open/portfolio-optimiser
1
0
Fork 0
Code Issues Releases 4 Activity
45 commits 1 branch 4 tags 10 MiB
Commit graph

4 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
6ef4efcdd1 docs(fase2): trekreview review.md — verdict BLOCK (2 BLOCKER, 5 MAJOR, 1 MINOR) 
Independent post-hoc review (high-effort) of the Fase 2 vertical slice
(scope 9973d9f..308b553, 32 files). Two independent reviewers converged,
ground-truth-verified against source:

- F1 BLOCKER (run.py:124): maker-checker debate output discarded; the
  validated proposal comes from a separate generate_via_llm call.
- F2 BLOCKER (budget.py:81): BudgetMiddleware defined+tested but never
  wired onto the debate; the NFR short-circuit path is absent.
- F7/F3/F4/F8/F5 MAJOR, F9 MINOR.

The slice's three load-bearing seams are built + unit-tested but not
connected by the orchestrator; the green e2e suite asserts proposal
shape only. Fase 2 not closed — awaits operator decision.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
 2026-06-24 15:10:07 +02:00
Kjell Tore Guttormsen
9973d9fe58 docs(fase2): /trekplan — adversarial-reviewed implementation plan [skip-docs] 
14-step plan composing the four Fase 1 spikes into a src/ vertical slice
(debate -> blocking validator -> two-layer HITL + provenance -> ExpeL learning),
deterministic-core-first, on real chat clients in both profiles. Grounded in the
3 research briefs + installed-1.9.0-source introspection (7 exploration agents).

Adversarial review: plan-critic REVISE (3 blockers/7 major/4 minor) -> all
addressed; scope-guardian ALIGNED (0 creep, 9/9 criteria mapped, 6/6 Non-Goals
honored). Key revisions: in-process retriever-as-tool MVP path (mcp dep
conditional/GA-only); two-layer HITL capture + stable Verdict.id minting;
extend_instructions retired by a REAL SessionContext test; TextSpan ownership +
wave re-ordering; budget None-as-hard-fail with synthetic-usage test double;
self_repair token-bound in the generate loop (validator.py frozen); global
stop-on-failure rule. gemini-bridge Pass 2 unavailable (MCP SDK broke).
plan-validator strict 0 errors. brief research_status pending to complete.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
 2026-06-24 12:58:33 +02:00
Kjell Tore Guttormsen
c72730941e docs(fase2): 3 /trekresearch briefs — installed-source-verified [skip-docs] 
Topic 1 (HITL): native HITL is GA (ctx.request_info/@response_handler/
run(responses=); GroupChatBuilder.with_request_info → AgentApprovalExecutor),
but durable checkpoint-resume is fragile (open #5818/#6127/#6372 into 1.9.0)
→ capture verdict out-of-band in VerdictStore, defer checkpointing off MVP path.

Topic 2 (MCP citation): REVERSES brief lean — official server-filesystem cannot
cite (raw text + bare paths) → build thin custom local-folder MCP server
returning {file,locator,snippet,score} over a framework-agnostic in-process
retriever (D7 seam). Corrected docs error: ContextProvider(source_id) +
before_run/after_run + extend_instructions(source_id,...) DO exist in 1.9.0.

Topic 3 (local chat client): use OpenAIChatCompletionClient(base_url) NON-STREAMING
(not OpenAIChatClient/Responses) — installed, 0 new deps, UsageDetails None-safe
and populated non-streaming. Native OllamaChatClient is --pre fallback (spike-gated).
validator-as-retry mitigates weak small-model tool-calling; Intel-CPU = plumbing only.

All grounded in installed 1.9.0 source (source wins over Learn docs). Gemini
bridge unavailable (MCP SDK predates Google May-2026 API change).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
 2026-06-24 12:33:42 +02:00
Kjell Tore Guttormsen
78e03c3254 docs(fase2): /trekbrief — gated MVP vertical-slice brief (6/6) [skip-docs] 
Fase 2 started. Brief for the MVP vertical slice (one synthetic project
end-to-end on MAF 1.9.0: debate -> blocking validator -> two-layer HITL +
provenance -> ExpeL learning) produced via /trekbrief from documented intent
(incremental-plan §Fase 2 + capability-map §1/§5 + Fase 1 findings), not live
Q&A per the project operating model. framing=preserve; phase_signals=high/opus.

Brief-reviewer gate passed 6/6 (all dimensions 5; verdict PROCEED_WITH_RISKS)
after 2 iterations: iter 1 flagged a no-op token-accounting criterion and a
false-positive on research-field order; 3 derivable refinements applied
(retargeted the UsageDetails assertion, added Open Questions for the concrete
local model + Foundry deployment names, added a topic-count note). Validator
green (0 errors/warnings).

3 research topics identified (gaps the capability-map did not resolve): native
HITL in MAF workflows, local_folder via MCPStdioTool + citation provenance, and
a real local-profile chat client (spikes used only FakeChatClient). Manual path:
stopped at the brief as a gated checkpoint; research must run before /trekplan.

.gitignore: ignore generated .html annotation + progress.json render-derivatives
under .claude/projects/ (the .md sources stay tracked).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
 2026-06-24 11:56:57 +02:00