Resolves conflict in .github/workflows/claude.yml: the comment 'All jobs use...' on the PR branch was reconciled with main's more specific 'All 5 jobs use...' (auto-fix job from #1159 brought the count to 5).

# GAIA v0.19.0 Release Notes

GAIA v0.19.0 tightens the agent loop against silent-failure regressions
and continues the focused-agent split. A new `gaia eval agent`
reliability harness exercises tool selection end-to-end against the
local Agent UI MCP backend and surfaced four agent-loop bugs that
previously produced silently-wrong "Task completed" answers — all four
are fixed in this release. Dedicated `BrowserAgent` and `AnalystAgent`
replace the ChatAgent-backed web and data profiles. Agents can now
declare a `REQUIRED_HARDWARE` capability tier that is validated at
startup against the running Lemonade server. GAIA can connect to a
remote Lemonade Server protected by an API key. And a new CI job
auto-implements PRs for bulletproof bug issues in parallel with the
existing triage path.

**Why upgrade:**
- **MCP tool-calling reliability framework + four framework fixes** —
`gaia eval agent` runs a user-simulator + judge against the local MCP
backend; the harness uncovered and fixed silent loop-break lies, a
~85-token JSON-envelope leak in tool-calling-model prompts, a missed
native-path failure check, and an over-broad eval rubric.
- **Specialized agents** — `BrowserAgent` and `AnalystAgent` ship as
dedicated implementations behind the `gaia browse` and `gaia analyze`
CLIs, replacing the monolithic ChatAgent-backed profiles.
- **Hardware-requirement validation** — agents can declare
`REQUIRED_HARDWARE` and fail fast at startup when the host's device tier
(CPU/iGPU/dGPU/NPU/hybrid) does not satisfy it, instead of silently
degrading.
- **Remote Lemonade auth** — setting `LEMONADE_API_KEY` threads
`Authorization: Bearer <key>` through every Lemonade-bound HTTP path;
wrong/missing key surfaces an actionable error naming the variable.
- **CI auto-fix for bulletproof bug issues** — bug-labelled issues that
meet the "1-2 files, < 50 lines, 100% confidence" bar now get an
auto-implemented PR in parallel with the standard triage comment.


## What's New

### MCP Tool-Calling Reliability Framework

A new end-to-end eval harness lands at `src/gaia/eval/runner.py` (PR
[amd#718](amd#718)) and is invoked via `gaia
eval agent`. The runner spawns a subprocess that acts as user-simulator
+ LLM judge against the live Agent UI MCP backend, exercises 10 generic
scenarios (no-param, single-param, multi-step, conditional,
error-handling, "no tool needed"), and produces per-tool failure rollups
via `analyze_failures.py`. The judge rubric in `judge_turn.md` grades on
tool selection alone for `verbatim`-tagged scenarios — it explicitly
does not penalize the agent for underlying-service failures, which had
been conflating pipeline correctness with hardware availability.

Running the harness against the agent loop immediately exposed four
framework regressions, all fixed in this release:

- **Silent loop-break lie.** When small local models emitted just the
server prefix (`mcp_foo_mcp`) instead of the full registered tool name,
the agent retried four times and then hard-coded `"Task completed with
mcp_foo_mcp. No further action needed"` as the final answer despite zero
successful tool calls. Server-name sanitisation now strips redundant
`mcp` tokens before namespacing, and a new
`Agent._build_loop_break_summary` helper branches on whether the last
result was an error so the user sees the actual error wording. A new AST
guard in `tests/unit/agents/test_agent_source_invariants.py` prevents
the lie-on-loop literal from reappearing.
- **JSON envelope leak in tool-calling-model prompts.** The `{"tool":
..., "tool_args": ...}` template was supposed to be suppressed for
models that support native `tools=[]` calling, but `self.model_id` was
assigned *after* `_register_tools()` ran, so the suppression check
always returned False and ~85 redundant tokens shipped in every prompt.
Moving the `model_id = model_id` assignment ahead of registration closes
the gap; a regression test asserts the `==== RESPONSE FORMAT ====` block
does not appear in a tool-calling agent's system prompt.
- **Loop-break helper missed the native path.** The shared helper looked
at `step_results[-1]` to detect a failure streak, but the
native-tool-call path appends to `previous_outputs` instead (wrapper
dicts). On native callers the helper saw an empty list, missed every
failure, and returned `"Task completed"`. The fix unwraps
`previous_outputs` at the call site; the regression test exercises the
helper with a sequence of error results.
- **Eval rubric conflated pipeline and hardware.** Some MCP services
wrap real operation failures in a `status: success` envelope with the
failure buried in `data.content[*].text`. On dev hardware where
vendor-side features don't all work, the judge graded the agent as
failing even when it picked the right tool. The new STEP 0 in
`judge_turn.md` overrides the rubric for `verbatim`-tagged scenarios —
`correctness = 10` if the right tool was invoked, `0` if the wrong tool
was, regardless of underlying op success.

Eight new unit-test files cover the sanitiser matrix, loop-break helper,
candidate-list invariant, scenario validation, and `--iterations` flag.


### Dedicated Browser and Analyst Agents

The Agent UI's web and data entries previously routed to `ChatAgent`
profiles, which meant they carried the full monolithic agent surface
instead of the focused tool sets the use cases actually need. PR
[amd#1070](amd#1070) adds dedicated
`BrowserAgent` and `AnalystAgent` implementations and wires the built-in
web/data registrations (plus their `lite` variants) to them. Two new CLI
subcommands ship alongside: `gaia browse` for the browser flow and `gaia
analyze` for the analyst flow. Both compose the relevant tool mixins
explicitly rather than inheriting everything from the ChatAgent shim.


### Hardware-Requirement Validation for Agents

Agents can now declare a hardware capability tier via `REQUIRED_HARDWARE
= HardwareRequirement(min_device=...)` (PR
[amd#1057](amd#1057)). At agent startup,
`LemonadeManager.ensure_ready(required_min_device=...)` queries the
running Lemonade server through `LemonadeClient.get_system_info()` and
raises `HardwareRequirementError` if the host's reported device tier
does not satisfy the declaration. NPU-only or dGPU-only agents fail fast
at construction time instead of silently degrading at first inference.

This is Phase 1 — validation only. The resolved `recipe` is computed and
logged for debugging but is *not* applied to the Lemonade server startup
path; a follow-up will wire the resolved recipe through if the project
chooses to.


### `LEMONADE_API_KEY` for Authenticated Remote Lemonade

Before this release, GAIA could not connect to a remote Lemonade Server
protected by an API key — every request returned `401` regardless of the
user's configuration. PR [amd#1149](amd#1149)
(closes [amd#1139](amd#1139)) threads
`LEMONADE_API_KEY` (from `.env` or the shell environment) as
`Authorization: Bearer <key>` through every Lemonade-bound HTTP path in
GAIA: the central `LemonadeClient._send_request`, the four
`requests`-bypass sites, both OpenAI-SDK constructor sites,
`LemonadeProvider`, `VLMClient`, the Agent UI router (`system.py`),
Agent UI chat helpers, the server startup probes, and the base `Agent`
health probe.

Behaviour is fully additive — when the env var is unset, every call path
behaves identically to v0.18.1. A wrong or missing key produces a
fixed-string error naming `LEMONADE_API_KEY` (the response body is
intentionally not echoed back, to avoid leaking reflected
`Authorization` headers from misconfigured proxies).


### CI Auto-Fix for Bulletproof Bug Issues

PR [amd#1159](amd#1159) adds a Claude-powered
auto-fix job to `.github/workflows/claude.yml` that runs in parallel
with the existing `issue-handler` triage. When a new issue lands with
the `bug` label, Claude reads the report, and if the fix passes a strict
"bulletproof" bar — 1–2 files touched, fewer than 50 lines changed, 100%
confidence, no hardware-dependent verification needed — it implements
the change, validates with `python util/lint.py` and the relevant unit
tests, opens a PR, and posts the PR link plus step-by-step verification
instructions back on the originating issue. Bug reports that don't meet
the bar still get the standard triage comment from `issue-handler`; the
auto-fixer exits silently for the rest.


## Bug Fixes

- **BrowserAgent and AnalystAgent crashed instantly in the Agent UI**
(PR [amd#1202](amd#1202)) — Selecting either
of the new split agents and sending any message raised `AttributeError:
'<Agent>' object has no attribute '_mcp_manager'`. The MCP client
mixin's optional attribute was never initialised on the split agents,
and `get_mcp_status_report()` — invoked on every `/api/chat/send` — hit
the undefined dereference. The two-layer fix adds a class-level
`_mcp_manager: Optional[MCPClientManager] = None` on `MCPClientMixin`
(covering every future agent that inherits it) plus explicit per-agent
initialisation in the five affected agents (documenting intent at the
point of use). CLI paths were unaffected — only the Agent UI's
`/api/chat/send` triggered the bug.
- **`LEMONADE_BASE_URL` env var normalisation** (PR
[amd#1160](amd#1160)) — Setting
`LEMONADE_BASE_URL` to a value without the trailing `/api/v1` suffix
produced 404s deep in the request pipeline. The variable is now
normalised on load so both `http://host:8000` and
`http://host:8000/api/v1` resolve to the same canonical form.
- **Custom agents on disk now visible to the Agent UI** (PR
[amd#1138](amd#1138)) — `~/.gaia/agents/`
registrations were not surfacing to the Agent UI's agent list because
the registry discovery pass skipped the disk source on cold start. The
fix lists custom-directory agents alongside the built-ins on every
request.
- **`pr-review` CI re-enabled and credit-resilient** (PR
[amd#1163](amd#1163)) — The Claude-based
`pr-review` job had been disabled after an Anthropic credit window; all
Claude-backed jobs now treat 429 quota errors as non-fatal warnings so
CI keeps moving when the project hits its quota.
- **Silent skips in `test_sdk.py` removed** (PR
[amd#1190](amd#1190)) — Tests that depended on
an environment fixture were silently `pytest.skip()`-ing instead of
being explicitly conditional. The skips are now gated on the actual
fixture and surface as `XFAIL` when intentionally inapplicable. Closes
the first slice of [amd#877](amd#877).
- **`refresh-context7` fails loudly on unexpected status** (PR
[amd#1073](amd#1073)) — The terminal job of
the publish workflow previously masked non-cooldown HTTP responses as
"OK". It now distinguishes the known HTTP 400 cooldown window from any
other status code, so a regression that breaks the Context7 refresh is
no longer indistinguishable from the documented cooldown.


## Tooling & Docs

- **CLI smoke-test for every subcommand and console script** (PR
[amd#1193](amd#1193)) — Every `gaia
<subcommand>` and every console script declared in `setup.py` is now
exercised with `--help` in CI, catching import-time regressions and
shadowed entry points before they ship.
- **Fail-path coverage for `GovernedAgentMixin` and `CheckpointBridge`**
(PR [amd#1161](amd#1161)) — Adds unit tests
for the error/abort branches of the governance layer that were
previously only exercised on the happy path.
- **Custom-agent MCP harness for installer testing** (PR
[amd#1069](amd#1069)) — A reproducible
installer-level MCP harness for custom agents, so installer-affecting
changes are tested against the real agent-registration path rather than
mocks.
- **Dependabot revived, agent-ui entry added, patch auto-merge shipped**
(PR [amd#1191](amd#1191)) — Dependabot PRs are
flowing again, the Agent UI npm workspace is now covered, and patch-bump
PRs that pass CI auto-merge.


## Full Changelog

**17 commits** since v0.18.1:

- `6c6e4c34` — fix(agents): unbreak BrowserAgent/AnalystAgent in Agent
UI (amd#1202)
- `6379e183` — feat(agent-hub): discover installed agent entry points
(amd#1187)
- `a79acc88` — test(cli): smoke-test every subcommand and console script
with --help (amd#1193)
- `f7a75902` — ci(dependabot): revive PRs, add agent-ui entry, ship
patch auto-merge (amd#1191)
- `70d75b70` — fix(tests): remove silent skips in test_sdk.py (amd#877 Part
A) (amd#1190)
- `f8b2c1ab` — feat: MCP tool calling reliability test framework (amd#718)
- `f4270687` — feat(agent-hub): Agent Hub UI + platform plan + hub
skeleton (amd#1103)
- `6ef1feee` — fix(llm): normalize LEMONADE_BASE_URL env var to include
/api/v1 suffix (amd#1160)
- `72b77167` — fix(ci): re-enable pr-review and make all Claude jobs
credit-resilient (amd#1163)
- `b46bf654` — fix(agent-ui): list custom agents from disk (amd#1138)
- `63aedb47` — test: add fail-path coverage for GovernedAgentMixin and
CheckpointBridge (amd#1161)
- `7b8f22c0` — feat(llm): support LEMONADE_API_KEY for authenticated
remote Lemonade (amd#1149)
- `b22fa73d` — feat(ci): auto-fix job for bulletproof bug issues (amd#1159)
- `6b7b9e7d` — fix(ci): make refresh-context7 fail loudly on unexpected
status (amd#1073)
- `e2d4e2d7` — feat(sdk): hardware requirement validation for agents
(amd#1057)
- `1a73dcc5` — feat(agents): add browser and analyst agents (amd#1070)
- `2554424b` — test(installer): add custom agent MCP harness (amd#1069)

Full Changelog:
[v0.18.1...v0.19.0](amd/gaia@v0.18.1...v0.19.0)

## Release checklist

- [x] `util/validate_release_notes.py docs/releases/v0.19.0.mdx` passes
- [x] `src/gaia/version.py` → `0.19.0`
- [x] `src/gaia/apps/webui/package.json` → `0.19.0`
- [x] Navbar label in `docs/docs.json` → `v0.19.0 · Lemonade 10.2.0`
- [x] All 17 commits in range (v0.18.1..HEAD) are represented in the
notes
- [ ] Review from @kovtcharov-amd addressed