|
|
|
248
|
-
[Skill marketplace](docs/marketplace/) · [A2A integration](docs/marketplace/a2a-integration.md) · [Wallet](docs/wallet/) · [Action review](docs/tools/action-review.md)
|
|
250
|
+
[Skill marketplace](docs/marketplace/) · [A2A integration](docs/marketplace/a2a-integration.md) · [OpenAI-compatible endpoint](docs/gateway/openai-http-api.md) · [Wallet](docs/wallet/) · [Action review](docs/tools/action-review.md)
|
|
249
251
|
|
|
250
252
|
## Models
|
|
251
253
|
|
package/bitterbot.mjs
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
#!/usr/bin/env node
|
|
2
|
-
// bitterbot 1.
|
|
2
|
+
// bitterbot 1.13.0 launcher: installs the signed release tarball on
|
|
3
3
|
// first run, then runs it. Source: src/launcher/ in
|
|
4
4
|
// https://github.com/Bitterbot-AI/bitterbot-desktop (built by scripts/npm-package.ts).
|
|
5
5
|
|
|
@@ -1739,7 +1739,7 @@ function launcherFile() {
|
|
|
1739
1739
|
return null;
|
|
1740
1740
|
}
|
|
1741
1741
|
}
|
|
1742
|
-
var version = true ? "1.
|
|
1742
|
+
var version = true ? "1.13.0" : "0.0.0";
|
|
1743
1743
|
runLauncher({
|
|
1744
1744
|
argv: process.argv.slice(2),
|
|
1745
1745
|
env: process.env,
|